From 4fb8ecd7fc69f9e6aa6f89b339b6bb474a50e718 Mon Sep 17 00:00:00 2001
From: Yoshi Automation
Date: Tue, 28 Jul 2026 07:56:25 +0000
Subject: [PATCH 01/59] chore: update docs/dyn/index.md
---
docs/dyn/index.md | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/docs/dyn/index.md b/docs/dyn/index.md
index dc4fca983d..bc55431ed6 100644
--- a/docs/dyn/index.md
+++ b/docs/dyn/index.md
@@ -50,6 +50,18 @@
* [v1](http://googleapis.github.io/google-api-python-client/docs/dyn/advisorynotifications_v1.html)
+## agentidentity
+* [v1](http://googleapis.github.io/google-api-python-client/docs/dyn/agentidentity_v1.html)
+* [v1alpha](http://googleapis.github.io/google-api-python-client/docs/dyn/agentidentity_v1alpha.html)
+* [v1beta](http://googleapis.github.io/google-api-python-client/docs/dyn/agentidentity_v1beta.html)
+
+
+## agentidentitycredentials
+* [v1](http://googleapis.github.io/google-api-python-client/docs/dyn/agentidentitycredentials_v1.html)
+* [v1alpha](http://googleapis.github.io/google-api-python-client/docs/dyn/agentidentitycredentials_v1alpha.html)
+* [v1beta](http://googleapis.github.io/google-api-python-client/docs/dyn/agentidentitycredentials_v1beta.html)
+
+
## agentregistry
* [v1](http://googleapis.github.io/google-api-python-client/docs/dyn/agentregistry_v1.html)
* [v1alpha](http://googleapis.github.io/google-api-python-client/docs/dyn/agentregistry_v1alpha.html)
From e574f10b82253855acb805cc9a33f60d970807c5 Mon Sep 17 00:00:00 2001
From: Yoshi Automation
Date: Tue, 28 Jul 2026 07:56:26 +0000
Subject: [PATCH 02/59] feat(accesscontextmanager): update the api
#### accesscontextmanager:v1
The following keys were added:
- schemas.GcpUserAccessBinding.properties.principal.$ref (Total Keys: 1)
- schemas.GcpUserAccessBinding.properties.restrictedClientApplications.deprecated (Total Keys: 1)
- schemas.Principal (Total Keys: 4)
---
...1.organizations.gcpUserAccessBindings.html | 24 +++++++++++++++----
.../documents/accesscontextmanager.v1.json | 24 +++++++++++++++++--
2 files changed, 42 insertions(+), 6 deletions(-)
diff --git a/docs/dyn/accesscontextmanager_v1.organizations.gcpUserAccessBindings.html b/docs/dyn/accesscontextmanager_v1.organizations.gcpUserAccessBindings.html
index bde399dcf6..7291bb9da5 100644
--- a/docs/dyn/accesscontextmanager_v1.organizations.gcpUserAccessBindings.html
+++ b/docs/dyn/accesscontextmanager_v1.organizations.gcpUserAccessBindings.html
@@ -119,7 +119,11 @@ Method Details
],
"groupKey": "A String", # Optional. Immutable. Google Group id whose users are subject to this binding's restrictions. See "id" in the [Google Workspace Directory API's Group Resource] (https://developers.google.com/admin-sdk/directory/v1/reference/groups#resource). If a group's email address/alias is changed, this resource will continue to point at the changed group. This field does not accept group email addresses or aliases. Example: "01d520gv4vjcrht"
"name": "A String", # Immutable. Assigned by the server during creation. The last segment has an arbitrary length and has only URI unreserved characters (as defined by [RFC 3986 Section 2.3](https://tools.ietf.org/html/rfc3986#section-2.3)). Should not be specified by the client during creation. Example: "organizations/256/gcpUserAccessBindings/b3-BhcX_Ud5N"
- "restrictedClientApplications": [ # Optional. A list of applications that are subject to this binding's restrictions. If the list is empty, the binding restrictions will universally apply to all applications.
+ "principal": { # The comprehensive identity container supporting identities including groups, service accounts and federated identities. Only one of them can be set to create an access binding. # Optional. Immutable. The principal that is subject to the access policies in this policy binding.
+ "serviceAccount": "A String", # Immutable. Service account email used to assign policies to a specific service account. If a service account is subject to multiple policies (e.g., if there is a policy for all service accounts in a project and a policy for the service account), the closest (i.e. the most specific) dry-run policy will be used for the dry-run functionality and the closest policy will be used for the enforcement.
+ "serviceAccountProjectNumber": "A String", # Immutable. Cloud project number used to assign policies to all service accounts owned by the project.
+ },
+ "restrictedClientApplications": [ # Optional. Deprecated: use scoped_access_settings instead. A list of applications that are subject to this binding's restrictions. If the list is empty, the binding restrictions will universally apply to all applications.
{ # An application that accesses Google Cloud APIs.
"clientId": "A String", # The OAuth client ID of the application.
"name": "A String", # The name of the application. Example: "Cloud Console"
@@ -257,7 +261,11 @@ Method Details
],
"groupKey": "A String", # Optional. Immutable. Google Group id whose users are subject to this binding's restrictions. See "id" in the [Google Workspace Directory API's Group Resource] (https://developers.google.com/admin-sdk/directory/v1/reference/groups#resource). If a group's email address/alias is changed, this resource will continue to point at the changed group. This field does not accept group email addresses or aliases. Example: "01d520gv4vjcrht"
"name": "A String", # Immutable. Assigned by the server during creation. The last segment has an arbitrary length and has only URI unreserved characters (as defined by [RFC 3986 Section 2.3](https://tools.ietf.org/html/rfc3986#section-2.3)). Should not be specified by the client during creation. Example: "organizations/256/gcpUserAccessBindings/b3-BhcX_Ud5N"
- "restrictedClientApplications": [ # Optional. A list of applications that are subject to this binding's restrictions. If the list is empty, the binding restrictions will universally apply to all applications.
+ "principal": { # The comprehensive identity container supporting identities including groups, service accounts and federated identities. Only one of them can be set to create an access binding. # Optional. Immutable. The principal that is subject to the access policies in this policy binding.
+ "serviceAccount": "A String", # Immutable. Service account email used to assign policies to a specific service account. If a service account is subject to multiple policies (e.g., if there is a policy for all service accounts in a project and a policy for the service account), the closest (i.e. the most specific) dry-run policy will be used for the dry-run functionality and the closest policy will be used for the enforcement.
+ "serviceAccountProjectNumber": "A String", # Immutable. Cloud project number used to assign policies to all service accounts owned by the project.
+ },
+ "restrictedClientApplications": [ # Optional. Deprecated: use scoped_access_settings instead. A list of applications that are subject to this binding's restrictions. If the list is empty, the binding restrictions will universally apply to all applications.
{ # An application that accesses Google Cloud APIs.
"clientId": "A String", # The OAuth client ID of the application.
"name": "A String", # The name of the application. Example: "Cloud Console"
@@ -336,7 +344,11 @@ Method Details
],
"groupKey": "A String", # Optional. Immutable. Google Group id whose users are subject to this binding's restrictions. See "id" in the [Google Workspace Directory API's Group Resource] (https://developers.google.com/admin-sdk/directory/v1/reference/groups#resource). If a group's email address/alias is changed, this resource will continue to point at the changed group. This field does not accept group email addresses or aliases. Example: "01d520gv4vjcrht"
"name": "A String", # Immutable. Assigned by the server during creation. The last segment has an arbitrary length and has only URI unreserved characters (as defined by [RFC 3986 Section 2.3](https://tools.ietf.org/html/rfc3986#section-2.3)). Should not be specified by the client during creation. Example: "organizations/256/gcpUserAccessBindings/b3-BhcX_Ud5N"
- "restrictedClientApplications": [ # Optional. A list of applications that are subject to this binding's restrictions. If the list is empty, the binding restrictions will universally apply to all applications.
+ "principal": { # The comprehensive identity container supporting identities including groups, service accounts and federated identities. Only one of them can be set to create an access binding. # Optional. Immutable. The principal that is subject to the access policies in this policy binding.
+ "serviceAccount": "A String", # Immutable. Service account email used to assign policies to a specific service account. If a service account is subject to multiple policies (e.g., if there is a policy for all service accounts in a project and a policy for the service account), the closest (i.e. the most specific) dry-run policy will be used for the dry-run functionality and the closest policy will be used for the enforcement.
+ "serviceAccountProjectNumber": "A String", # Immutable. Cloud project number used to assign policies to all service accounts owned by the project.
+ },
+ "restrictedClientApplications": [ # Optional. Deprecated: use scoped_access_settings instead. A list of applications that are subject to this binding's restrictions. If the list is empty, the binding restrictions will universally apply to all applications.
{ # An application that accesses Google Cloud APIs.
"clientId": "A String", # The OAuth client ID of the application.
"name": "A String", # The name of the application. Example: "Cloud Console"
@@ -423,7 +435,11 @@ Method Details
],
"groupKey": "A String", # Optional. Immutable. Google Group id whose users are subject to this binding's restrictions. See "id" in the [Google Workspace Directory API's Group Resource] (https://developers.google.com/admin-sdk/directory/v1/reference/groups#resource). If a group's email address/alias is changed, this resource will continue to point at the changed group. This field does not accept group email addresses or aliases. Example: "01d520gv4vjcrht"
"name": "A String", # Immutable. Assigned by the server during creation. The last segment has an arbitrary length and has only URI unreserved characters (as defined by [RFC 3986 Section 2.3](https://tools.ietf.org/html/rfc3986#section-2.3)). Should not be specified by the client during creation. Example: "organizations/256/gcpUserAccessBindings/b3-BhcX_Ud5N"
- "restrictedClientApplications": [ # Optional. A list of applications that are subject to this binding's restrictions. If the list is empty, the binding restrictions will universally apply to all applications.
+ "principal": { # The comprehensive identity container supporting identities including groups, service accounts and federated identities. Only one of them can be set to create an access binding. # Optional. Immutable. The principal that is subject to the access policies in this policy binding.
+ "serviceAccount": "A String", # Immutable. Service account email used to assign policies to a specific service account. If a service account is subject to multiple policies (e.g., if there is a policy for all service accounts in a project and a policy for the service account), the closest (i.e. the most specific) dry-run policy will be used for the dry-run functionality and the closest policy will be used for the enforcement.
+ "serviceAccountProjectNumber": "A String", # Immutable. Cloud project number used to assign policies to all service accounts owned by the project.
+ },
+ "restrictedClientApplications": [ # Optional. Deprecated: use scoped_access_settings instead. A list of applications that are subject to this binding's restrictions. If the list is empty, the binding restrictions will universally apply to all applications.
{ # An application that accesses Google Cloud APIs.
"clientId": "A String", # The OAuth client ID of the application.
"name": "A String", # The name of the application. Example: "Cloud Console"
diff --git a/googleapiclient/discovery_cache/documents/accesscontextmanager.v1.json b/googleapiclient/discovery_cache/documents/accesscontextmanager.v1.json
index 96488cc53e..b03b535f3e 100644
--- a/googleapiclient/discovery_cache/documents/accesscontextmanager.v1.json
+++ b/googleapiclient/discovery_cache/documents/accesscontextmanager.v1.json
@@ -1331,7 +1331,7 @@
}
}
},
-"revision": "20260707",
+"revision": "20260722",
"rootUrl": "https://accesscontextmanager.googleapis.com/",
"schemas": {
"AccessContextManagerOperationMetadata": {
@@ -1975,8 +1975,13 @@
"description": "Immutable. Assigned by the server during creation. The last segment has an arbitrary length and has only URI unreserved characters (as defined by [RFC 3986 Section 2.3](https://tools.ietf.org/html/rfc3986#section-2.3)). Should not be specified by the client during creation. Example: \"organizations/256/gcpUserAccessBindings/b3-BhcX_Ud5N\"",
"type": "string"
},
+"principal": {
+"$ref": "Principal",
+"description": "Optional. Immutable. The principal that is subject to the access policies in this policy binding."
+},
"restrictedClientApplications": {
-"description": "Optional. A list of applications that are subject to this binding's restrictions. If the list is empty, the binding restrictions will universally apply to all applications.",
+"deprecated": true,
+"description": "Optional. Deprecated: use scoped_access_settings instead. A list of applications that are subject to this binding's restrictions. If the list is empty, the binding restrictions will universally apply to all applications.",
"items": {
"$ref": "Application"
},
@@ -2408,6 +2413,21 @@
},
"type": "object"
},
+"Principal": {
+"description": "The comprehensive identity container supporting identities including groups, service accounts and federated identities. Only one of them can be set to create an access binding.",
+"id": "Principal",
+"properties": {
+"serviceAccount": {
+"description": "Immutable. Service account email used to assign policies to a specific service account. If a service account is subject to multiple policies (e.g., if there is a policy for all service accounts in a project and a policy for the service account), the closest (i.e. the most specific) dry-run policy will be used for the dry-run functionality and the closest policy will be used for the enforcement.",
+"type": "string"
+},
+"serviceAccountProjectNumber": {
+"description": "Immutable. Cloud project number used to assign policies to all service accounts owned by the project.",
+"type": "string"
+}
+},
+"type": "object"
+},
"PrivateServiceConnectEndpoint": {
"description": "Specifies the Private Service Connect endpoint that an API call refers to.",
"id": "PrivateServiceConnectEndpoint",
From 5d6c97491027c008af2b71a5f185116e33cefd29 Mon Sep 17 00:00:00 2001
From: Yoshi Automation
Date: Tue, 28 Jul 2026 07:56:26 +0000
Subject: [PATCH 03/59] feat(admin): update the api
#### admin:reports_v1
The following keys were added:
- schemas.Activity.properties.actor.properties.agentAttributionInfo.$ref (Total Keys: 1)
- schemas.Activity.properties.isAgenticAction.type (Total Keys: 1)
- schemas.Activity.properties.userDeviceInfo.$ref (Total Keys: 1)
- schemas.ActivityUserDeviceInfo (Total Keys: 8)
- schemas.AgentAttributionInfo (Total Keys: 9)
---
docs/dyn/admin_reports_v1.activities.html | 14 ++++
.../documents/admin.reports_v1.json | 70 ++++++++++++++++++-
2 files changed, 83 insertions(+), 1 deletion(-)
diff --git a/docs/dyn/admin_reports_v1.activities.html b/docs/dyn/admin_reports_v1.activities.html
index 12fc870483..6702bedcd0 100644
--- a/docs/dyn/admin_reports_v1.activities.html
+++ b/docs/dyn/admin_reports_v1.activities.html
@@ -168,6 +168,14 @@ Method Details
"items": [ # Each activity record in the response.
{ # JSON template for the activity resource.
"actor": { # User doing the action.
+ "agentAttributionInfo": { # Details of the AI agent that was the actor for the activity. # Details of the AI agent that was the actor for the activity.
+ "agentId": "A String", # The ID of the agent.
+ "agentName": "A String", # The user visible name of the agent.
+ "agentOwner": { # Details of the owner of the AI agent. # The owner of the agent.
+ "email": "A String", # The email of the agent owner.
+ },
+ "agentType": "A String", # Type of the agent.
+ },
"applicationInfo": { # Details of the application that was the actor for the activity.
"applicationName": "A String", # Name of the application used to perform the action.
"impersonation": True or False, # Whether the application was impersonating a user.
@@ -309,6 +317,7 @@ Method Details
"uniqueQualifier": "A String", # Unique qualifier if multiple events have the same time.
},
"ipAddress": "A String", # IP address of the user doing the action. This is the Internet Protocol (IP) address of the user when logging into Google Workspace, which may or may not reflect the user's physical location. For example, the IP address can be the user's proxy server's address or a virtual private network (VPN) address. The API supports IPv4 and IPv6.
+ "isAgenticAction": True or False, # Whether the activity was performed by an agent.
"kind": "admin#reports#activity", # The type of API resource. For an activity report, the value is `audit#activity`.
"networkInfo": { # Network information of the user doing the action. # Network information of the user doing the action.
"ipAsn": [ # IP Address of the user doing the action.
@@ -401,6 +410,11 @@ Method Details
"type": "A String", # Type of the resource - document, email, chat message
},
],
+ "userDeviceInfo": { # Device details of the user doing the action. # Device details of the user doing the action.
+ "deviceId": "A String", # Output only. Device ID of the user's device.
+ "deviceOsVersion": "A String", # Output only. Device OS version of the user's device.
+ "deviceType": "A String", # Output only. The type of the user's device.
+ },
},
],
"kind": "admin#reports#activities", # The type of API resource. For an activity report, the value is `reports#activities`.
diff --git a/googleapiclient/discovery_cache/documents/admin.reports_v1.json b/googleapiclient/discovery_cache/documents/admin.reports_v1.json
index affdac3c76..22deb74150 100644
--- a/googleapiclient/discovery_cache/documents/admin.reports_v1.json
+++ b/googleapiclient/discovery_cache/documents/admin.reports_v1.json
@@ -690,7 +690,7 @@
}
}
},
-"revision": "20260504",
+"revision": "20260722",
"rootUrl": "https://admin.googleapis.com/",
"schemas": {
"Activities": {
@@ -727,6 +727,10 @@
"actor": {
"description": "User doing the action.",
"properties": {
+"agentAttributionInfo": {
+"$ref": "AgentAttributionInfo",
+"description": "Details of the AI agent that was the actor for the activity."
+},
"applicationInfo": {
"description": "Details of the application that was the actor for the activity.",
"properties": {
@@ -964,6 +968,10 @@
"description": "IP address of the user doing the action. This is the Internet Protocol (IP) address of the user when logging into Google Workspace, which may or may not reflect the user's physical location. For example, the IP address can be the user's proxy server's address or a virtual private network (VPN) address. The API supports IPv4 and IPv6.",
"type": "string"
},
+"isAgenticAction": {
+"description": "Whether the activity was performed by an agent.",
+"type": "boolean"
+},
"kind": {
"default": "admin#reports#activity",
"description": "The type of API resource. For an activity report, the value is `audit#activity`.",
@@ -983,6 +991,10 @@
"$ref": "ResourceDetails"
},
"type": "array"
+},
+"userDeviceInfo": {
+"$ref": "ActivityUserDeviceInfo",
+"description": "Device details of the user doing the action."
}
},
"type": "object"
@@ -1034,6 +1046,62 @@
},
"type": "object"
},
+"ActivityUserDeviceInfo": {
+"description": "Device details of the user doing the action.",
+"id": "ActivityUserDeviceInfo",
+"properties": {
+"deviceId": {
+"description": "Output only. Device ID of the user's device.",
+"readOnly": true,
+"type": "string"
+},
+"deviceOsVersion": {
+"description": "Output only. Device OS version of the user's device.",
+"readOnly": true,
+"type": "string"
+},
+"deviceType": {
+"description": "Output only. The type of the user's device.",
+"readOnly": true,
+"type": "string"
+}
+},
+"type": "object"
+},
+"AgentAttributionInfo": {
+"description": "Details of the AI agent that was the actor for the activity.",
+"id": "AgentAttributionInfo",
+"properties": {
+"agentId": {
+"description": "The ID of the agent.",
+"type": "string"
+},
+"agentName": {
+"description": "The user visible name of the agent.",
+"type": "string"
+},
+"agentOwner": {
+"$ref": "AgentAttributionInfoAgentOwner",
+"description": "The owner of the agent."
+},
+"agentType": {
+"description": "Type of the agent.",
+"type": "string"
+}
+},
+"type": "object"
+},
+"AgentAttributionInfoAgentOwner": {
+"description": "Details of the owner of the AI agent.",
+"id": "AgentAttributionInfoAgentOwner",
+"properties": {
+"email": {
+"description": "The email of the agent owner.",
+"type": "string"
+}
+},
+"type": "object"
+},
"AppliedLabel": {
"description": "Details of the label applied on the resource.",
"id": "AppliedLabel",
From 34bcfc34f9d6cfcdf1442a87f782272a7c19f0c0 Mon Sep 17 00:00:00 2001
From: Yoshi Automation
Date: Tue, 28 Jul 2026 07:56:26 +0000
Subject: [PATCH 04/59] feat(agentregistry): update the api
#### agentregistry:v1alpha
The following keys were added:
- resources.projects.resources.locations.resources.publishers.methods.get (Total Keys: 11)
- resources.projects.resources.locations.resources.publishers.methods.list (Total Keys: 16)
- resources.projects.resources.locations.resources.skills.methods.create (Total Keys: 16)
- resources.projects.resources.locations.resources.skills.methods.delete (Total Keys: 15)
- resources.projects.resources.locations.resources.skills.methods.get (Total Keys: 11)
- resources.projects.resources.locations.resources.skills.methods.list (Total Keys: 20)
- resources.projects.resources.locations.resources.skills.methods.patch (Total Keys: 17)
- resources.projects.resources.locations.resources.skills.methods.search (Total Keys: 22)
- schemas.ArchiveUploadSource (Total Keys: 4)
- schemas.Frontmatter (Total Keys: 7)
- schemas.GcsSource (Total Keys: 5)
- schemas.ListPublishersResponse (Total Keys: 5)
- schemas.ListSkillsResponse (Total Keys: 7)
- schemas.Publisher (Total Keys: 8)
- schemas.SearchSkillsResponse (Total Keys: 5)
- schemas.Skill (Total Keys: 21)
---
...ntregistry_v1alpha.projects.locations.html | 10 +
...v1alpha.projects.locations.publishers.html | 164 ++++
...try_v1alpha.projects.locations.skills.html | 571 +++++++++++
...a.projects.locations.skills.revisions.html | 323 +++++++
.../documents/agentregistry.v1alpha.json | 889 +++++++++++++++++-
5 files changed, 1936 insertions(+), 21 deletions(-)
create mode 100644 docs/dyn/agentregistry_v1alpha.projects.locations.publishers.html
create mode 100644 docs/dyn/agentregistry_v1alpha.projects.locations.skills.html
create mode 100644 docs/dyn/agentregistry_v1alpha.projects.locations.skills.revisions.html
diff --git a/docs/dyn/agentregistry_v1alpha.projects.locations.html b/docs/dyn/agentregistry_v1alpha.projects.locations.html
index c2231a4eb2..ed5e77f017 100644
--- a/docs/dyn/agentregistry_v1alpha.projects.locations.html
+++ b/docs/dyn/agentregistry_v1alpha.projects.locations.html
@@ -99,11 +99,21 @@ Instance Methods
Returns the operations Resource.
+
+ publishers()
+
+Returns the publishers Resource.
+
services()
Returns the services Resource.
+
+ skills()
+
+Returns the skills Resource.
+
close()
Close httplib2 connections.
diff --git a/docs/dyn/agentregistry_v1alpha.projects.locations.publishers.html b/docs/dyn/agentregistry_v1alpha.projects.locations.publishers.html
new file mode 100644
index 0000000000..d60085930c
--- /dev/null
+++ b/docs/dyn/agentregistry_v1alpha.projects.locations.publishers.html
@@ -0,0 +1,164 @@
+
+
+
+
+Instance Methods
+
+ close()
+Close httplib2 connections.
+
+ get(name, x__xgafv=None)
+Fetches details of a specific Publisher.
+
+ list(parent, pageSize=None, pageToken=None, x__xgafv=None)
+Lists all Publishers in a location.
+
+ list_next()
+Retrieves the next page of results.
+Method Details
+
+
close()
+
Close httplib2 connections.
+
+
+
+
get(name, x__xgafv=None)
+
Fetches details of a specific Publisher.
+
+Args:
+ name: string, Required. Target publisher resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}` (required)
+ x__xgafv: string, V1 error format.
+ Allowed values
+ 1 - v1 error format
+ 2 - v2 error format
+
+Returns:
+ An object of the form:
+
+ { # Represents a verified Publisher of Skills. Prepopulated publishers include `publishers/cloud.google.com` and `publishers/workspace.google.com`.
+ "displayName": "A String", # Optional. Human readable display name of the publisher.
+ "documentationUri": "A String", # Optional. URI pointing to official publisher documentation.
+ "name": "A String", # Identifier. Resource name of the publisher. Format: `projects/{project}/locations/{location}/publishers/{publisher}`
+ "publisherTier": "A String", # Output only. The curation tier of the publisher.
+ "supportUri": "A String", # Optional. URI pointing to the support portal or email.
+ "verifiedPrefix": "A String", # Required. The verified prefix (e.g. "snowflake-", "google-") associated with this publisher. The system uses this prefix to enforce name-squatting rules during Skill registration. Must be globally unique across all publishers.
+}
+
+
+
+
list(parent, pageSize=None, pageToken=None, x__xgafv=None)
+
Lists all Publishers in a location.
+
+Args:
+ parent: string, Required. Parent location to query. Format: `projects/{project}/locations/{location}` (required)
+ pageSize: integer, Optional. Page limit size.
+ pageToken: string, Optional. Page offset token.
+ x__xgafv: string, V1 error format.
+ Allowed values
+ 1 - v1 error format
+ 2 - v2 error format
+
+Returns:
+ An object of the form:
+
+ { # Response listing Publishers.
+ "nextPageToken": "A String", # Page offset continuation token.
+ "publishers": [ # The returned list of Publishers.
+ { # Represents a verified Publisher of Skills. Prepopulated publishers include `publishers/cloud.google.com` and `publishers/workspace.google.com`.
+ "displayName": "A String", # Optional. Human readable display name of the publisher.
+ "documentationUri": "A String", # Optional. URI pointing to official publisher documentation.
+ "name": "A String", # Identifier. Resource name of the publisher. Format: `projects/{project}/locations/{location}/publishers/{publisher}`
+ "publisherTier": "A String", # Output only. The curation tier of the publisher.
+ "supportUri": "A String", # Optional. URI pointing to the support portal or email.
+ "verifiedPrefix": "A String", # Required. The verified prefix (e.g. "snowflake-", "google-") associated with this publisher. The system uses this prefix to enforce name-squatting rules during Skill registration. Must be globally unique across all publishers.
+ },
+ ],
+}
+
+
+
+
list_next()
+
Retrieves the next page of results.
+
+ Args:
+ previous_request: The request for the previous page. (required)
+ previous_response: The response from the request for the previous page. (required)
+
+ Returns:
+ A request object that you can call 'execute()' on to request the next
+ page. Returns None if there are no more items in the collection.
+
+
+
+
\ No newline at end of file
diff --git a/docs/dyn/agentregistry_v1alpha.projects.locations.skills.html b/docs/dyn/agentregistry_v1alpha.projects.locations.skills.html
new file mode 100644
index 0000000000..583af19843
--- /dev/null
+++ b/docs/dyn/agentregistry_v1alpha.projects.locations.skills.html
@@ -0,0 +1,571 @@
+
+
+
+
+Instance Methods
+
+ revisions()
+
+Returns the revisions Resource.
+
+
+ close()
+Close httplib2 connections.
+
+ create(parent, body=None, requestId=None, skillId=None, x__xgafv=None)
+========================================================================= # Skills Collection APIs Creates a Skill resource container, optionally publishing the initial SkillRevision inline in a single, atomic CRUD roundtrip.
+
+ delete(name, force=None, requestId=None, x__xgafv=None)
+Deletes a Skill container along with all its revisions.
+
+ get(name, x__xgafv=None)
+Fetches the active configuration and metadata of a Skill.
+
+ list(parent, filter=None, orderBy=None, pageSize=None, pageToken=None, x__xgafv=None)
+Lists logical Skills available in a project.
+
+ list_next()
+Retrieves the next page of results.
+
+ patch(name, body=None, requestId=None, updateMask=None, x__xgafv=None)
+Updates Skill metadata or overrides active pointers/state using REST standard PATCH.
+
+ search(parent, filter=None, pageSize=None, pageToken=None, searchString=None, searchType=None, x__xgafv=None)
+Custom deep-search method to filter by frontmatter or query SKILL.md text blobs.
+
+ search_next()
+Retrieves the next page of results.
+Method Details
+
+
close()
+
Close httplib2 connections.
+
+
+
+
create(parent, body=None, requestId=None, skillId=None, x__xgafv=None)
+
========================================================================= # Skills Collection APIs Creates a Skill resource container, optionally publishing the initial SkillRevision inline in a single, atomic CRUD roundtrip.
+
+Args:
+ parent: string, Required. The project and location location to bootstrap. (required)
+ body: object, The request body.
+ The object takes the form of:
+
+{ # Represents an Executable Agent Skill or a Composite Tool Suite (Bundle). Sibling resource with Agent and McpServer under agentregistry.googleapis.com.
+ "createTime": "A String", # Output only. Create time.
+ "defaultRevision": "A String", # Optional. The full resource name of the revision currently served by default (floating track). Format: `projects/{project}/locations/{location}/skills/{skill}/revisions/{revision}`
+ "description": "A String", # Optional. Brief summary describing the capabilities of the skill. Maximum length is 2048 characters.
+ "displayName": "A String", # Required. Human-readable display name of the skill. Maximum length is 128 characters.
+ "frontmatter": { # Structured metadata attributes extracted from the package's local SKILL.md frontmatter. # Output only. Lightweight frontmatter metadata attributes copied from the default revision.
+ "compatibility": "A String", # Optional. Environmental dependencies or local sidecars.
+ "description": "A String", # Required. Functional description.
+ "license": "A String", # Optional. License.
+ "metadata": { # Optional. Extensible flattened map mapping custom tags, authors, and version parameters.
+ "a_key": "A String",
+ },
+ "name": "A String", # Required. The name of the skill.
+ },
+ "initialRevision": { # Represents an immutable, versioned snapshot of a Skill package. # Optional. Input only. Optional nested initial revision payload to support standard one-shot creation. The server processes this field on input during creation but must never return it in responses.
+ "archiveUploadSource": { # Direct write-only raw archive payload upload. # Optional. Immutable. Direct write-only raw archive upload source.
+ "archiveContent": "A String", # Required. Input only. Write-only raw ZIP/TAR archive payload bytes containing the skill package.
+ },
+ "createTime": "A String", # Output only. Revision creation timestamp.
+ "frontmatter": { # Structured metadata attributes extracted from the package's local SKILL.md frontmatter. # Output only. Extracted YAML frontmatter configuration snapshot.
+ "compatibility": "A String", # Optional. Environmental dependencies or local sidecars.
+ "description": "A String", # Required. Functional description.
+ "license": "A String", # Optional. License.
+ "metadata": { # Optional. Extensible flattened map mapping custom tags, authors, and version parameters.
+ "a_key": "A String",
+ },
+ "name": "A String", # Required. The name of the skill.
+ },
+ "gcsSource": { # Specifications for Cloud Storage objects. # Optional. Immutable. Cloud Storage object generation URI.
+ "generation": "A String", # Optional. Cloud Storage object generation ID. If not specified, the latest generation is used.
+ "uri": "A String", # Required. Cloud Storage object URI. Format: `gs://{bucket_name}/{object_name}`
+ },
+ "name": "A String", # Identifier. Resource name of the SkillRevision. Format: `projects/{project}/locations/{location}/skills/{skill}/revisions/{revision}`
+ "sha256Hash": "A String", # Output only. Cryptographic SHA-256 integrity and deduplication digest of the payload zip.
+ "sizeBytes": "A String", # Output only. Size of the compiled zip payload in bytes (assists client download progress).
+ "state": "A String", # Output only. The system-managed lifecycle state of this revision.
+ "uid": "A String", # Output only. Universally unique identifier (UUID4) for the skill revision.
+ },
+ "name": "A String", # Identifier. Resource name of the Skill. Format: `projects/{project}/locations/{location}/skills/{skill}` The `{skill}` segment acts as the resource ID. If the skill is associated with a Publisher, this segment typically uses a hyphenated namespace prefix corresponding to the publisher (e.g., `google-workspace-create-docs`).
+ "publisher": "A String", # Optional. The publisher resource associated with this skill. Format: `projects/{project}/locations/{location}/publishers/{publisher}` The publisher dictates the allowed namespace prefixes for the skill's name and logical `skill_id` (e.g., Publisher `google` authorizes the `google-*` prefix).
+ "skillId": "A String", # Output only. A stable, globally unique logical identifier for the skill. It is securely constructed by the backend by combining the associated `publisher`'s verified namespace and the skill's resource ID to enforce strict ownership. For example, the prefix `google-` is reserved exclusively for first-party Google publishers to prevent namespace squatting. Example: `urn:skill:google-workspace:create-docs`
+ "state": "A String", # Output only. The system-managed state of the skill.
+ "targetState": "A String", # Required. User-managed target state of the skill.
+ "type": "A String", # Required. Structural deployment type (SIMPLE leaf vs COMPOSITE bundle).
+ "uid": "A String", # Output only. Universally unique identifier (UUID4) for the logical container.
+ "updateTime": "A String", # Output only. Update time.
+}
+
+ requestId: string, Optional. Signed UUID request idempotency token.
+ skillId: string, Required. Custom, user-defined unique container identifier. Must be unique within the parent project and location. This value should be 4-63 characters, and valid characters are `/a-z-/`.
+ x__xgafv: string, V1 error format.
+ Allowed values
+ 1 - v1 error format
+ 2 - v2 error format
+
+Returns:
+ An object of the form:
+
+ { # This resource represents a long-running operation that is the result of a network API call.
+ "done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
+ "error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
+ "code": 42, # The status code, which should be an enum value of google.rpc.Code.
+ "details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
+ {
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+ ],
+ "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
+ },
+ "metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+ "name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
+ "response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+}
+
+
+
+
delete(name, force=None, requestId=None, x__xgafv=None)
+
Deletes a Skill container along with all its revisions.
+
+Args:
+ name: string, Required. Target Skill container name to remove. (required)
+ force: boolean, Optional. If set to true, any child SkillRevisions under this Skill will also be deleted. Otherwise, the request will only succeed if the Skill has no child SkillRevisions.
+ requestId: string, Optional. Signed UUID request idempotency token.
+ x__xgafv: string, V1 error format.
+ Allowed values
+ 1 - v1 error format
+ 2 - v2 error format
+
+Returns:
+ An object of the form:
+
+ { # This resource represents a long-running operation that is the result of a network API call.
+ "done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
+ "error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
+ "code": 42, # The status code, which should be an enum value of google.rpc.Code.
+ "details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
+ {
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+ ],
+ "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
+ },
+ "metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+ "name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
+ "response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+}
+
+
+
+
get(name, x__xgafv=None)
+
Fetches the active configuration and metadata of a Skill.
+
+Args:
+ name: string, Required. Target resource container name. (required)
+ x__xgafv: string, V1 error format.
+ Allowed values
+ 1 - v1 error format
+ 2 - v2 error format
+
+Returns:
+ An object of the form:
+
+ { # Represents an Executable Agent Skill or a Composite Tool Suite (Bundle). Sibling resource with Agent and McpServer under agentregistry.googleapis.com.
+ "createTime": "A String", # Output only. Create time.
+ "defaultRevision": "A String", # Optional. The full resource name of the revision currently served by default (floating track). Format: `projects/{project}/locations/{location}/skills/{skill}/revisions/{revision}`
+ "description": "A String", # Optional. Brief summary describing the capabilities of the skill. Maximum length is 2048 characters.
+ "displayName": "A String", # Required. Human-readable display name of the skill. Maximum length is 128 characters.
+ "frontmatter": { # Structured metadata attributes extracted from the package's local SKILL.md frontmatter. # Output only. Lightweight frontmatter metadata attributes copied from the default revision.
+ "compatibility": "A String", # Optional. Environmental dependencies or local sidecars.
+ "description": "A String", # Required. Functional description.
+ "license": "A String", # Optional. License.
+ "metadata": { # Optional. Extensible flattened map mapping custom tags, authors, and version parameters.
+ "a_key": "A String",
+ },
+ "name": "A String", # Required. The name of the skill.
+ },
+ "initialRevision": { # Represents an immutable, versioned snapshot of a Skill package. # Optional. Input only. Optional nested initial revision payload to support standard one-shot creation. The server processes this field on input during creation but must never return it in responses.
+ "archiveUploadSource": { # Direct write-only raw archive payload upload. # Optional. Immutable. Direct write-only raw archive upload source.
+ "archiveContent": "A String", # Required. Input only. Write-only raw ZIP/TAR archive payload bytes containing the skill package.
+ },
+ "createTime": "A String", # Output only. Revision creation timestamp.
+ "frontmatter": { # Structured metadata attributes extracted from the package's local SKILL.md frontmatter. # Output only. Extracted YAML frontmatter configuration snapshot.
+ "compatibility": "A String", # Optional. Environmental dependencies or local sidecars.
+ "description": "A String", # Required. Functional description.
+ "license": "A String", # Optional. License.
+ "metadata": { # Optional. Extensible flattened map mapping custom tags, authors, and version parameters.
+ "a_key": "A String",
+ },
+ "name": "A String", # Required. The name of the skill.
+ },
+ "gcsSource": { # Specifications for Cloud Storage objects. # Optional. Immutable. Cloud Storage object generation URI.
+ "generation": "A String", # Optional. Cloud Storage object generation ID. If not specified, the latest generation is used.
+ "uri": "A String", # Required. Cloud Storage object URI. Format: `gs://{bucket_name}/{object_name}`
+ },
+ "name": "A String", # Identifier. Resource name of the SkillRevision. Format: `projects/{project}/locations/{location}/skills/{skill}/revisions/{revision}`
+ "sha256Hash": "A String", # Output only. Cryptographic SHA-256 integrity and deduplication digest of the payload zip.
+ "sizeBytes": "A String", # Output only. Size of the compiled zip payload in bytes (assists client download progress).
+ "state": "A String", # Output only. The system-managed lifecycle state of this revision.
+ "uid": "A String", # Output only. Universally unique identifier (UUID4) for the skill revision.
+ },
+ "name": "A String", # Identifier. Resource name of the Skill. Format: `projects/{project}/locations/{location}/skills/{skill}` The `{skill}` segment acts as the resource ID. If the skill is associated with a Publisher, this segment typically uses a hyphenated namespace prefix corresponding to the publisher (e.g., `google-workspace-create-docs`).
+ "publisher": "A String", # Optional. The publisher resource associated with this skill. Format: `projects/{project}/locations/{location}/publishers/{publisher}` The publisher dictates the allowed namespace prefixes for the skill's name and logical `skill_id` (e.g., Publisher `google` authorizes the `google-*` prefix).
+ "skillId": "A String", # Output only. A stable, globally unique logical identifier for the skill. It is securely constructed by the backend by combining the associated `publisher`'s verified namespace and the skill's resource ID to enforce strict ownership. For example, the prefix `google-` is reserved exclusively for first-party Google publishers to prevent namespace squatting. Example: `urn:skill:google-workspace:create-docs`
+ "state": "A String", # Output only. The system-managed state of the skill.
+ "targetState": "A String", # Required. User-managed target state of the skill.
+ "type": "A String", # Required. Structural deployment type (SIMPLE leaf vs COMPOSITE bundle).
+ "uid": "A String", # Output only. Universally unique identifier (UUID4) for the logical container.
+ "updateTime": "A String", # Output only. Update time.
+}
+
+
+
+
list(parent, filter=None, orderBy=None, pageSize=None, pageToken=None, x__xgafv=None)
+
Lists logical Skills available in a project.
+
+Args:
+ parent: string, Required. Parent value for ListSkillsRequest (required)
+ filter: string, Optional. Use this field to specify filter criteria on list results. Filter expressions can be used to restrict results based upon filterable fields, where equality operators can be used. See [instructions](https://docs.cloud.google.com/agent-registry/search-agents-and-tools) for more details. Allowed operators: `=`, `<`, `>`, `NOT`, `AND`, `OR`, and `()`. | Field | `=` | `<`, `>` | |--------------|-----|----------| | state | Yes | No | | targetState | Yes | No | | createTime | Yes | Yes | | updateTime | Yes | Yes | Examples: * `state=ACTIVE` to restrict results to skills in the `ACTIVE` state.
+ orderBy: string, Optional. Hint for how to order the results
+ pageSize: integer, Optional. Requested page size. Server may return fewer items than requested. If unspecified, server will pick an appropriate default.
+ pageToken: string, Optional. A token identifying a page of results the server should return.
+ x__xgafv: string, V1 error format.
+ Allowed values
+ 1 - v1 error format
+ 2 - v2 error format
+
+Returns:
+ An object of the form:
+
+ { # Response structure listing logical Skills.
+ "nextPageToken": "A String", # Page continuation continuation token.
+ "skills": [ # Returned container list.
+ { # Represents an Executable Agent Skill or a Composite Tool Suite (Bundle). Sibling resource with Agent and McpServer under agentregistry.googleapis.com.
+ "createTime": "A String", # Output only. Create time.
+ "defaultRevision": "A String", # Optional. The full resource name of the revision currently served by default (floating track). Format: `projects/{project}/locations/{location}/skills/{skill}/revisions/{revision}`
+ "description": "A String", # Optional. Brief summary describing the capabilities of the skill. Maximum length is 2048 characters.
+ "displayName": "A String", # Required. Human-readable display name of the skill. Maximum length is 128 characters.
+ "frontmatter": { # Structured metadata attributes extracted from the package's local SKILL.md frontmatter. # Output only. Lightweight frontmatter metadata attributes copied from the default revision.
+ "compatibility": "A String", # Optional. Environmental dependencies or local sidecars.
+ "description": "A String", # Required. Functional description.
+ "license": "A String", # Optional. License.
+ "metadata": { # Optional. Extensible flattened map mapping custom tags, authors, and version parameters.
+ "a_key": "A String",
+ },
+ "name": "A String", # Required. The name of the skill.
+ },
+ "initialRevision": { # Represents an immutable, versioned snapshot of a Skill package. # Optional. Input only. Optional nested initial revision payload to support standard one-shot creation. The server processes this field on input during creation but must never return it in responses.
+ "archiveUploadSource": { # Direct write-only raw archive payload upload. # Optional. Immutable. Direct write-only raw archive upload source.
+ "archiveContent": "A String", # Required. Input only. Write-only raw ZIP/TAR archive payload bytes containing the skill package.
+ },
+ "createTime": "A String", # Output only. Revision creation timestamp.
+ "frontmatter": { # Structured metadata attributes extracted from the package's local SKILL.md frontmatter. # Output only. Extracted YAML frontmatter configuration snapshot.
+ "compatibility": "A String", # Optional. Environmental dependencies or local sidecars.
+ "description": "A String", # Required. Functional description.
+ "license": "A String", # Optional. License.
+ "metadata": { # Optional. Extensible flattened map mapping custom tags, authors, and version parameters.
+ "a_key": "A String",
+ },
+ "name": "A String", # Required. The name of the skill.
+ },
+ "gcsSource": { # Specifications for Cloud Storage objects. # Optional. Immutable. Cloud Storage object generation URI.
+ "generation": "A String", # Optional. Cloud Storage object generation ID. If not specified, the latest generation is used.
+ "uri": "A String", # Required. Cloud Storage object URI. Format: `gs://{bucket_name}/{object_name}`
+ },
+ "name": "A String", # Identifier. Resource name of the SkillRevision. Format: `projects/{project}/locations/{location}/skills/{skill}/revisions/{revision}`
+ "sha256Hash": "A String", # Output only. Cryptographic SHA-256 integrity and deduplication digest of the payload zip.
+ "sizeBytes": "A String", # Output only. Size of the compiled zip payload in bytes (assists client download progress).
+ "state": "A String", # Output only. The system-managed lifecycle state of this revision.
+ "uid": "A String", # Output only. Universally unique identifier (UUID4) for the skill revision.
+ },
+ "name": "A String", # Identifier. Resource name of the Skill. Format: `projects/{project}/locations/{location}/skills/{skill}` The `{skill}` segment acts as the resource ID. If the skill is associated with a Publisher, this segment typically uses a hyphenated namespace prefix corresponding to the publisher (e.g., `google-workspace-create-docs`).
+ "publisher": "A String", # Optional. The publisher resource associated with this skill. Format: `projects/{project}/locations/{location}/publishers/{publisher}` The publisher dictates the allowed namespace prefixes for the skill's name and logical `skill_id` (e.g., Publisher `google` authorizes the `google-*` prefix).
+ "skillId": "A String", # Output only. A stable, globally unique logical identifier for the skill. It is securely constructed by the backend by combining the associated `publisher`'s verified namespace and the skill's resource ID to enforce strict ownership. For example, the prefix `google-` is reserved exclusively for first-party Google publishers to prevent namespace squatting. Example: `urn:skill:google-workspace:create-docs`
+ "state": "A String", # Output only. The system-managed state of the skill.
+ "targetState": "A String", # Required. User-managed target state of the skill.
+ "type": "A String", # Required. Structural deployment type (SIMPLE leaf vs COMPOSITE bundle).
+ "uid": "A String", # Output only. Universally unique identifier (UUID4) for the logical container.
+ "updateTime": "A String", # Output only. Update time.
+ },
+ ],
+ "unreachable": [ # Unreachable locations or failures.
+ "A String",
+ ],
+}
+
+
+
+
list_next()
+
Retrieves the next page of results.
+
+ Args:
+ previous_request: The request for the previous page. (required)
+ previous_response: The response from the request for the previous page. (required)
+
+ Returns:
+ A request object that you can call 'execute()' on to request the next
+ page. Returns None if there are no more items in the collection.
+
+
+
+
+
patch(name, body=None, requestId=None, updateMask=None, x__xgafv=None)
+
Updates Skill metadata or overrides active pointers/state using REST standard PATCH.
+
+Args:
+ name: string, Identifier. Resource name of the Skill. Format: `projects/{project}/locations/{location}/skills/{skill}` The `{skill}` segment acts as the resource ID. If the skill is associated with a Publisher, this segment typically uses a hyphenated namespace prefix corresponding to the publisher (e.g., `google-workspace-create-docs`). (required)
+ body: object, The request body.
+ The object takes the form of:
+
+{ # Represents an Executable Agent Skill or a Composite Tool Suite (Bundle). Sibling resource with Agent and McpServer under agentregistry.googleapis.com.
+ "createTime": "A String", # Output only. Create time.
+ "defaultRevision": "A String", # Optional. The full resource name of the revision currently served by default (floating track). Format: `projects/{project}/locations/{location}/skills/{skill}/revisions/{revision}`
+ "description": "A String", # Optional. Brief summary describing the capabilities of the skill. Maximum length is 2048 characters.
+ "displayName": "A String", # Required. Human-readable display name of the skill. Maximum length is 128 characters.
+ "frontmatter": { # Structured metadata attributes extracted from the package's local SKILL.md frontmatter. # Output only. Lightweight frontmatter metadata attributes copied from the default revision.
+ "compatibility": "A String", # Optional. Environmental dependencies or local sidecars.
+ "description": "A String", # Required. Functional description.
+ "license": "A String", # Optional. License.
+ "metadata": { # Optional. Extensible flattened map mapping custom tags, authors, and version parameters.
+ "a_key": "A String",
+ },
+ "name": "A String", # Required. The name of the skill.
+ },
+ "initialRevision": { # Represents an immutable, versioned snapshot of a Skill package. # Optional. Input only. Optional nested initial revision payload to support standard one-shot creation. The server processes this field on input during creation but must never return it in responses.
+ "archiveUploadSource": { # Direct write-only raw archive payload upload. # Optional. Immutable. Direct write-only raw archive upload source.
+ "archiveContent": "A String", # Required. Input only. Write-only raw ZIP/TAR archive payload bytes containing the skill package.
+ },
+ "createTime": "A String", # Output only. Revision creation timestamp.
+ "frontmatter": { # Structured metadata attributes extracted from the package's local SKILL.md frontmatter. # Output only. Extracted YAML frontmatter configuration snapshot.
+ "compatibility": "A String", # Optional. Environmental dependencies or local sidecars.
+ "description": "A String", # Required. Functional description.
+ "license": "A String", # Optional. License.
+ "metadata": { # Optional. Extensible flattened map mapping custom tags, authors, and version parameters.
+ "a_key": "A String",
+ },
+ "name": "A String", # Required. The name of the skill.
+ },
+ "gcsSource": { # Specifications for Cloud Storage objects. # Optional. Immutable. Cloud Storage object generation URI.
+ "generation": "A String", # Optional. Cloud Storage object generation ID. If not specified, the latest generation is used.
+ "uri": "A String", # Required. Cloud Storage object URI. Format: `gs://{bucket_name}/{object_name}`
+ },
+ "name": "A String", # Identifier. Resource name of the SkillRevision. Format: `projects/{project}/locations/{location}/skills/{skill}/revisions/{revision}`
+ "sha256Hash": "A String", # Output only. Cryptographic SHA-256 integrity and deduplication digest of the payload zip.
+ "sizeBytes": "A String", # Output only. Size of the compiled zip payload in bytes (assists client download progress).
+ "state": "A String", # Output only. The system-managed lifecycle state of this revision.
+ "uid": "A String", # Output only. Universally unique identifier (UUID4) for the skill revision.
+ },
+ "name": "A String", # Identifier. Resource name of the Skill. Format: `projects/{project}/locations/{location}/skills/{skill}` The `{skill}` segment acts as the resource ID. If the skill is associated with a Publisher, this segment typically uses a hyphenated namespace prefix corresponding to the publisher (e.g., `google-workspace-create-docs`).
+ "publisher": "A String", # Optional. The publisher resource associated with this skill. Format: `projects/{project}/locations/{location}/publishers/{publisher}` The publisher dictates the allowed namespace prefixes for the skill's name and logical `skill_id` (e.g., Publisher `google` authorizes the `google-*` prefix).
+ "skillId": "A String", # Output only. A stable, globally unique logical identifier for the skill. It is securely constructed by the backend by combining the associated `publisher`'s verified namespace and the skill's resource ID to enforce strict ownership. For example, the prefix `google-` is reserved exclusively for first-party Google publishers to prevent namespace squatting. Example: `urn:skill:google-workspace:create-docs`
+ "state": "A String", # Output only. The system-managed state of the skill.
+ "targetState": "A String", # Required. User-managed target state of the skill.
+ "type": "A String", # Required. Structural deployment type (SIMPLE leaf vs COMPOSITE bundle).
+ "uid": "A String", # Output only. Universally unique identifier (UUID4) for the logical container.
+ "updateTime": "A String", # Output only. Update time.
+}
+
+ requestId: string, Optional. Signed UUID request idempotency token.
+ updateMask: string, Optional. Standard update target mask mapping relative fields.
+ x__xgafv: string, V1 error format.
+ Allowed values
+ 1 - v1 error format
+ 2 - v2 error format
+
+Returns:
+ An object of the form:
+
+ { # This resource represents a long-running operation that is the result of a network API call.
+ "done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
+ "error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
+ "code": 42, # The status code, which should be an enum value of google.rpc.Code.
+ "details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
+ {
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+ ],
+ "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
+ },
+ "metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+ "name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
+ "response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+}
+
+
+
+
search(parent, filter=None, pageSize=None, pageToken=None, searchString=None, searchType=None, x__xgafv=None)
+
Custom deep-search method to filter by frontmatter or query SKILL.md text blobs.
+
+Args:
+ parent: string, Required. Parent value for SearchSkillsRequest. Format: `projects/{project}/locations/{location}`. (required)
+ filter: string, Optional. Use this field to specify additional filter criteria on search results. Filter expressions can be used to restrict results based upon filterable fields, where equality operators can be used. See [instructions](https://docs.cloud.google.com/agent-registry/search-agents-and-tools) for more details. Allowed operators: `=`, `<`, `>`, `NOT`, `AND`, `OR`, and `()`. | Field | `=` | `<`, `>` | |--------------|-----|----------| | state | Yes | No | | targetState | Yes | No | | createTime | Yes | Yes | | updateTime | Yes | Yes | Examples: * `state=ACTIVE` to restrict results to skills in the `ACTIVE` state.
+ pageSize: integer, Optional. The maximum number of search results to return per page. The page size is capped at `100`, even if a larger value is specified. A negative value will result in an `INVALID_ARGUMENT` error. If unspecified or set to `0`, a default value of `20` will be used. The server may return fewer results than requested.
+ pageToken: string, Optional. If present, retrieve the next batch of results from the preceding call to this method. `page_token` must be the value of `next_page_token` from the previous response. The values of all other method parameters, must be identical to those in the previous call.
+ searchString: string, Optional. Search criteria used to select the Skills to return. If no search criteria is specified then all accessible Skills will be returned. Search expressions can be used to restrict results based upon searchable fields, where the operators can be used along with the suffix wildcard symbol `*`. See [instructions](https://docs.cloud.google.com/agent-registry/search-agents-and-tools) for more details. Allowed operators: `=`, `:`, `NOT`, `AND`, `OR`, and `()`. Searchable fields: | Field | `=` | `:` | `*` | Keyword Search | |---------------------------|-----|-----|-----|----------------| | skillId | Yes | Yes | Yes | Included | | name | No | Yes | Yes | Included | | displayName | No | Yes | Yes | Included | | description | No | Yes | No | Included | | frontmatter.name | No | Yes | No | Included | | frontmatter.description | No | Yes | No | Included | | frontmatter.compatibility | No | Yes | No | Included | | frontmatter.license | No | Yes | No | Included | Examples: * `skillId="urn:skill:projects-1234:locations:global:private-important-skill"` to find the skill with the specified skill ID. * `name:important` to find skills whose name contains `important` as a word. * `displayName:works*` to find skills whose display name contains words that start with `works`.
+ searchType: string, Optional. The type of search.
+ Allowed values
+ SEARCH_TYPE_UNSPECIFIED - Invalid search type.
+ KEYWORD - Search for a keyword across all searchable fields.
+ SEMANTIC - Search based on the meaning and intent of a natural language query.
+ x__xgafv: string, V1 error format.
+ Allowed values
+ 1 - v1 error format
+ 2 - v2 error format
+
+Returns:
+ An object of the form:
+
+ { # Response listing searched Skills.
+ "nextPageToken": "A String", # Query page offset continuation token.
+ "skills": [ # Matched Skills list.
+ { # Represents an Executable Agent Skill or a Composite Tool Suite (Bundle). Sibling resource with Agent and McpServer under agentregistry.googleapis.com.
+ "createTime": "A String", # Output only. Create time.
+ "defaultRevision": "A String", # Optional. The full resource name of the revision currently served by default (floating track). Format: `projects/{project}/locations/{location}/skills/{skill}/revisions/{revision}`
+ "description": "A String", # Optional. Brief summary describing the capabilities of the skill. Maximum length is 2048 characters.
+ "displayName": "A String", # Required. Human-readable display name of the skill. Maximum length is 128 characters.
+ "frontmatter": { # Structured metadata attributes extracted from the package's local SKILL.md frontmatter. # Output only. Lightweight frontmatter metadata attributes copied from the default revision.
+ "compatibility": "A String", # Optional. Environmental dependencies or local sidecars.
+ "description": "A String", # Required. Functional description.
+ "license": "A String", # Optional. License.
+ "metadata": { # Optional. Extensible flattened map mapping custom tags, authors, and version parameters.
+ "a_key": "A String",
+ },
+ "name": "A String", # Required. The name of the skill.
+ },
+ "initialRevision": { # Represents an immutable, versioned snapshot of a Skill package. # Optional. Input only. Optional nested initial revision payload to support standard one-shot creation. The server processes this field on input during creation but must never return it in responses.
+ "archiveUploadSource": { # Direct write-only raw archive payload upload. # Optional. Immutable. Direct write-only raw archive upload source.
+ "archiveContent": "A String", # Required. Input only. Write-only raw ZIP/TAR archive payload bytes containing the skill package.
+ },
+ "createTime": "A String", # Output only. Revision creation timestamp.
+ "frontmatter": { # Structured metadata attributes extracted from the package's local SKILL.md frontmatter. # Output only. Extracted YAML frontmatter configuration snapshot.
+ "compatibility": "A String", # Optional. Environmental dependencies or local sidecars.
+ "description": "A String", # Required. Functional description.
+ "license": "A String", # Optional. License.
+ "metadata": { # Optional. Extensible flattened map mapping custom tags, authors, and version parameters.
+ "a_key": "A String",
+ },
+ "name": "A String", # Required. The name of the skill.
+ },
+ "gcsSource": { # Specifications for Cloud Storage objects. # Optional. Immutable. Cloud Storage object generation URI.
+ "generation": "A String", # Optional. Cloud Storage object generation ID. If not specified, the latest generation is used.
+ "uri": "A String", # Required. Cloud Storage object URI. Format: `gs://{bucket_name}/{object_name}`
+ },
+ "name": "A String", # Identifier. Resource name of the SkillRevision. Format: `projects/{project}/locations/{location}/skills/{skill}/revisions/{revision}`
+ "sha256Hash": "A String", # Output only. Cryptographic SHA-256 integrity and deduplication digest of the payload zip.
+ "sizeBytes": "A String", # Output only. Size of the compiled zip payload in bytes (assists client download progress).
+ "state": "A String", # Output only. The system-managed lifecycle state of this revision.
+ "uid": "A String", # Output only. Universally unique identifier (UUID4) for the skill revision.
+ },
+ "name": "A String", # Identifier. Resource name of the Skill. Format: `projects/{project}/locations/{location}/skills/{skill}` The `{skill}` segment acts as the resource ID. If the skill is associated with a Publisher, this segment typically uses a hyphenated namespace prefix corresponding to the publisher (e.g., `google-workspace-create-docs`).
+ "publisher": "A String", # Optional. The publisher resource associated with this skill. Format: `projects/{project}/locations/{location}/publishers/{publisher}` The publisher dictates the allowed namespace prefixes for the skill's name and logical `skill_id` (e.g., Publisher `google` authorizes the `google-*` prefix).
+ "skillId": "A String", # Output only. A stable, globally unique logical identifier for the skill. It is securely constructed by the backend by combining the associated `publisher`'s verified namespace and the skill's resource ID to enforce strict ownership. For example, the prefix `google-` is reserved exclusively for first-party Google publishers to prevent namespace squatting. Example: `urn:skill:google-workspace:create-docs`
+ "state": "A String", # Output only. The system-managed state of the skill.
+ "targetState": "A String", # Required. User-managed target state of the skill.
+ "type": "A String", # Required. Structural deployment type (SIMPLE leaf vs COMPOSITE bundle).
+ "uid": "A String", # Output only. Universally unique identifier (UUID4) for the logical container.
+ "updateTime": "A String", # Output only. Update time.
+ },
+ ],
+}
+
+
+
+
search_next()
+
Retrieves the next page of results.
+
+ Args:
+ previous_request: The request for the previous page. (required)
+ previous_response: The response from the request for the previous page. (required)
+
+ Returns:
+ A request object that you can call 'execute()' on to request the next
+ page. Returns None if there are no more items in the collection.
+
+
+
+
\ No newline at end of file
diff --git a/docs/dyn/agentregistry_v1alpha.projects.locations.skills.revisions.html b/docs/dyn/agentregistry_v1alpha.projects.locations.skills.revisions.html
new file mode 100644
index 0000000000..838ade25b4
--- /dev/null
+++ b/docs/dyn/agentregistry_v1alpha.projects.locations.skills.revisions.html
@@ -0,0 +1,323 @@
+
+
+
+
+Instance Methods
+
+ close()
+Close httplib2 connections.
+
+ create(parent, body=None, requestId=None, skillRevisionId=None, x__xgafv=None)
+Creates a new immutable revision and triggers validation pipelines.
+
+ delete(name, requestId=None, x__xgafv=None)
+Deletes a specific revision (restricted to admins to purge accidentally committed secrets).
+
+ get(name, x__xgafv=None)
+Gets details of a single immutable Revision.
+
+ get_media(name, x__xgafv=None)
+Gets details of a single immutable Revision.
+
+ list(parent, pageSize=None, pageToken=None, x__xgafv=None)
+Lists all revisions belonging to a parent Skill.
+
+ list_next()
+Retrieves the next page of results.
+Method Details
+
+
close()
+
Close httplib2 connections.
+
+
+
+
create(parent, body=None, requestId=None, skillRevisionId=None, x__xgafv=None)
+
Creates a new immutable revision and triggers validation pipelines.
+
+Args:
+ parent: string, Required. Parent logical container name. (required)
+ body: object, The request body.
+ The object takes the form of:
+
+{ # Represents an immutable, versioned snapshot of a Skill package.
+ "archiveUploadSource": { # Direct write-only raw archive payload upload. # Optional. Immutable. Direct write-only raw archive upload source.
+ "archiveContent": "A String", # Required. Input only. Write-only raw ZIP/TAR archive payload bytes containing the skill package.
+ },
+ "createTime": "A String", # Output only. Revision creation timestamp.
+ "frontmatter": { # Structured metadata attributes extracted from the package's local SKILL.md frontmatter. # Output only. Extracted YAML frontmatter configuration snapshot.
+ "compatibility": "A String", # Optional. Environmental dependencies or local sidecars.
+ "description": "A String", # Required. Functional description.
+ "license": "A String", # Optional. License.
+ "metadata": { # Optional. Extensible flattened map mapping custom tags, authors, and version parameters.
+ "a_key": "A String",
+ },
+ "name": "A String", # Required. The name of the skill.
+ },
+ "gcsSource": { # Specifications for Cloud Storage objects. # Optional. Immutable. Cloud Storage object generation URI.
+ "generation": "A String", # Optional. Cloud Storage object generation ID. If not specified, the latest generation is used.
+ "uri": "A String", # Required. Cloud Storage object URI. Format: `gs://{bucket_name}/{object_name}`
+ },
+ "name": "A String", # Identifier. Resource name of the SkillRevision. Format: `projects/{project}/locations/{location}/skills/{skill}/revisions/{revision}`
+ "sha256Hash": "A String", # Output only. Cryptographic SHA-256 integrity and deduplication digest of the payload zip.
+ "sizeBytes": "A String", # Output only. Size of the compiled zip payload in bytes (assists client download progress).
+ "state": "A String", # Output only. The system-managed lifecycle state of this revision.
+ "uid": "A String", # Output only. Universally unique identifier (UUID4) for the skill revision.
+}
+
+ requestId: string, Optional. Signed UUID request idempotency token.
+ skillRevisionId: string, Optional. Custom, user-defined unique revision identifier. Format: 4-63 characters, matching regex `^[a-z]([a-z0-9-]{0,61}[a-z0-9])?$`
+ x__xgafv: string, V1 error format.
+ Allowed values
+ 1 - v1 error format
+ 2 - v2 error format
+
+Returns:
+ An object of the form:
+
+ { # This resource represents a long-running operation that is the result of a network API call.
+ "done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
+ "error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
+ "code": 42, # The status code, which should be an enum value of google.rpc.Code.
+ "details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
+ {
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+ ],
+ "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
+ },
+ "metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+ "name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
+ "response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+}
+
+
+
+
delete(name, requestId=None, x__xgafv=None)
+
Deletes a specific revision (restricted to admins to purge accidentally committed secrets).
+
+Args:
+ name: string, Required. Target revision name to remove. (required)
+ requestId: string, Optional. Signed UUID request idempotency token.
+ x__xgafv: string, V1 error format.
+ Allowed values
+ 1 - v1 error format
+ 2 - v2 error format
+
+Returns:
+ An object of the form:
+
+ { # This resource represents a long-running operation that is the result of a network API call.
+ "done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
+ "error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
+ "code": 42, # The status code, which should be an enum value of google.rpc.Code.
+ "details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
+ {
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+ ],
+ "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
+ },
+ "metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+ "name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
+ "response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+}
+
+
+
+
get(name, x__xgafv=None)
+
Gets details of a single immutable Revision.
+
+Args:
+ name: string, Required. Target revision name. (required)
+ x__xgafv: string, V1 error format.
+ Allowed values
+ 1 - v1 error format
+ 2 - v2 error format
+
+Returns:
+ An object of the form:
+
+ { # Represents an immutable, versioned snapshot of a Skill package.
+ "archiveUploadSource": { # Direct write-only raw archive payload upload. # Optional. Immutable. Direct write-only raw archive upload source.
+ "archiveContent": "A String", # Required. Input only. Write-only raw ZIP/TAR archive payload bytes containing the skill package.
+ },
+ "createTime": "A String", # Output only. Revision creation timestamp.
+ "frontmatter": { # Structured metadata attributes extracted from the package's local SKILL.md frontmatter. # Output only. Extracted YAML frontmatter configuration snapshot.
+ "compatibility": "A String", # Optional. Environmental dependencies or local sidecars.
+ "description": "A String", # Required. Functional description.
+ "license": "A String", # Optional. License.
+ "metadata": { # Optional. Extensible flattened map mapping custom tags, authors, and version parameters.
+ "a_key": "A String",
+ },
+ "name": "A String", # Required. The name of the skill.
+ },
+ "gcsSource": { # Specifications for Cloud Storage objects. # Optional. Immutable. Cloud Storage object generation URI.
+ "generation": "A String", # Optional. Cloud Storage object generation ID. If not specified, the latest generation is used.
+ "uri": "A String", # Required. Cloud Storage object URI. Format: `gs://{bucket_name}/{object_name}`
+ },
+ "name": "A String", # Identifier. Resource name of the SkillRevision. Format: `projects/{project}/locations/{location}/skills/{skill}/revisions/{revision}`
+ "sha256Hash": "A String", # Output only. Cryptographic SHA-256 integrity and deduplication digest of the payload zip.
+ "sizeBytes": "A String", # Output only. Size of the compiled zip payload in bytes (assists client download progress).
+ "state": "A String", # Output only. The system-managed lifecycle state of this revision.
+ "uid": "A String", # Output only. Universally unique identifier (UUID4) for the skill revision.
+}
+
+
+
+
get_media(name, x__xgafv=None)
+
Gets details of a single immutable Revision.
+
+Args:
+ name: string, Required. Target revision name. (required)
+ x__xgafv: string, V1 error format.
+ Allowed values
+ 1 - v1 error format
+ 2 - v2 error format
+
+Returns:
+ The media object as a string.
+
+
+
+
+
+
list(parent, pageSize=None, pageToken=None, x__xgafv=None)
+
Lists all revisions belonging to a parent Skill.
+
+Args:
+ parent: string, Required. Parent logical container name to query. (required)
+ pageSize: integer, Optional. Page limit size.
+ pageToken: string, Optional. Page offset token.
+ x__xgafv: string, V1 error format.
+ Allowed values
+ 1 - v1 error format
+ 2 - v2 error format
+
+Returns:
+ An object of the form:
+
+ { # Response listing Revisions.
+ "nextPageToken": "A String", # Page offset continuation token.
+ "skillRevisions": [ # Returned version snapshot list.
+ { # Represents an immutable, versioned snapshot of a Skill package.
+ "archiveUploadSource": { # Direct write-only raw archive payload upload. # Optional. Immutable. Direct write-only raw archive upload source.
+ "archiveContent": "A String", # Required. Input only. Write-only raw ZIP/TAR archive payload bytes containing the skill package.
+ },
+ "createTime": "A String", # Output only. Revision creation timestamp.
+ "frontmatter": { # Structured metadata attributes extracted from the package's local SKILL.md frontmatter. # Output only. Extracted YAML frontmatter configuration snapshot.
+ "compatibility": "A String", # Optional. Environmental dependencies or local sidecars.
+ "description": "A String", # Required. Functional description.
+ "license": "A String", # Optional. License.
+ "metadata": { # Optional. Extensible flattened map mapping custom tags, authors, and version parameters.
+ "a_key": "A String",
+ },
+ "name": "A String", # Required. The name of the skill.
+ },
+ "gcsSource": { # Specifications for Cloud Storage objects. # Optional. Immutable. Cloud Storage object generation URI.
+ "generation": "A String", # Optional. Cloud Storage object generation ID. If not specified, the latest generation is used.
+ "uri": "A String", # Required. Cloud Storage object URI. Format: `gs://{bucket_name}/{object_name}`
+ },
+ "name": "A String", # Identifier. Resource name of the SkillRevision. Format: `projects/{project}/locations/{location}/skills/{skill}/revisions/{revision}`
+ "sha256Hash": "A String", # Output only. Cryptographic SHA-256 integrity and deduplication digest of the payload zip.
+ "sizeBytes": "A String", # Output only. Size of the compiled zip payload in bytes (assists client download progress).
+ "state": "A String", # Output only. The system-managed lifecycle state of this revision.
+ "uid": "A String", # Output only. Universally unique identifier (UUID4) for the skill revision.
+ },
+ ],
+}
+
+
+
+
list_next()
+
Retrieves the next page of results.
+
+ Args:
+ previous_request: The request for the previous page. (required)
+ previous_response: The response from the request for the previous page. (required)
+
+ Returns:
+ A request object that you can call 'execute()' on to request the next
+ page. Returns None if there are no more items in the collection.
+
+
+
+
\ No newline at end of file
diff --git a/googleapiclient/discovery_cache/documents/agentregistry.v1alpha.json b/googleapiclient/discovery_cache/documents/agentregistry.v1alpha.json
index 98f2555b00..2f0e212167 100644
--- a/googleapiclient/discovery_cache/documents/agentregistry.v1alpha.json
+++ b/googleapiclient/discovery_cache/documents/agentregistry.v1alpha.json
@@ -874,6 +874,77 @@
}
}
},
+"publishers": {
+"methods": {
+"get": {
+"description": "Fetches details of a specific Publisher.",
+"flatPath": "v1alpha/projects/{projectsId}/locations/{locationsId}/publishers/{publishersId}",
+"httpMethod": "GET",
+"id": "agentregistry.projects.locations.publishers.get",
+"parameterOrder": [
+"name"
+],
+"parameters": {
+"name": {
+"description": "Required. Target publisher resource name. Format: `projects/{project}/locations/{location}/publishers/{publisher}`",
+"location": "path",
+"pattern": "^projects/[^/]+/locations/[^/]+/publishers/[^/]+$",
+"required": true,
+"type": "string"
+}
+},
+"path": "v1alpha/{+name}",
+"response": {
+"$ref": "Publisher"
+},
+"scopes": [
+"https://www.googleapis.com/auth/agentregistry.read-only",
+"https://www.googleapis.com/auth/agentregistry.read-write",
+"https://www.googleapis.com/auth/cloud-platform",
+"https://www.googleapis.com/auth/cloud-platform.read-only"
+]
+},
+"list": {
+"description": "Lists all Publishers in a location.",
+"flatPath": "v1alpha/projects/{projectsId}/locations/{locationsId}/publishers",
+"httpMethod": "GET",
+"id": "agentregistry.projects.locations.publishers.list",
+"parameterOrder": [
+"parent"
+],
+"parameters": {
+"pageSize": {
+"description": "Optional. Page limit size.",
+"format": "int32",
+"location": "query",
+"type": "integer"
+},
+"pageToken": {
+"description": "Optional. Page offset token.",
+"location": "query",
+"type": "string"
+},
+"parent": {
+"description": "Required. Parent location to query. Format: `projects/{project}/locations/{location}`",
+"location": "path",
+"pattern": "^projects/[^/]+/locations/[^/]+$",
+"required": true,
+"type": "string"
+}
+},
+"path": "v1alpha/{+parent}/publishers",
+"response": {
+"$ref": "ListPublishersResponse"
+},
+"scopes": [
+"https://www.googleapis.com/auth/agentregistry.read-only",
+"https://www.googleapis.com/auth/agentregistry.read-write",
+"https://www.googleapis.com/auth/cloud-platform",
+"https://www.googleapis.com/auth/cloud-platform.read-only"
+]
+}
+}
+},
"services": {
"methods": {
"create": {
@@ -1011,9 +1082,395 @@
"type": "string"
}
},
-"path": "v1alpha/{+parent}/services",
+"path": "v1alpha/{+parent}/services",
+"response": {
+"$ref": "ListServicesResponse"
+},
+"scopes": [
+"https://www.googleapis.com/auth/agentregistry.read-only",
+"https://www.googleapis.com/auth/agentregistry.read-write",
+"https://www.googleapis.com/auth/cloud-platform",
+"https://www.googleapis.com/auth/cloud-platform.read-only"
+]
+},
+"patch": {
+"description": "Updates the parameters of a single Service.",
+"flatPath": "v1alpha/projects/{projectsId}/locations/{locationsId}/services/{servicesId}",
+"httpMethod": "PATCH",
+"id": "agentregistry.projects.locations.services.patch",
+"parameterOrder": [
+"name"
+],
+"parameters": {
+"name": {
+"description": "Identifier. The resource name of the Service. Format: `projects/{project}/locations/{location}/services/{service}`.",
+"location": "path",
+"pattern": "^projects/[^/]+/locations/[^/]+/services/[^/]+$",
+"required": true,
+"type": "string"
+},
+"requestId": {
+"description": "Optional. An optional request ID to identify requests. Specify a unique request ID so that if you must retry your request, the server will know to ignore the request if it has already been completed. The server will guarantee that for at least 60 minutes since the first request. For example, consider a situation where you make an initial request and the request times out. If you make the request again with the same request ID, the server can check if original operation with the same request ID was received, and if so, will ignore the second request. This prevents clients from accidentally creating duplicate commitments. The request ID must be a valid UUID with the exception that zero UUID is not supported (00000000-0000-0000-0000-000000000000).",
+"location": "query",
+"type": "string"
+},
+"updateMask": {
+"description": "Optional. Field mask is used to specify the fields to be overwritten in the Service resource by the update. The fields specified in the update_mask are relative to the resource, not the full request. A field will be overwritten if it is in the mask. If the user does not provide a mask then all fields present in the request will be overwritten.",
+"format": "google-fieldmask",
+"location": "query",
+"type": "string"
+}
+},
+"path": "v1alpha/{+name}",
+"request": {
+"$ref": "Service"
+},
+"response": {
+"$ref": "Operation"
+},
+"scopes": [
+"https://www.googleapis.com/auth/agentregistry.read-only",
+"https://www.googleapis.com/auth/agentregistry.read-write",
+"https://www.googleapis.com/auth/cloud-platform",
+"https://www.googleapis.com/auth/cloud-platform.read-only"
+]
+}
+}
+},
+"skills": {
+"methods": {
+"create": {
+"description": "========================================================================= # Skills Collection APIs Creates a Skill resource container, optionally publishing the initial SkillRevision inline in a single, atomic CRUD roundtrip.",
+"flatPath": "v1alpha/projects/{projectsId}/locations/{locationsId}/skills",
+"httpMethod": "POST",
+"id": "agentregistry.projects.locations.skills.create",
+"parameterOrder": [
+"parent"
+],
+"parameters": {
+"parent": {
+"description": "Required. The project and location location to bootstrap.",
+"location": "path",
+"pattern": "^projects/[^/]+/locations/[^/]+$",
+"required": true,
+"type": "string"
+},
+"requestId": {
+"description": "Optional. Signed UUID request idempotency token.",
+"location": "query",
+"type": "string"
+},
+"skillId": {
+"description": "Required. Custom, user-defined unique container identifier. Must be unique within the parent project and location. This value should be 4-63 characters, and valid characters are `/a-z-/`.",
+"location": "query",
+"type": "string"
+}
+},
+"path": "v1alpha/{+parent}/skills",
+"request": {
+"$ref": "Skill"
+},
+"response": {
+"$ref": "Operation"
+},
+"scopes": [
+"https://www.googleapis.com/auth/agentregistry.read-only",
+"https://www.googleapis.com/auth/agentregistry.read-write",
+"https://www.googleapis.com/auth/cloud-platform",
+"https://www.googleapis.com/auth/cloud-platform.read-only"
+]
+},
+"delete": {
+"description": "Deletes a Skill container along with all its revisions.",
+"flatPath": "v1alpha/projects/{projectsId}/locations/{locationsId}/skills/{skillsId}",
+"httpMethod": "DELETE",
+"id": "agentregistry.projects.locations.skills.delete",
+"parameterOrder": [
+"name"
+],
+"parameters": {
+"force": {
+"description": "Optional. If set to true, any child SkillRevisions under this Skill will also be deleted. Otherwise, the request will only succeed if the Skill has no child SkillRevisions.",
+"location": "query",
+"type": "boolean"
+},
+"name": {
+"description": "Required. Target Skill container name to remove.",
+"location": "path",
+"pattern": "^projects/[^/]+/locations/[^/]+/skills/[^/]+$",
+"required": true,
+"type": "string"
+},
+"requestId": {
+"description": "Optional. Signed UUID request idempotency token.",
+"location": "query",
+"type": "string"
+}
+},
+"path": "v1alpha/{+name}",
+"response": {
+"$ref": "Operation"
+},
+"scopes": [
+"https://www.googleapis.com/auth/agentregistry.read-only",
+"https://www.googleapis.com/auth/agentregistry.read-write",
+"https://www.googleapis.com/auth/cloud-platform",
+"https://www.googleapis.com/auth/cloud-platform.read-only"
+]
+},
+"get": {
+"description": "Fetches the active configuration and metadata of a Skill.",
+"flatPath": "v1alpha/projects/{projectsId}/locations/{locationsId}/skills/{skillsId}",
+"httpMethod": "GET",
+"id": "agentregistry.projects.locations.skills.get",
+"parameterOrder": [
+"name"
+],
+"parameters": {
+"name": {
+"description": "Required. Target resource container name.",
+"location": "path",
+"pattern": "^projects/[^/]+/locations/[^/]+/skills/[^/]+$",
+"required": true,
+"type": "string"
+}
+},
+"path": "v1alpha/{+name}",
+"response": {
+"$ref": "Skill"
+},
+"scopes": [
+"https://www.googleapis.com/auth/agentregistry.read-only",
+"https://www.googleapis.com/auth/agentregistry.read-write",
+"https://www.googleapis.com/auth/cloud-platform",
+"https://www.googleapis.com/auth/cloud-platform.read-only"
+]
+},
+"list": {
+"description": "Lists logical Skills available in a project.",
+"flatPath": "v1alpha/projects/{projectsId}/locations/{locationsId}/skills",
+"httpMethod": "GET",
+"id": "agentregistry.projects.locations.skills.list",
+"parameterOrder": [
+"parent"
+],
+"parameters": {
+"filter": {
+"description": "Optional. Use this field to specify filter criteria on list results. Filter expressions can be used to restrict results based upon filterable fields, where equality operators can be used. See [instructions](https://docs.cloud.google.com/agent-registry/search-agents-and-tools) for more details. Allowed operators: `=`, `<`, `>`, `NOT`, `AND`, `OR`, and `()`. | Field | `=` | `<`, `>` | |--------------|-----|----------| | state | Yes | No | | targetState | Yes | No | | createTime | Yes | Yes | | updateTime | Yes | Yes | Examples: * `state=ACTIVE` to restrict results to skills in the `ACTIVE` state.",
+"location": "query",
+"type": "string"
+},
+"orderBy": {
+"description": "Optional. Hint for how to order the results",
+"location": "query",
+"type": "string"
+},
+"pageSize": {
+"description": "Optional. Requested page size. Server may return fewer items than requested. If unspecified, server will pick an appropriate default.",
+"format": "int32",
+"location": "query",
+"type": "integer"
+},
+"pageToken": {
+"description": "Optional. A token identifying a page of results the server should return.",
+"location": "query",
+"type": "string"
+},
+"parent": {
+"description": "Required. Parent value for ListSkillsRequest",
+"location": "path",
+"pattern": "^projects/[^/]+/locations/[^/]+$",
+"required": true,
+"type": "string"
+}
+},
+"path": "v1alpha/{+parent}/skills",
+"response": {
+"$ref": "ListSkillsResponse"
+},
+"scopes": [
+"https://www.googleapis.com/auth/agentregistry.read-only",
+"https://www.googleapis.com/auth/agentregistry.read-write",
+"https://www.googleapis.com/auth/cloud-platform",
+"https://www.googleapis.com/auth/cloud-platform.read-only"
+]
+},
+"patch": {
+"description": "Updates Skill metadata or overrides active pointers/state using REST standard PATCH.",
+"flatPath": "v1alpha/projects/{projectsId}/locations/{locationsId}/skills/{skillsId}",
+"httpMethod": "PATCH",
+"id": "agentregistry.projects.locations.skills.patch",
+"parameterOrder": [
+"name"
+],
+"parameters": {
+"name": {
+"description": "Identifier. Resource name of the Skill. Format: `projects/{project}/locations/{location}/skills/{skill}` The `{skill}` segment acts as the resource ID. If the skill is associated with a Publisher, this segment typically uses a hyphenated namespace prefix corresponding to the publisher (e.g., `google-workspace-create-docs`).",
+"location": "path",
+"pattern": "^projects/[^/]+/locations/[^/]+/skills/[^/]+$",
+"required": true,
+"type": "string"
+},
+"requestId": {
+"description": "Optional. Signed UUID request idempotency token.",
+"location": "query",
+"type": "string"
+},
+"updateMask": {
+"description": "Optional. Standard update target mask mapping relative fields.",
+"format": "google-fieldmask",
+"location": "query",
+"type": "string"
+}
+},
+"path": "v1alpha/{+name}",
+"request": {
+"$ref": "Skill"
+},
+"response": {
+"$ref": "Operation"
+},
+"scopes": [
+"https://www.googleapis.com/auth/agentregistry.read-only",
+"https://www.googleapis.com/auth/agentregistry.read-write",
+"https://www.googleapis.com/auth/cloud-platform",
+"https://www.googleapis.com/auth/cloud-platform.read-only"
+]
+},
+"search": {
+"description": "Custom deep-search method to filter by frontmatter or query SKILL.md text blobs.",
+"flatPath": "v1alpha/projects/{projectsId}/locations/{locationsId}/skills:search",
+"httpMethod": "GET",
+"id": "agentregistry.projects.locations.skills.search",
+"parameterOrder": [
+"parent"
+],
+"parameters": {
+"filter": {
+"description": "Optional. Use this field to specify additional filter criteria on search results. Filter expressions can be used to restrict results based upon filterable fields, where equality operators can be used. See [instructions](https://docs.cloud.google.com/agent-registry/search-agents-and-tools) for more details. Allowed operators: `=`, `<`, `>`, `NOT`, `AND`, `OR`, and `()`. | Field | `=` | `<`, `>` | |--------------|-----|----------| | state | Yes | No | | targetState | Yes | No | | createTime | Yes | Yes | | updateTime | Yes | Yes | Examples: * `state=ACTIVE` to restrict results to skills in the `ACTIVE` state.",
+"location": "query",
+"type": "string"
+},
+"pageSize": {
+"description": "Optional. The maximum number of search results to return per page. The page size is capped at `100`, even if a larger value is specified. A negative value will result in an `INVALID_ARGUMENT` error. If unspecified or set to `0`, a default value of `20` will be used. The server may return fewer results than requested.",
+"format": "int32",
+"location": "query",
+"type": "integer"
+},
+"pageToken": {
+"description": "Optional. If present, retrieve the next batch of results from the preceding call to this method. `page_token` must be the value of `next_page_token` from the previous response. The values of all other method parameters, must be identical to those in the previous call.",
+"location": "query",
+"type": "string"
+},
+"parent": {
+"description": "Required. Parent value for SearchSkillsRequest. Format: `projects/{project}/locations/{location}`.",
+"location": "path",
+"pattern": "^projects/[^/]+/locations/[^/]+$",
+"required": true,
+"type": "string"
+},
+"searchString": {
+"description": "Optional. Search criteria used to select the Skills to return. If no search criteria is specified then all accessible Skills will be returned. Search expressions can be used to restrict results based upon searchable fields, where the operators can be used along with the suffix wildcard symbol `*`. See [instructions](https://docs.cloud.google.com/agent-registry/search-agents-and-tools) for more details. Allowed operators: `=`, `:`, `NOT`, `AND`, `OR`, and `()`. Searchable fields: | Field | `=` | `:` | `*` | Keyword Search | |---------------------------|-----|-----|-----|----------------| | skillId | Yes | Yes | Yes | Included | | name | No | Yes | Yes | Included | | displayName | No | Yes | Yes | Included | | description | No | Yes | No | Included | | frontmatter.name | No | Yes | No | Included | | frontmatter.description | No | Yes | No | Included | | frontmatter.compatibility | No | Yes | No | Included | | frontmatter.license | No | Yes | No | Included | Examples: * `skillId=\"urn:skill:projects-1234:locations:global:private-important-skill\"` to find the skill with the specified skill ID. * `name:important` to find skills whose name contains `important` as a word. * `displayName:works*` to find skills whose display name contains words that start with `works`.",
+"location": "query",
+"type": "string"
+},
+"searchType": {
+"description": "Optional. The type of search.",
+"enum": [
+"SEARCH_TYPE_UNSPECIFIED",
+"KEYWORD",
+"SEMANTIC"
+],
+"enumDescriptions": [
+"Invalid search type.",
+"Search for a keyword across all searchable fields.",
+"Search based on the meaning and intent of a natural language query."
+],
+"location": "query",
+"type": "string"
+}
+},
+"path": "v1alpha/{+parent}/skills:search",
+"response": {
+"$ref": "SearchSkillsResponse"
+},
+"scopes": [
+"https://www.googleapis.com/auth/agentregistry.read-only",
+"https://www.googleapis.com/auth/agentregistry.read-write",
+"https://www.googleapis.com/auth/cloud-platform",
+"https://www.googleapis.com/auth/cloud-platform.read-only"
+]
+}
+},
+"resources": {
+"revisions": {
+"methods": {
+"create": {
+"description": "Creates a new immutable revision and triggers validation pipelines.",
+"flatPath": "v1alpha/projects/{projectsId}/locations/{locationsId}/skills/{skillsId}/revisions",
+"httpMethod": "POST",
+"id": "agentregistry.projects.locations.skills.revisions.create",
+"parameterOrder": [
+"parent"
+],
+"parameters": {
+"parent": {
+"description": "Required. Parent logical container name.",
+"location": "path",
+"pattern": "^projects/[^/]+/locations/[^/]+/skills/[^/]+$",
+"required": true,
+"type": "string"
+},
+"requestId": {
+"description": "Optional. Signed UUID request idempotency token.",
+"location": "query",
+"type": "string"
+},
+"skillRevisionId": {
+"description": "Optional. Custom, user-defined unique revision identifier. Format: 4-63 characters, matching regex `^[a-z]([a-z0-9-]{0,61}[a-z0-9])?$`",
+"location": "query",
+"type": "string"
+}
+},
+"path": "v1alpha/{+parent}/revisions",
+"request": {
+"$ref": "SkillRevision"
+},
+"response": {
+"$ref": "Operation"
+},
+"scopes": [
+"https://www.googleapis.com/auth/agentregistry.read-only",
+"https://www.googleapis.com/auth/agentregistry.read-write",
+"https://www.googleapis.com/auth/cloud-platform",
+"https://www.googleapis.com/auth/cloud-platform.read-only"
+]
+},
+"delete": {
+"description": "Deletes a specific revision (restricted to admins to purge accidentally committed secrets).",
+"flatPath": "v1alpha/projects/{projectsId}/locations/{locationsId}/skills/{skillsId}/revisions/{revisionsId}",
+"httpMethod": "DELETE",
+"id": "agentregistry.projects.locations.skills.revisions.delete",
+"parameterOrder": [
+"name"
+],
+"parameters": {
+"name": {
+"description": "Required. Target revision name to remove.",
+"location": "path",
+"pattern": "^projects/[^/]+/locations/[^/]+/skills/[^/]+/revisions/[^/]+$",
+"required": true,
+"type": "string"
+},
+"requestId": {
+"description": "Optional. Signed UUID request idempotency token.",
+"location": "query",
+"type": "string"
+}
+},
+"path": "v1alpha/{+name}",
"response": {
-"$ref": "ListServicesResponse"
+"$ref": "Operation"
},
"scopes": [
"https://www.googleapis.com/auth/agentregistry.read-only",
@@ -1022,40 +1479,67 @@
"https://www.googleapis.com/auth/cloud-platform.read-only"
]
},
-"patch": {
-"description": "Updates the parameters of a single Service.",
-"flatPath": "v1alpha/projects/{projectsId}/locations/{locationsId}/services/{servicesId}",
-"httpMethod": "PATCH",
-"id": "agentregistry.projects.locations.services.patch",
+"get": {
+"description": "Gets details of a single immutable Revision.",
+"flatPath": "v1alpha/projects/{projectsId}/locations/{locationsId}/skills/{skillsId}/revisions/{revisionsId}",
+"httpMethod": "GET",
+"id": "agentregistry.projects.locations.skills.revisions.get",
"parameterOrder": [
"name"
],
"parameters": {
"name": {
-"description": "Identifier. The resource name of the Service. Format: `projects/{project}/locations/{location}/services/{service}`.",
+"description": "Required. Target revision name.",
"location": "path",
-"pattern": "^projects/[^/]+/locations/[^/]+/services/[^/]+$",
+"pattern": "^projects/[^/]+/locations/[^/]+/skills/[^/]+/revisions/[^/]+$",
"required": true,
"type": "string"
+}
},
-"requestId": {
-"description": "Optional. An optional request ID to identify requests. Specify a unique request ID so that if you must retry your request, the server will know to ignore the request if it has already been completed. The server will guarantee that for at least 60 minutes since the first request. For example, consider a situation where you make an initial request and the request times out. If you make the request again with the same request ID, the server can check if original operation with the same request ID was received, and if so, will ignore the second request. This prevents clients from accidentally creating duplicate commitments. The request ID must be a valid UUID with the exception that zero UUID is not supported (00000000-0000-0000-0000-000000000000).",
+"path": "v1alpha/{+name}",
+"response": {
+"$ref": "SkillRevision"
+},
+"scopes": [
+"https://www.googleapis.com/auth/agentregistry.read-only",
+"https://www.googleapis.com/auth/agentregistry.read-write",
+"https://www.googleapis.com/auth/cloud-platform",
+"https://www.googleapis.com/auth/cloud-platform.read-only"
+],
+"supportsMediaDownload": true,
+"useMediaDownloadService": true
+},
+"list": {
+"description": "Lists all revisions belonging to a parent Skill.",
+"flatPath": "v1alpha/projects/{projectsId}/locations/{locationsId}/skills/{skillsId}/revisions",
+"httpMethod": "GET",
+"id": "agentregistry.projects.locations.skills.revisions.list",
+"parameterOrder": [
+"parent"
+],
+"parameters": {
+"pageSize": {
+"description": "Optional. Page limit size.",
+"format": "int32",
"location": "query",
-"type": "string"
+"type": "integer"
},
-"updateMask": {
-"description": "Optional. Field mask is used to specify the fields to be overwritten in the Service resource by the update. The fields specified in the update_mask are relative to the resource, not the full request. A field will be overwritten if it is in the mask. If the user does not provide a mask then all fields present in the request will be overwritten.",
-"format": "google-fieldmask",
+"pageToken": {
+"description": "Optional. Page offset token.",
"location": "query",
"type": "string"
-}
},
-"path": "v1alpha/{+name}",
-"request": {
-"$ref": "Service"
+"parent": {
+"description": "Required. Parent logical container name to query.",
+"location": "path",
+"pattern": "^projects/[^/]+/locations/[^/]+/skills/[^/]+$",
+"required": true,
+"type": "string"
+}
},
+"path": "v1alpha/{+parent}/revisions",
"response": {
-"$ref": "Operation"
+"$ref": "ListSkillRevisionsResponse"
},
"scopes": [
"https://www.googleapis.com/auth/agentregistry.read-only",
@@ -1070,8 +1554,10 @@
}
}
}
+}
+}
},
-"revision": "20260608",
+"revision": "20260722",
"rootUrl": "https://agentregistry.googleapis.com/",
"schemas": {
"A2ASkill": {
@@ -1259,6 +1745,18 @@
},
"type": "object"
},
+"ArchiveUploadSource": {
+"description": "Direct write-only raw archive payload upload.",
+"id": "ArchiveUploadSource",
+"properties": {
+"archiveContent": {
+"description": "Required. Input only. Write-only raw ZIP/TAR archive payload bytes containing the skill package.",
+"format": "byte",
+"type": "string"
+}
+},
+"type": "object"
+},
"AuthProviderBinding": {
"description": "The AuthProvider of the Binding.",
"id": "AuthProviderBinding",
@@ -1467,6 +1965,52 @@
},
"type": "object"
},
+"Frontmatter": {
+"description": "Structured metadata attributes extracted from the package's local SKILL.md frontmatter.",
+"id": "Frontmatter",
+"properties": {
+"compatibility": {
+"description": "Optional. Environmental dependencies or local sidecars.",
+"type": "string"
+},
+"description": {
+"description": "Required. Functional description.",
+"type": "string"
+},
+"license": {
+"description": "Optional. License.",
+"type": "string"
+},
+"metadata": {
+"additionalProperties": {
+"type": "string"
+},
+"description": "Optional. Extensible flattened map mapping custom tags, authors, and version parameters.",
+"type": "object"
+},
+"name": {
+"description": "Required. The name of the skill.",
+"type": "string"
+}
+},
+"type": "object"
+},
+"GcsSource": {
+"description": "Specifications for Cloud Storage objects.",
+"id": "GcsSource",
+"properties": {
+"generation": {
+"description": "Optional. Cloud Storage object generation ID. If not specified, the latest generation is used.",
+"format": "int64",
+"type": "string"
+},
+"uri": {
+"description": "Required. Cloud Storage object URI. Format: `gs://{bucket_name}/{object_name}`",
+"type": "string"
+}
+},
+"type": "object"
+},
"Interface": {
"description": "Represents the connection details for an Agent or MCP Server.",
"id": "Interface",
@@ -1609,6 +2153,24 @@
},
"type": "object"
},
+"ListPublishersResponse": {
+"description": "Response listing Publishers.",
+"id": "ListPublishersResponse",
+"properties": {
+"nextPageToken": {
+"description": "Page offset continuation token.",
+"type": "string"
+},
+"publishers": {
+"description": "The returned list of Publishers.",
+"items": {
+"$ref": "Publisher"
+},
+"type": "array"
+}
+},
+"type": "object"
+},
"ListServicesResponse": {
"description": "Message for response to listing Services",
"id": "ListServicesResponse",
@@ -1627,6 +2189,49 @@
},
"type": "object"
},
+"ListSkillRevisionsResponse": {
+"description": "Response listing Revisions.",
+"id": "ListSkillRevisionsResponse",
+"properties": {
+"nextPageToken": {
+"description": "Page offset continuation token.",
+"type": "string"
+},
+"skillRevisions": {
+"description": "Returned version snapshot list.",
+"items": {
+"$ref": "SkillRevision"
+},
+"type": "array"
+}
+},
+"type": "object"
+},
+"ListSkillsResponse": {
+"description": "Response structure listing logical Skills.",
+"id": "ListSkillsResponse",
+"properties": {
+"nextPageToken": {
+"description": "Page continuation continuation token.",
+"type": "string"
+},
+"skills": {
+"description": "Returned container list.",
+"items": {
+"$ref": "Skill"
+},
+"type": "array"
+},
+"unreachable": {
+"description": "Unreachable locations or failures.",
+"items": {
+"type": "string"
+},
+"type": "array"
+}
+},
+"type": "object"
+},
"Location": {
"description": "A resource that represents a Google Cloud location.",
"id": "Location",
@@ -1870,6 +2475,50 @@
},
"type": "object"
},
+"Publisher": {
+"description": "Represents a verified Publisher of Skills. Prepopulated publishers include `publishers/cloud.google.com` and `publishers/workspace.google.com`.",
+"id": "Publisher",
+"properties": {
+"displayName": {
+"description": "Optional. Human readable display name of the publisher.",
+"type": "string"
+},
+"documentationUri": {
+"description": "Optional. URI pointing to official publisher documentation.",
+"type": "string"
+},
+"name": {
+"description": "Identifier. Resource name of the publisher. Format: `projects/{project}/locations/{location}/publishers/{publisher}`",
+"type": "string"
+},
+"publisherTier": {
+"description": "Output only. The curation tier of the publisher.",
+"enum": [
+"PUBLISHER_TIER_UNSPECIFIED",
+"FIRST_PARTY",
+"THIRD_PARTY",
+"PRIVATE"
+],
+"enumDescriptions": [
+"Default value. Unspecified.",
+"First-party Google-curated and verified global publishers.",
+"Third-party verified enterprise partner publishers.",
+"Private publishers within the developer's workspace/project."
+],
+"readOnly": true,
+"type": "string"
+},
+"supportUri": {
+"description": "Optional. URI pointing to the support portal or email.",
+"type": "string"
+},
+"verifiedPrefix": {
+"description": "Required. The verified prefix (e.g. \"snowflake-\", \"google-\") associated with this publisher. The system uses this prefix to enforce name-squatting rules during Skill registration. Must be globally unique across all publishers.",
+"type": "string"
+}
+},
+"type": "object"
+},
"SearchAgentsRequest": {
"description": "Message for searching Agents",
"id": "SearchAgentsRequest",
@@ -1946,6 +2595,24 @@
},
"type": "object"
},
+"SearchSkillsResponse": {
+"description": "Response listing searched Skills.",
+"id": "SearchSkillsResponse",
+"properties": {
+"nextPageToken": {
+"description": "Query page offset continuation token.",
+"type": "string"
+},
+"skills": {
+"description": "Matched Skills list.",
+"items": {
+"$ref": "Skill"
+},
+"type": "array"
+}
+},
+"type": "object"
+},
"Service": {
"description": "Represents a user-defined Service.",
"id": "Service",
@@ -2001,6 +2668,186 @@
},
"type": "object"
},
+"Skill": {
+"description": "Represents an Executable Agent Skill or a Composite Tool Suite (Bundle). Sibling resource with Agent and McpServer under agentregistry.googleapis.com.",
+"id": "Skill",
+"properties": {
+"createTime": {
+"description": "Output only. Create time.",
+"format": "google-datetime",
+"readOnly": true,
+"type": "string"
+},
+"defaultRevision": {
+"description": "Optional. The full resource name of the revision currently served by default (floating track). Format: `projects/{project}/locations/{location}/skills/{skill}/revisions/{revision}`",
+"type": "string"
+},
+"description": {
+"description": "Optional. Brief summary describing the capabilities of the skill. Maximum length is 2048 characters.",
+"type": "string"
+},
+"displayName": {
+"description": "Required. Human-readable display name of the skill. Maximum length is 128 characters.",
+"type": "string"
+},
+"frontmatter": {
+"$ref": "Frontmatter",
+"description": "Output only. Lightweight frontmatter metadata attributes copied from the default revision.",
+"readOnly": true
+},
+"initialRevision": {
+"$ref": "SkillRevision",
+"description": "Optional. Input only. Optional nested initial revision payload to support standard one-shot creation. The server processes this field on input during creation but must never return it in responses."
+},
+"name": {
+"description": "Identifier. Resource name of the Skill. Format: `projects/{project}/locations/{location}/skills/{skill}` The `{skill}` segment acts as the resource ID. If the skill is associated with a Publisher, this segment typically uses a hyphenated namespace prefix corresponding to the publisher (e.g., `google-workspace-create-docs`).",
+"type": "string"
+},
+"publisher": {
+"description": "Optional. The publisher resource associated with this skill. Format: `projects/{project}/locations/{location}/publishers/{publisher}` The publisher dictates the allowed namespace prefixes for the skill's name and logical `skill_id` (e.g., Publisher `google` authorizes the `google-*` prefix).",
+"type": "string"
+},
+"skillId": {
+"description": "Output only. A stable, globally unique logical identifier for the skill. It is securely constructed by the backend by combining the associated `publisher`'s verified namespace and the skill's resource ID to enforce strict ownership. For example, the prefix `google-` is reserved exclusively for first-party Google publishers to prevent namespace squatting. Example: `urn:skill:google-workspace:create-docs`",
+"readOnly": true,
+"type": "string"
+},
+"state": {
+"description": "Output only. The system-managed state of the skill.",
+"enum": [
+"STATE_UNSPECIFIED",
+"STATE_CREATING",
+"STATE_DRAFT",
+"STATE_ACTIVE",
+"STATE_DISABLED",
+"STATE_DEPRECATED",
+"STATE_DECOMMISSIONED",
+"STATE_DELETING"
+],
+"enumDescriptions": [
+"Default value. This value is unused.",
+"The skill is being created. It is not served.",
+"The skill is in draft, or lacks a valid payload. It is not served.",
+"The skill is active and is served.",
+"The skill is disabled and is not served.",
+"The skill is deprecated. It is served, but emits warnings.",
+"The skill is decommissioned and is not served.",
+"The skill is being deleted. It is not served."
+],
+"readOnly": true,
+"type": "string"
+},
+"targetState": {
+"description": "Required. User-managed target state of the skill.",
+"enum": [
+"TARGET_STATE_UNSPECIFIED",
+"TARGET_STATE_DRAFT",
+"TARGET_STATE_ACTIVE",
+"TARGET_STATE_DISABLED",
+"TARGET_STATE_DEPRECATED",
+"TARGET_STATE_DECOMMISSIONED"
+],
+"enumDescriptions": [
+"Default value. This value is unused.",
+"The skill is in draft and cannot be served.",
+"The skill is active and can be served.",
+"The skill is disabled and cannot be served.",
+"The skill is deprecated. It can still be served, but emits warnings.",
+"The skill is decommissioned and cannot be served."
+],
+"type": "string"
+},
+"type": {
+"description": "Required. Structural deployment type (SIMPLE leaf vs COMPOSITE bundle).",
+"enum": [
+"TYPE_UNSPECIFIED",
+"SIMPLE"
+],
+"enumDescriptions": [
+"Default value. This value is unused.",
+"A standard, leaf executable skill containing natural language and code."
+],
+"type": "string"
+},
+"uid": {
+"description": "Output only. Universally unique identifier (UUID4) for the logical container.",
+"readOnly": true,
+"type": "string"
+},
+"updateTime": {
+"description": "Output only. Update time.",
+"format": "google-datetime",
+"readOnly": true,
+"type": "string"
+}
+},
+"type": "object"
+},
+"SkillRevision": {
+"description": "Represents an immutable, versioned snapshot of a Skill package.",
+"id": "SkillRevision",
+"properties": {
+"archiveUploadSource": {
+"$ref": "ArchiveUploadSource",
+"description": "Optional. Immutable. Direct write-only raw archive upload source."
+},
+"createTime": {
+"description": "Output only. Revision creation timestamp.",
+"format": "google-datetime",
+"readOnly": true,
+"type": "string"
+},
+"frontmatter": {
+"$ref": "Frontmatter",
+"description": "Output only. Extracted YAML frontmatter configuration snapshot.",
+"readOnly": true
+},
+"gcsSource": {
+"$ref": "GcsSource",
+"description": "Optional. Immutable. Cloud Storage object generation URI."
+},
+"name": {
+"description": "Identifier. Resource name of the SkillRevision. Format: `projects/{project}/locations/{location}/skills/{skill}/revisions/{revision}`",
+"type": "string"
+},
+"sha256Hash": {
+"description": "Output only. Cryptographic SHA-256 integrity and deduplication digest of the payload zip.",
+"readOnly": true,
+"type": "string"
+},
+"sizeBytes": {
+"description": "Output only. Size of the compiled zip payload in bytes (assists client download progress).",
+"format": "int64",
+"readOnly": true,
+"type": "string"
+},
+"state": {
+"description": "Output only. The system-managed lifecycle state of this revision.",
+"enum": [
+"STATE_UNSPECIFIED",
+"CREATING",
+"ACTIVE",
+"FAILED",
+"DELETING"
+],
+"enumDescriptions": [
+"Default value. This value is unused.",
+"The revision is being created.",
+"The revision is active.",
+"The revision failed to compile or ingest.",
+"The revision is being deleted."
+],
+"readOnly": true,
+"type": "string"
+},
+"uid": {
+"description": "Output only. Universally unique identifier (UUID4) for the skill revision.",
+"readOnly": true,
+"type": "string"
+}
+},
+"type": "object"
+},
"Source": {
"description": "The source of the Binding.",
"id": "Source",
From a3f41ddc7d50d62a6dabe29e4731748e477c3422 Mon Sep 17 00:00:00 2001
From: Yoshi Automation
Date: Tue, 28 Jul 2026 07:56:27 +0000
Subject: [PATCH 05/59] feat(aiplatform): update the api
#### aiplatform:v1
The following keys were added:
- resources.projects.resources.locations.resources.indexEndpoints.methods.mutateDeployedIndex.parameters.updateMask (Total Keys: 3)
- resources.projects.resources.locations.resources.memoryBanks.methods.ingestEvents (Total Keys: 12)
- resources.projects.resources.locations.resources.memoryBanks.resources.memories.methods.create (Total Keys: 14)
- resources.projects.resources.locations.resources.memoryBanks.resources.memories.methods.delete (Total Keys: 11)
- resources.projects.resources.locations.resources.memoryBanks.resources.memories.methods.generate (Total Keys: 12)
- resources.projects.resources.locations.resources.memoryBanks.resources.memories.methods.list (Total Keys: 20)
- resources.projects.resources.locations.resources.memoryBanks.resources.memories.methods.patch (Total Keys: 15)
- resources.projects.resources.locations.resources.memoryBanks.resources.memories.methods.purge (Total Keys: 12)
- resources.projects.resources.locations.resources.memoryBanks.resources.memories.methods.retrieve (Total Keys: 12)
- resources.projects.resources.locations.resources.memoryBanks.resources.memories.methods.rollback (Total Keys: 12)
- resources.projects.resources.locations.resources.publishers.resources.v1.methods.responses (Total Keys: 14)
- schemas.CloudAiLargeModelsVisionGenerateVideoExperiments.properties.cfgScale (Total Keys: 2)
- schemas.CloudAiLargeModelsVisionGenerateVideoExperiments.properties.colorAlignment.$ref (Total Keys: 1)
- schemas.CloudAiLargeModelsVisionGenerateVideoExperiments.properties.omniRewriter.$ref (Total Keys: 1)
- schemas.CloudAiLargeModelsVisionGenerateVideoExperiments.properties.spatialAlignment.$ref (Total Keys: 1)
- schemas.CloudAiLargeModelsVisionGenerateVideoExperimentsColorAlignmentConfig (Total Keys: 3)
- schemas.CloudAiLargeModelsVisionGenerateVideoExperimentsOmniRewriterConfig (Total Keys: 6)
- schemas.CloudAiLargeModelsVisionGenerateVideoExperimentsSpatialAlignmentConfig (Total Keys: 3)
- schemas.GoogleCloudAiplatformV1AudioTranscription (Total Keys: 30)
- schemas.GoogleCloudAiplatformV1DeprovisionSemanticGovernancePolicyEngineRequest.properties.force.type (Total Keys: 1)
- schemas.GoogleCloudAiplatformV1EvaluationMetric.properties.encryptionSpec.$ref (Total Keys: 1)
- schemas.GoogleCloudAiplatformV1EvaluationSet.properties.encryptionSpec.$ref (Total Keys: 1)
- schemas.GoogleCloudAiplatformV1GatewayConfig.properties.allowedProjects (Total Keys: 2)
- schemas.GoogleCloudAiplatformV1GenerationConfig.properties.audioTranscriptionConfig.$ref (Total Keys: 1)
- schemas.GoogleCloudAiplatformV1GroundingMetadata.properties.retrievalQueries (Total Keys: 2)
- schemas.GoogleCloudAiplatformV1Part.properties.audioTranscription.$ref (Total Keys: 1)
- schemas.GoogleCloudAiplatformV1ReasoningEngineSpecBuildSpec.properties.serviceAccount.type (Total Keys: 1)
- schemas.GoogleCloudAiplatformV1ReasoningEngineSpecContainerSpec.properties.port (Total Keys: 2)
- schemas.GoogleCloudAiplatformV1SandboxEnvironmentTemplateEgressControlConfig.properties.customerVpcNetwork.type (Total Keys: 1)
- schemas.GoogleCloudAiplatformV1SandboxEnvironmentTemplateEgressControlConfig.properties.dnsPeeringConfigs (Total Keys: 2)
- schemas.GoogleCloudAiplatformV1SandboxEnvironmentTemplateEgressControlConfig.properties.networkAttachment.type (Total Keys: 1)
- schemas.GoogleCloudAiplatformV1SandboxEnvironmentTemplateEgressControlConfigDnsPeeringConfig (Total Keys: 5)
#### aiplatform:v1beta1
The following keys were deleted:
- schemas.GenaiVertexV1beta1FunctionResultDelta.properties.contentList.$ref (Total Keys: 1)
- schemas.GenaiVertexV1beta1FunctionResultDelta.properties.stringResult.type (Total Keys: 1)
- schemas.GenaiVertexV1beta1FunctionResultDelta.properties.structResult.$ref (Total Keys: 1)
- schemas.GenaiVertexV1beta1FunctionResultStep.properties.contentList.$ref (Total Keys: 1)
- schemas.GenaiVertexV1beta1FunctionResultStep.properties.stringResult.type (Total Keys: 1)
- schemas.GenaiVertexV1beta1FunctionResultStep.properties.structResult.$ref (Total Keys: 1)
- schemas.GenaiVertexV1beta1GenerationConfig.properties.frequency_penalty (Total Keys: 2)
- schemas.GenaiVertexV1beta1GenerationConfig.properties.presence_penalty (Total Keys: 2)
- schemas.GenaiVertexV1beta1McpServerToolResultDelta.properties.contentList.$ref (Total Keys: 1)
- schemas.GenaiVertexV1beta1McpServerToolResultDelta.properties.stringResult.type (Total Keys: 1)
- schemas.GenaiVertexV1beta1McpServerToolResultDelta.properties.structResult.$ref (Total Keys: 1)
- schemas.GenaiVertexV1beta1McpServerToolResultStep.properties.contentList.$ref (Total Keys: 1)
- schemas.GenaiVertexV1beta1McpServerToolResultStep.properties.stringResult.type (Total Keys: 1)
- schemas.GenaiVertexV1beta1McpServerToolResultStep.properties.structResult.$ref (Total Keys: 1)
- schemas.GenaiVertexV1beta1ModelInteraction.properties.cached_content.type (Total Keys: 1)
The following keys were added:
- resources.memoryBanks.methods.ingestEvents (Total Keys: 12)
- resources.memoryBanks.resources.memories.methods.create (Total Keys: 14)
- resources.memoryBanks.resources.memories.methods.delete (Total Keys: 11)
- resources.memoryBanks.resources.memories.methods.generate (Total Keys: 12)
- resources.memoryBanks.resources.memories.methods.list (Total Keys: 20)
- resources.memoryBanks.resources.memories.methods.patch (Total Keys: 15)
- resources.memoryBanks.resources.memories.methods.purge (Total Keys: 12)
- resources.memoryBanks.resources.memories.methods.retrieve (Total Keys: 24)
- resources.memoryBanks.resources.memories.methods.rollback (Total Keys: 12)
- resources.projects.resources.locations.resources.indexEndpoints.methods.mutateDeployedIndex.parameters.updateMask (Total Keys: 3)
- resources.projects.resources.locations.resources.memoryBanks.methods.ingestEvents (Total Keys: 12)
- resources.projects.resources.locations.resources.memoryBanks.resources.memories.methods.create (Total Keys: 14)
- resources.projects.resources.locations.resources.memoryBanks.resources.memories.methods.delete (Total Keys: 11)
- resources.projects.resources.locations.resources.memoryBanks.resources.memories.methods.generate (Total Keys: 12)
- resources.projects.resources.locations.resources.memoryBanks.resources.memories.methods.list (Total Keys: 20)
- resources.projects.resources.locations.resources.memoryBanks.resources.memories.methods.patch (Total Keys: 15)
- resources.projects.resources.locations.resources.memoryBanks.resources.memories.methods.purge (Total Keys: 12)
- resources.projects.resources.locations.resources.memoryBanks.resources.memories.methods.retrieve (Total Keys: 24)
- resources.projects.resources.locations.resources.memoryBanks.resources.memories.methods.rollback (Total Keys: 12)
- resources.projects.resources.locations.resources.publishers.resources.v1.methods.responses (Total Keys: 14)
- resources.projects.resources.locations.resources.reasoningEngines.resources.feedbackEntries.methods.create (Total Keys: 12)
- resources.projects.resources.locations.resources.reasoningEngines.resources.feedbackEntries.methods.delete (Total Keys: 11)
- resources.projects.resources.locations.resources.reasoningEngines.resources.feedbackEntries.methods.get (Total Keys: 22)
- resources.projects.resources.locations.resources.reasoningEngines.resources.feedbackEntries.methods.list (Total Keys: 20)
- resources.projects.resources.locations.resources.reasoningEngines.resources.feedbackEntries.methods.patch (Total Keys: 15)
- resources.projects.resources.locations.resources.reasoningEngines.resources.feedbackEntries.methods.updateFeedbackContext (Total Keys: 15)
- resources.projects.resources.locations.resources.servingProfiles.methods.create (Total Keys: 14)
- resources.projects.resources.locations.resources.servingProfiles.methods.delete (Total Keys: 11)
- resources.projects.resources.locations.resources.servingProfiles.methods.get (Total Keys: 11)
- resources.projects.resources.locations.resources.servingProfiles.methods.list (Total Keys: 16)
- resources.projects.resources.locations.resources.servingProfiles.methods.patch (Total Keys: 15)
- schemas.CloudAiLargeModelsVisionGenerateVideoExperiments.properties.cfgScale (Total Keys: 2)
- schemas.CloudAiLargeModelsVisionGenerateVideoExperiments.properties.colorAlignment.$ref (Total Keys: 1)
- schemas.CloudAiLargeModelsVisionGenerateVideoExperiments.properties.omniRewriter.$ref (Total Keys: 1)
- schemas.CloudAiLargeModelsVisionGenerateVideoExperiments.properties.spatialAlignment.$ref (Total Keys: 1)
- schemas.CloudAiLargeModelsVisionGenerateVideoExperimentsColorAlignmentConfig (Total Keys: 3)
- schemas.CloudAiLargeModelsVisionGenerateVideoExperimentsOmniRewriterConfig (Total Keys: 6)
- schemas.CloudAiLargeModelsVisionGenerateVideoExperimentsSpatialAlignmentConfig (Total Keys: 3)
- schemas.GenaiVertexV1beta1AgentInteraction.properties.antigravityConfig.$ref (Total Keys: 1)
- schemas.GenaiVertexV1beta1AgentInteraction.properties.codeMenderConfig.$ref (Total Keys: 1)
- schemas.GenaiVertexV1beta1AntigravityAgentConfig (Total Keys: 5)
- schemas.GenaiVertexV1beta1CodeExecutionCallContent.deprecated (Total Keys: 1)
- schemas.GenaiVertexV1beta1CodeExecutionResultContent.deprecated (Total Keys: 1)
- schemas.GenaiVertexV1beta1CodeMenderAgentConfig (Total Keys: 26)
- schemas.GenaiVertexV1beta1EnvironmentConfig.properties.environmentId.type (Total Keys: 1)
- schemas.GenaiVertexV1beta1FileSearchCallContent.deprecated (Total Keys: 1)
- schemas.GenaiVertexV1beta1FileSearchResultContent.deprecated (Total Keys: 1)
- schemas.GenaiVertexV1beta1FunctionCallContent.deprecated (Total Keys: 1)
- schemas.GenaiVertexV1beta1FunctionResultContent.deprecated (Total Keys: 1)
- schemas.GenaiVertexV1beta1FunctionResultDelta.properties.result.$ref (Total Keys: 1)
- schemas.GenaiVertexV1beta1FunctionResultStep.properties.result.$ref (Total Keys: 1)
- schemas.GenaiVertexV1beta1GoogleMapsCallContent.deprecated (Total Keys: 1)
- schemas.GenaiVertexV1beta1GoogleMapsResultContent.deprecated (Total Keys: 1)
- schemas.GenaiVertexV1beta1GoogleSearchCallContent.deprecated (Total Keys: 1)
- schemas.GenaiVertexV1beta1GoogleSearchResultContent.deprecated (Total Keys: 1)
- schemas.GenaiVertexV1beta1Interaction.properties.labels (Total Keys: 2)
- schemas.GenaiVertexV1beta1Interaction.properties.localEnvironment.$ref (Total Keys: 1)
- schemas.GenaiVertexV1beta1Interaction.properties.safety_settings (Total Keys: 2)
- schemas.GenaiVertexV1beta1LocalEnvironmentConfig (Total Keys: 2)
- schemas.GenaiVertexV1beta1McpServerToolResultDelta.properties.result.$ref (Total Keys: 1)
- schemas.GenaiVertexV1beta1McpServerToolResultStep.properties.result.$ref (Total Keys: 1)
- schemas.GenaiVertexV1beta1RetrievalCallDelta (Total Keys: 4)
- schemas.GenaiVertexV1beta1RetrievalCallStep (Total Keys: 8)
- schemas.GenaiVertexV1beta1RetrievalResultDelta (Total Keys: 3)
- schemas.GenaiVertexV1beta1RetrievalResultStep (Total Keys: 3)
- schemas.GenaiVertexV1beta1SafetySetting (Total Keys: 5)
- schemas.GenaiVertexV1beta1ServerToolCallDelta.properties.retrievalCall.$ref (Total Keys: 1)
- schemas.GenaiVertexV1beta1ServerToolResultDelta.properties.retrievalResult.$ref (Total Keys: 1)
- schemas.GenaiVertexV1beta1ThoughtContent.deprecated (Total Keys: 1)
- schemas.GenaiVertexV1beta1ToolCallContent.deprecated (Total Keys: 1)
- schemas.GenaiVertexV1beta1ToolCallStep.properties.retrievalCall.$ref (Total Keys: 1)
- schemas.GenaiVertexV1beta1ToolResultContent.deprecated (Total Keys: 1)
- schemas.GenaiVertexV1beta1ToolResultStep.properties.retrievalResult.$ref (Total Keys: 1)
- schemas.GoogleCloudAiplatformV1beta1AudioTranscription (Total Keys: 30)
- schemas.GoogleCloudAiplatformV1beta1BatchPredictionJob.properties.endpoint.type (Total Keys: 1)
- schemas.GoogleCloudAiplatformV1beta1DeprovisionSemanticGovernancePolicyEngineRequest.properties.force.type (Total Keys: 1)
- schemas.GoogleCloudAiplatformV1beta1EvaluationMetric.properties.encryptionSpec.$ref (Total Keys: 1)
- schemas.GoogleCloudAiplatformV1beta1EvaluationSet.properties.encryptionSpec.$ref (Total Keys: 1)
- schemas.GoogleCloudAiplatformV1beta1FeedbackContext (Total Keys: 5)
- schemas.GoogleCloudAiplatformV1beta1FeedbackEntry (Total Keys: 19)
- schemas.GoogleCloudAiplatformV1beta1GatewayConfig.properties.allowedProjects (Total Keys: 2)
- schemas.GoogleCloudAiplatformV1beta1GenerationConfig.properties.audioTranscriptionConfig.$ref (Total Keys: 1)
- schemas.GoogleCloudAiplatformV1beta1ListFeedbackEntriesResponse (Total Keys: 5)
- schemas.GoogleCloudAiplatformV1beta1ListServingProfilesResponse (Total Keys: 7)
- schemas.GoogleCloudAiplatformV1beta1Part.properties.audioTranscription.$ref (Total Keys: 1)
- schemas.GoogleCloudAiplatformV1beta1ReasoningEngineSpecBuildSpec.properties.serviceAccount.type (Total Keys: 1)
- schemas.GoogleCloudAiplatformV1beta1ReasoningEngineSpecContainerSpec.properties.port (Total Keys: 2)
- schemas.GoogleCloudAiplatformV1beta1ReinforcementTuningHyperParameters.properties.stepCount (Total Keys: 2)
- schemas.GoogleCloudAiplatformV1beta1SandboxEnvironmentTemplateEgressControlConfig.properties.customerVpcNetwork.type (Total Keys: 1)
- schemas.GoogleCloudAiplatformV1beta1SandboxEnvironmentTemplateEgressControlConfig.properties.dnsPeeringConfigs (Total Keys: 2)
- schemas.GoogleCloudAiplatformV1beta1SandboxEnvironmentTemplateEgressControlConfig.properties.networkAttachment.type (Total Keys: 1)
- schemas.GoogleCloudAiplatformV1beta1SandboxEnvironmentTemplateEgressControlConfigDnsPeeringConfig (Total Keys: 5)
- schemas.GoogleCloudAiplatformV1beta1ServingProfile (Total Keys: 15)
- schemas.GoogleCloudAiplatformV1beta1SetPublisherModelConfigRequest.properties.updateMask (Total Keys: 2)
- schemas.GoogleCloudAiplatformV1beta1StructuredMemoryConfigSchemaConfig.properties.jsonSchema.type (Total Keys: 1)
---
docs/dyn/aiplatform_v1.endpoints.html | 156 +
..._v1.projects.locations.cachedContents.html | 132 +
...tform_v1.projects.locations.endpoints.html | 156 +
...v1.projects.locations.evaluationItems.html | 352 +
....projects.locations.evaluationMetrics.html | 148 +
..._v1.projects.locations.evaluationRuns.html | 680 +
..._v1.projects.locations.evaluationSets.html | 21 +
.../dyn/aiplatform_v1.projects.locations.html | 401 +
..._v1.projects.locations.indexEndpoints.html | 5 +-
...orm_v1.projects.locations.memoryBanks.html | 165 +
...ojects.locations.memoryBanks.memories.html | 657 +
...ations.memoryBanks.memories.revisions.html | 191 +
...platform_v1.projects.locations.models.html | 14 +-
...1.projects.locations.onlineEvaluators.html | 144 +-
...form_v1.projects.locations.publishers.html | 5 +
....projects.locations.publishers.models.html | 167 +
...m_v1.projects.locations.publishers.v1.html | 128 +
...1.projects.locations.reasoningEngines.html | 52 +
...s.locations.reasoningEngines.memories.html | 22 +
...ngEngines.sandboxEnvironmentTemplates.html | 27 +
...ions.reasoningEngines.sessions.events.html | 14 +
...s.locations.reasoningEngines.sessions.html | 14 +
...ations.semanticGovernancePolicyEngine.html | 1 +
....projects.locations.trainingPipelines.html | 8 +-
...form_v1.projects.locations.tuningJobs.html | 505 +
docs/dyn/aiplatform_v1.publishers.models.html | 156 +
docs/dyn/aiplatform_v1.reasoningEngines.html | 52 +
...ngEngines.sandboxEnvironmentTemplates.html | 27 +
docs/dyn/aiplatform_v1.v1.html | 296 +
...iplatform_v1beta1.batchPredictionJobs.html | 4 +
docs/dyn/aiplatform_v1beta1.endpoints.html | 150 +
docs/dyn/aiplatform_v1beta1.interactions.html | 29302 +++++---------
docs/dyn/aiplatform_v1beta1.memoryBanks.html | 167 +
...platform_v1beta1.memoryBanks.memories.html | 725 +
...1beta1.memoryBanks.memories.revisions.html | 191 +
docs/dyn/aiplatform_v1beta1.projects.html | 5 +-
...locations.agentAnomalyDetectionScopes.html | 30 +-
...rojects.locations.batchPredictionJobs.html | 4 +
...ta1.projects.locations.cachedContents.html | 132 +
...m_v1beta1.projects.locations.datasets.html | 78 +
..._v1beta1.projects.locations.endpoints.html | 162 +-
...a1.projects.locations.evaluationItems.html | 528 +
....projects.locations.evaluationMetrics.html | 148 +
...ta1.projects.locations.evaluationRuns.html | 988 +
...ta1.projects.locations.evaluationSets.html | 21 +
...eta1.projects.locations.exampleStores.html | 99 +
...v1beta1.projects.locations.extensions.html | 22 +
...aiplatform_v1beta1.projects.locations.html | 434 +
...ta1.projects.locations.indexEndpoints.html | 5 +-
...beta1.projects.locations.interactions.html | 32586 ++++++----------
...1beta1.projects.locations.memoryBanks.html | 167 +
...ojects.locations.memoryBanks.memories.html | 725 +
...ations.memoryBanks.memories.revisions.html | 191 +
...orm_v1beta1.projects.locations.models.html | 14 +-
....analyzedSessions.analyzedInvocations.html | 8 +-
...ions.monitoredAgents.analyzedSessions.html | 66 +-
...a1.projects.locations.monitoredAgents.html | 12 +-
...1.projects.locations.onlineEvaluators.html | 144 +-
...v1beta1.projects.locations.publishers.html | 5 +
....projects.locations.publishers.models.html | 166 +-
...eta1.projects.locations.publishers.v1.html | 128 +
...ions.reasoningEngines.a2aTasks.events.html | 33 +
...s.locations.reasoningEngines.a2aTasks.html | 121 +
...ions.reasoningEngines.feedbackEntries.html | 779 +
...1.projects.locations.reasoningEngines.html | 56 +
...s.locations.reasoningEngines.memories.html | 22 +
...ons.reasoningEngines.runtimeRevisions.html | 4 +
...ngEngines.sandboxEnvironmentTemplates.html | 27 +
...ions.reasoningEngines.sessions.events.html | 11 +
...s.locations.reasoningEngines.sessions.html | 11 +
...ations.semanticGovernancePolicyEngine.html | 1 +
...a1.projects.locations.servingProfiles.html | 215 +
....projects.locations.trainingPipelines.html | 8 +-
...v1beta1.projects.locations.tuningJobs.html | 1099 +
.../aiplatform_v1beta1.publishers.models.html | 150 +
.../aiplatform_v1beta1.reasoningEngines.html | 56 +
...orm_v1beta1.reasoningEngines.memories.html | 22 +
...ngEngines.sandboxEnvironmentTemplates.html | 27 +
...eta1.reasoningEngines.sessions.events.html | 11 +
...orm_v1beta1.reasoningEngines.sessions.html | 11 +
docs/dyn/aiplatform_v1beta1.v1beta1.html | 307 +
.../documents/aiplatform.v1.json | 643 +-
.../documents/aiplatform.v1beta1.json | 2600 +-
83 files changed, 37326 insertions(+), 40991 deletions(-)
create mode 100644 docs/dyn/aiplatform_v1.projects.locations.memoryBanks.memories.revisions.html
create mode 100644 docs/dyn/aiplatform_v1.projects.locations.publishers.v1.html
create mode 100644 docs/dyn/aiplatform_v1beta1.memoryBanks.memories.revisions.html
create mode 100644 docs/dyn/aiplatform_v1beta1.projects.locations.memoryBanks.memories.revisions.html
create mode 100644 docs/dyn/aiplatform_v1beta1.projects.locations.publishers.v1.html
diff --git a/docs/dyn/aiplatform_v1.endpoints.html b/docs/dyn/aiplatform_v1.endpoints.html
index eb53bb10a0..9f7a0007b2 100644
--- a/docs/dyn/aiplatform_v1.endpoints.html
+++ b/docs/dyn/aiplatform_v1.endpoints.html
@@ -128,6 +128,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -243,6 +254,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -317,6 +339,23 @@ Method Details
],
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Generation config that the model will use to generate the response.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -461,6 +500,17 @@ Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -837,6 +887,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -911,6 +972,23 @@ Method Details
],
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Generation config.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -1065,6 +1143,17 @@ Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -1411,6 +1500,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Output only. The content of the candidate.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -1559,6 +1659,9 @@ Method Details
"retrievalMetadata": { # Metadata related to the retrieval grounding source. This is part of the `GroundingMetadata` returned when grounding is enabled. # Optional. Output only. Metadata related to the retrieval grounding source.
"googleSearchDynamicRetrievalScore": 3.14, # Optional. A score indicating how likely it is that a Google Search query could help answer the prompt. The score is in the range of `[0, 1]`. A score of 1 means the model is confident that a search will be helpful, and 0 means it is not. This score is populated only when Google Search grounding and dynamic retrieval are enabled. The score is used to determine whether to trigger a search.
},
+ "retrievalQueries": [ # Optional. The queries that were executed by the retrieval tools. This field is populated only when the grounding source is a retrieval tool, such as Vertex AI Search.
+ "A String",
+ ],
"searchEntryPoint": { # An entry point for displaying Google Search results. A `SearchEntryPoint` is populated when the grounding source for a model's response is Google Search. It provides information that you can use to display the search results in your application. # Optional. A web search entry point that can be used to display search results. This field is populated only when the grounding source is Google Search.
"renderedContent": "A String", # Optional. An HTML snippet that can be embedded in a web page or an application's webview. This snippet displays a search result, including the title, URL, and a brief description of the search result.
"sdkBlob": "A String", # Optional. A base64-encoded JSON object that contains a list of search queries and their corresponding search URLs. This information can be used to build a custom search UI.
@@ -1771,6 +1874,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -1845,6 +1959,23 @@ Method Details
],
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Generation config.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -1999,6 +2130,17 @@ Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -2345,6 +2487,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Output only. The content of the candidate.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -2493,6 +2646,9 @@ Method Details
"retrievalMetadata": { # Metadata related to the retrieval grounding source. This is part of the `GroundingMetadata` returned when grounding is enabled. # Optional. Output only. Metadata related to the retrieval grounding source.
"googleSearchDynamicRetrievalScore": 3.14, # Optional. A score indicating how likely it is that a Google Search query could help answer the prompt. The score is in the range of `[0, 1]`. A score of 1 means the model is confident that a search will be helpful, and 0 means it is not. This score is populated only when Google Search grounding and dynamic retrieval are enabled. The score is used to determine whether to trigger a search.
},
+ "retrievalQueries": [ # Optional. The queries that were executed by the retrieval tools. This field is populated only when the grounding source is a retrieval tool, such as Vertex AI Search.
+ "A String",
+ ],
"searchEntryPoint": { # An entry point for displaying Google Search results. A `SearchEntryPoint` is populated when the grounding source for a model's response is Google Search. It provides information that you can use to display the search results in your application. # Optional. A web search entry point that can be used to display search results. This field is populated only when the grounding source is Google Search.
"renderedContent": "A String", # Optional. An HTML snippet that can be embedded in a web page or an application's webview. This snippet displays a search result, including the title, URL, and a brief description of the search result.
"sdkBlob": "A String", # Optional. A base64-encoded JSON object that contains a list of search queries and their corresponding search URLs. This information can be used to build a custom search UI.
diff --git a/docs/dyn/aiplatform_v1.projects.locations.cachedContents.html b/docs/dyn/aiplatform_v1.projects.locations.cachedContents.html
index d686f998ac..782fa71519 100644
--- a/docs/dyn/aiplatform_v1.projects.locations.cachedContents.html
+++ b/docs/dyn/aiplatform_v1.projects.locations.cachedContents.html
@@ -115,6 +115,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -198,6 +209,17 @@ Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Input only. Immutable. Developer set system instruction. Currently, text only
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -535,6 +557,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -618,6 +651,17 @@ Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Input only. Immutable. Developer set system instruction. Currently, text only
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -980,6 +1024,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -1063,6 +1118,17 @@ Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Input only. Immutable. Developer set system instruction. Currently, text only
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -1411,6 +1477,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -1494,6 +1571,17 @@ Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Input only. Immutable. Developer set system instruction. Currently, text only
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -1850,6 +1938,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -1933,6 +2032,17 @@ Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Input only. Immutable. Developer set system instruction. Currently, text only
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -2271,6 +2381,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -2354,6 +2475,17 @@ Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Input only. Immutable. Developer set system instruction. Currently, text only
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
diff --git a/docs/dyn/aiplatform_v1.projects.locations.endpoints.html b/docs/dyn/aiplatform_v1.projects.locations.endpoints.html
index bb29f97b60..93157f9abb 100644
--- a/docs/dyn/aiplatform_v1.projects.locations.endpoints.html
+++ b/docs/dyn/aiplatform_v1.projects.locations.endpoints.html
@@ -196,6 +196,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -311,6 +322,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -385,6 +407,23 @@ Method Details
],
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Generation config that the model will use to generate the response.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -529,6 +568,17 @@ Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -1801,6 +1851,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -1875,6 +1936,23 @@ Method Details
],
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Generation config.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -2029,6 +2107,17 @@ Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -2375,6 +2464,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Output only. The content of the candidate.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -2523,6 +2623,9 @@ Method Details
"retrievalMetadata": { # Metadata related to the retrieval grounding source. This is part of the `GroundingMetadata` returned when grounding is enabled. # Optional. Output only. Metadata related to the retrieval grounding source.
"googleSearchDynamicRetrievalScore": 3.14, # Optional. A score indicating how likely it is that a Google Search query could help answer the prompt. The score is in the range of `[0, 1]`. A score of 1 means the model is confident that a search will be helpful, and 0 means it is not. This score is populated only when Google Search grounding and dynamic retrieval are enabled. The score is used to determine whether to trigger a search.
},
+ "retrievalQueries": [ # Optional. The queries that were executed by the retrieval tools. This field is populated only when the grounding source is a retrieval tool, such as Vertex AI Search.
+ "A String",
+ ],
"searchEntryPoint": { # An entry point for displaying Google Search results. A `SearchEntryPoint` is populated when the grounding source for a model's response is Google Search. It provides information that you can use to display the search results in your application. # Optional. A web search entry point that can be used to display search results. This field is populated only when the grounding source is Google Search.
"renderedContent": "A String", # Optional. An HTML snippet that can be embedded in a web page or an application's webview. This snippet displays a search result, including the title, URL, and a brief description of the search result.
"sdkBlob": "A String", # Optional. A base64-encoded JSON object that contains a list of search queries and their corresponding search URLs. This information can be used to build a custom search UI.
@@ -4217,6 +4320,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -4291,6 +4405,23 @@ Method Details
],
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Generation config.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -4445,6 +4576,17 @@ Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -4791,6 +4933,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Output only. The content of the candidate.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -4939,6 +5092,9 @@ Method Details
"retrievalMetadata": { # Metadata related to the retrieval grounding source. This is part of the `GroundingMetadata` returned when grounding is enabled. # Optional. Output only. Metadata related to the retrieval grounding source.
"googleSearchDynamicRetrievalScore": 3.14, # Optional. A score indicating how likely it is that a Google Search query could help answer the prompt. The score is in the range of `[0, 1]`. A score of 1 means the model is confident that a search will be helpful, and 0 means it is not. This score is populated only when Google Search grounding and dynamic retrieval are enabled. The score is used to determine whether to trigger a search.
},
+ "retrievalQueries": [ # Optional. The queries that were executed by the retrieval tools. This field is populated only when the grounding source is a retrieval tool, such as Vertex AI Search.
+ "A String",
+ ],
"searchEntryPoint": { # An entry point for displaying Google Search results. A `SearchEntryPoint` is populated when the grounding source for a model's response is Google Search. It provides information that you can use to display the search results in your application. # Optional. A web search entry point that can be used to display search results. This field is populated only when the grounding source is Google Search.
"renderedContent": "A String", # Optional. An HTML snippet that can be embedded in a web page or an application's webview. This snippet displays a search result, including the title, URL, and a brief description of the search result.
"sdkBlob": "A String", # Optional. A base64-encoded JSON object that contains a list of search queries and their corresponding search URLs. This information can be used to build a custom search UI.
diff --git a/docs/dyn/aiplatform_v1.projects.locations.evaluationItems.html b/docs/dyn/aiplatform_v1.projects.locations.evaluationItems.html
index 393286c4cf..4f528d8fcd 100644
--- a/docs/dyn/aiplatform_v1.projects.locations.evaluationItems.html
+++ b/docs/dyn/aiplatform_v1.projects.locations.evaluationItems.html
@@ -595,6 +595,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -1164,6 +1175,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -1732,6 +1754,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -1819,6 +1852,17 @@ Method Details
"a_key": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -2432,6 +2476,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -3001,6 +3056,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -3569,6 +3635,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -3656,6 +3733,17 @@ Method Details
"a_key": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -4260,6 +4348,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -4829,6 +4928,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -5397,6 +5507,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -5484,6 +5605,17 @@ Method Details
"a_key": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -6097,6 +6229,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -6666,6 +6809,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -7234,6 +7388,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -7321,6 +7486,17 @@ Method Details
"a_key": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -7967,6 +8143,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -8536,6 +8723,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -9104,6 +9302,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -9191,6 +9400,17 @@ Method Details
"a_key": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -9804,6 +10024,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -10373,6 +10604,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -10941,6 +11183,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -11028,6 +11281,17 @@ Method Details
"a_key": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -11645,6 +11909,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -12214,6 +12489,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -12782,6 +13068,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -12869,6 +13166,17 @@ Method Details
"a_key": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -13482,6 +13790,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -14051,6 +14370,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -14619,6 +14949,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -14706,6 +15047,17 @@ Method Details
"a_key": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
diff --git a/docs/dyn/aiplatform_v1.projects.locations.evaluationMetrics.html b/docs/dyn/aiplatform_v1.projects.locations.evaluationMetrics.html
index b853265a44..70916183fb 100644
--- a/docs/dyn/aiplatform_v1.projects.locations.evaluationMetrics.html
+++ b/docs/dyn/aiplatform_v1.projects.locations.evaluationMetrics.html
@@ -111,6 +111,9 @@ Method Details
"createTime": "A String", # Output only. The time when the EvaluationMetric was created.
"description": "A String", # Optional. A description of the EvaluationMetric.
"displayName": "A String", # Required. The user-friendly display name for the EvaluationMetric.
+ "encryptionSpec": { # Represents a customer-managed encryption key specification that can be applied to a Vertex AI resource. # Optional. Customer-managed encryption key spec for this EvaluationMetric. If set, this EvaluationMetric will be secured by this key.
+ "kmsKeyName": "A String", # Required. Resource name of the Cloud KMS key used to protect the resource. The Cloud KMS key must be in the same region as the resource. It must have the format `projects/{project}/locations/{location}/keyRings/{key_ring}/cryptoKeys/{crypto_key}`.
+ },
"gcsUri": "A String", # Optional. The Google Cloud Storage URI that stores the metric specification..
"labels": { # Optional. Labels for the evaluation metric.
"a_key": "A String",
@@ -142,6 +145,23 @@ Method Details
"flipEnabled": True or False, # Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -299,6 +319,23 @@ Method Details
"flipEnabled": True or False, # Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -504,6 +541,9 @@ Method Details
"createTime": "A String", # Output only. The time when the EvaluationMetric was created.
"description": "A String", # Optional. A description of the EvaluationMetric.
"displayName": "A String", # Required. The user-friendly display name for the EvaluationMetric.
+ "encryptionSpec": { # Represents a customer-managed encryption key specification that can be applied to a Vertex AI resource. # Optional. Customer-managed encryption key spec for this EvaluationMetric. If set, this EvaluationMetric will be secured by this key.
+ "kmsKeyName": "A String", # Required. Resource name of the Cloud KMS key used to protect the resource. The Cloud KMS key must be in the same region as the resource. It must have the format `projects/{project}/locations/{location}/keyRings/{key_ring}/cryptoKeys/{crypto_key}`.
+ },
"gcsUri": "A String", # Optional. The Google Cloud Storage URI that stores the metric specification..
"labels": { # Optional. Labels for the evaluation metric.
"a_key": "A String",
@@ -535,6 +575,23 @@ Method Details
"flipEnabled": True or False, # Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -692,6 +749,23 @@ Method Details
"flipEnabled": True or False, # Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -938,6 +1012,9 @@ Method Details
"createTime": "A String", # Output only. The time when the EvaluationMetric was created.
"description": "A String", # Optional. A description of the EvaluationMetric.
"displayName": "A String", # Required. The user-friendly display name for the EvaluationMetric.
+ "encryptionSpec": { # Represents a customer-managed encryption key specification that can be applied to a Vertex AI resource. # Optional. Customer-managed encryption key spec for this EvaluationMetric. If set, this EvaluationMetric will be secured by this key.
+ "kmsKeyName": "A String", # Required. Resource name of the Cloud KMS key used to protect the resource. The Cloud KMS key must be in the same region as the resource. It must have the format `projects/{project}/locations/{location}/keyRings/{key_ring}/cryptoKeys/{crypto_key}`.
+ },
"gcsUri": "A String", # Optional. The Google Cloud Storage URI that stores the metric specification..
"labels": { # Optional. Labels for the evaluation metric.
"a_key": "A String",
@@ -969,6 +1046,23 @@ Method Details
"flipEnabled": True or False, # Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -1126,6 +1220,23 @@ Method Details
"flipEnabled": True or False, # Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -1343,6 +1454,9 @@ Method Details
"createTime": "A String", # Output only. The time when the EvaluationMetric was created.
"description": "A String", # Optional. A description of the EvaluationMetric.
"displayName": "A String", # Required. The user-friendly display name for the EvaluationMetric.
+ "encryptionSpec": { # Represents a customer-managed encryption key specification that can be applied to a Vertex AI resource. # Optional. Customer-managed encryption key spec for this EvaluationMetric. If set, this EvaluationMetric will be secured by this key.
+ "kmsKeyName": "A String", # Required. Resource name of the Cloud KMS key used to protect the resource. The Cloud KMS key must be in the same region as the resource. It must have the format `projects/{project}/locations/{location}/keyRings/{key_ring}/cryptoKeys/{crypto_key}`.
+ },
"gcsUri": "A String", # Optional. The Google Cloud Storage URI that stores the metric specification..
"labels": { # Optional. Labels for the evaluation metric.
"a_key": "A String",
@@ -1374,6 +1488,23 @@ Method Details
"flipEnabled": True or False, # Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -1531,6 +1662,23 @@ Method Details
"flipEnabled": True or False, # Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
diff --git a/docs/dyn/aiplatform_v1.projects.locations.evaluationRuns.html b/docs/dyn/aiplatform_v1.projects.locations.evaluationRuns.html
index 9f867fadb4..dbfc965f58 100644
--- a/docs/dyn/aiplatform_v1.projects.locations.evaluationRuns.html
+++ b/docs/dyn/aiplatform_v1.projects.locations.evaluationRuns.html
@@ -168,6 +168,23 @@ Method Details
"autoraterModel": "A String", # Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -347,6 +364,23 @@ Method Details
"autoraterModel": "A String", # Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -499,6 +533,23 @@ Method Details
"autoraterModel": "A String", # Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -675,6 +726,23 @@ Method Details
"flipEnabled": True or False, # Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -832,6 +900,23 @@ Method Details
"flipEnabled": True or False, # Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -1046,6 +1131,23 @@ Method Details
"autoraterModel": "A String", # Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -1192,6 +1294,23 @@ Method Details
"autoraterModel": "A String", # Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -1367,6 +1486,23 @@ Method Details
"autoraterModel": "A String", # Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -1544,6 +1680,23 @@ Method Details
"maxTurn": 42, # Maximum number of invocations allowed by the multi-turn agent scraping. This property allows us to stop a run-off conversation, where the agent and the user simulator get into a never ending loop. The initial fixed prompt is also counted as an invocation.
"modelConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # The configuration for the model.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -1923,6 +2076,23 @@ Method Details
},
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Generation config.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -2118,6 +2288,23 @@ Method Details
"autoraterModel": "A String", # Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -2297,6 +2484,23 @@ Method Details
"autoraterModel": "A String", # Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -2449,6 +2653,23 @@ Method Details
"autoraterModel": "A String", # Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -2625,6 +2846,23 @@ Method Details
"flipEnabled": True or False, # Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -2782,6 +3020,23 @@ Method Details
"flipEnabled": True or False, # Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -2996,6 +3251,23 @@ Method Details
"autoraterModel": "A String", # Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -3142,6 +3414,23 @@ Method Details
"autoraterModel": "A String", # Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -3317,6 +3606,23 @@ Method Details
"autoraterModel": "A String", # Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -3494,6 +3800,23 @@ Method Details
"maxTurn": 42, # Maximum number of invocations allowed by the multi-turn agent scraping. This property allows us to stop a run-off conversation, where the agent and the user simulator get into a never ending loop. The initial fixed prompt is also counted as an invocation.
"modelConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # The configuration for the model.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -3873,6 +4196,23 @@ Method Details
},
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Generation config.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -4110,6 +4450,23 @@ Method Details
"autoraterModel": "A String", # Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -4289,6 +4646,23 @@ Method Details
"autoraterModel": "A String", # Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -4441,6 +4815,23 @@ Method Details
"autoraterModel": "A String", # Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -4617,6 +5008,23 @@ Method Details
"flipEnabled": True or False, # Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -4774,6 +5182,23 @@ Method Details
"flipEnabled": True or False, # Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -4988,6 +5413,23 @@ Method Details
"autoraterModel": "A String", # Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -5134,6 +5576,23 @@ Method Details
"autoraterModel": "A String", # Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -5309,6 +5768,23 @@ Method Details
"autoraterModel": "A String", # Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -5486,6 +5962,23 @@ Method Details
"maxTurn": 42, # Maximum number of invocations allowed by the multi-turn agent scraping. This property allows us to stop a run-off conversation, where the agent and the user simulator get into a never ending loop. The initial fixed prompt is also counted as an invocation.
"modelConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # The configuration for the model.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -5865,6 +6358,23 @@ Method Details
},
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Generation config.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -6073,6 +6583,23 @@ Method Details
"autoraterModel": "A String", # Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -6252,6 +6779,23 @@ Method Details
"autoraterModel": "A String", # Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -6404,6 +6948,23 @@ Method Details
"autoraterModel": "A String", # Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -6580,6 +7141,23 @@ Method Details
"flipEnabled": True or False, # Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -6737,6 +7315,23 @@ Method Details
"flipEnabled": True or False, # Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -6951,6 +7546,23 @@ Method Details
"autoraterModel": "A String", # Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -7097,6 +7709,23 @@ Method Details
"autoraterModel": "A String", # Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -7272,6 +7901,23 @@ Method Details
"autoraterModel": "A String", # Optional. The fully qualified name of the publisher model or tuned autorater endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -7449,6 +8095,23 @@ Method Details
"maxTurn": 42, # Maximum number of invocations allowed by the multi-turn agent scraping. This property allows us to stop a run-off conversation, where the agent and the user simulator get into a never ending loop. The initial fixed prompt is also counted as an invocation.
"modelConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # The configuration for the model.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -7828,6 +8491,23 @@ Method Details
},
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Generation config.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
diff --git a/docs/dyn/aiplatform_v1.projects.locations.evaluationSets.html b/docs/dyn/aiplatform_v1.projects.locations.evaluationSets.html
index 9df98be642..686f48bb1c 100644
--- a/docs/dyn/aiplatform_v1.projects.locations.evaluationSets.html
+++ b/docs/dyn/aiplatform_v1.projects.locations.evaluationSets.html
@@ -353,6 +353,9 @@ Method Details
},
"createTime": "A String", # Output only. Timestamp when this item was created.
"displayName": "A String", # Required. The display name of the EvaluationSet.
+ "encryptionSpec": { # Represents a customer-managed encryption key specification that can be applied to a Vertex AI resource. # Optional. Customer-managed encryption key spec for this EvaluationSet. If set, this EvaluationSet and its sub-resources will be secured by this key.
+ "kmsKeyName": "A String", # Required. Resource name of the Cloud KMS key used to protect the resource. The Cloud KMS key must be in the same region as the resource. It must have the format `projects/{project}/locations/{location}/keyRings/{key_ring}/cryptoKeys/{crypto_key}`.
+ },
"evaluationItems": [ # Required. The EvaluationItems that are part of this dataset.
"A String",
],
@@ -609,6 +612,9 @@ Method Details
},
"createTime": "A String", # Output only. Timestamp when this item was created.
"displayName": "A String", # Required. The display name of the EvaluationSet.
+ "encryptionSpec": { # Represents a customer-managed encryption key specification that can be applied to a Vertex AI resource. # Optional. Customer-managed encryption key spec for this EvaluationSet. If set, this EvaluationSet and its sub-resources will be secured by this key.
+ "kmsKeyName": "A String", # Required. Resource name of the Cloud KMS key used to protect the resource. The Cloud KMS key must be in the same region as the resource. It must have the format `projects/{project}/locations/{location}/keyRings/{key_ring}/cryptoKeys/{crypto_key}`.
+ },
"evaluationItems": [ # Required. The EvaluationItems that are part of this dataset.
"A String",
],
@@ -907,6 +913,9 @@ Method Details
},
"createTime": "A String", # Output only. Timestamp when this item was created.
"displayName": "A String", # Required. The display name of the EvaluationSet.
+ "encryptionSpec": { # Represents a customer-managed encryption key specification that can be applied to a Vertex AI resource. # Optional. Customer-managed encryption key spec for this EvaluationSet. If set, this EvaluationSet and its sub-resources will be secured by this key.
+ "kmsKeyName": "A String", # Required. Resource name of the Cloud KMS key used to protect the resource. The Cloud KMS key must be in the same region as the resource. It must have the format `projects/{project}/locations/{location}/keyRings/{key_ring}/cryptoKeys/{crypto_key}`.
+ },
"evaluationItems": [ # Required. The EvaluationItems that are part of this dataset.
"A String",
],
@@ -1196,6 +1205,9 @@ Method Details
},
"createTime": "A String", # Output only. Timestamp when this item was created.
"displayName": "A String", # Required. The display name of the EvaluationSet.
+ "encryptionSpec": { # Represents a customer-managed encryption key specification that can be applied to a Vertex AI resource. # Optional. Customer-managed encryption key spec for this EvaluationSet. If set, this EvaluationSet and its sub-resources will be secured by this key.
+ "kmsKeyName": "A String", # Required. Resource name of the Cloud KMS key used to protect the resource. The Cloud KMS key must be in the same region as the resource. It must have the format `projects/{project}/locations/{location}/keyRings/{key_ring}/cryptoKeys/{crypto_key}`.
+ },
"evaluationItems": [ # Required. The EvaluationItems that are part of this dataset.
"A String",
],
@@ -1511,6 +1523,9 @@ Method Details
},
"createTime": "A String", # Output only. Timestamp when this item was created.
"displayName": "A String", # Required. The display name of the EvaluationSet.
+ "encryptionSpec": { # Represents a customer-managed encryption key specification that can be applied to a Vertex AI resource. # Optional. Customer-managed encryption key spec for this EvaluationSet. If set, this EvaluationSet and its sub-resources will be secured by this key.
+ "kmsKeyName": "A String", # Required. Resource name of the Cloud KMS key used to protect the resource. The Cloud KMS key must be in the same region as the resource. It must have the format `projects/{project}/locations/{location}/keyRings/{key_ring}/cryptoKeys/{crypto_key}`.
+ },
"evaluationItems": [ # Required. The EvaluationItems that are part of this dataset.
"A String",
],
@@ -1786,6 +1801,9 @@ Method Details
},
"createTime": "A String", # Output only. Timestamp when this item was created.
"displayName": "A String", # Required. The display name of the EvaluationSet.
+ "encryptionSpec": { # Represents a customer-managed encryption key specification that can be applied to a Vertex AI resource. # Optional. Customer-managed encryption key spec for this EvaluationSet. If set, this EvaluationSet and its sub-resources will be secured by this key.
+ "kmsKeyName": "A String", # Required. Resource name of the Cloud KMS key used to protect the resource. The Cloud KMS key must be in the same region as the resource. It must have the format `projects/{project}/locations/{location}/keyRings/{key_ring}/cryptoKeys/{crypto_key}`.
+ },
"evaluationItems": [ # Required. The EvaluationItems that are part of this dataset.
"A String",
],
@@ -2043,6 +2061,9 @@ Method Details
},
"createTime": "A String", # Output only. Timestamp when this item was created.
"displayName": "A String", # Required. The display name of the EvaluationSet.
+ "encryptionSpec": { # Represents a customer-managed encryption key specification that can be applied to a Vertex AI resource. # Optional. Customer-managed encryption key spec for this EvaluationSet. If set, this EvaluationSet and its sub-resources will be secured by this key.
+ "kmsKeyName": "A String", # Required. Resource name of the Cloud KMS key used to protect the resource. The Cloud KMS key must be in the same region as the resource. It must have the format `projects/{project}/locations/{location}/keyRings/{key_ring}/cryptoKeys/{crypto_key}`.
+ },
"evaluationItems": [ # Required. The EvaluationItems that are part of this dataset.
"A String",
],
diff --git a/docs/dyn/aiplatform_v1.projects.locations.html b/docs/dyn/aiplatform_v1.projects.locations.html
index f410629cb6..0d8de63213 100644
--- a/docs/dyn/aiplatform_v1.projects.locations.html
+++ b/docs/dyn/aiplatform_v1.projects.locations.html
@@ -942,6 +942,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -1061,6 +1072,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -1171,6 +1193,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Input content to corroborate, only text format is supported for now.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -1536,6 +1569,23 @@ Method Details
"flipEnabled": True or False, # Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -1714,6 +1764,23 @@ Method Details
"flipEnabled": True or False, # Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -1871,6 +1938,23 @@ Method Details
"flipEnabled": True or False, # Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -2111,6 +2195,23 @@ Method Details
"flipEnabled": True or False, # Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -2329,6 +2430,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -2648,6 +2760,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -2963,6 +3086,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -3043,6 +3177,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -3579,6 +3724,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -3669,6 +3825,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -3752,6 +3919,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -3833,6 +4011,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -3914,6 +4103,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -4038,6 +4238,23 @@ Method Details
"flipEnabled": True or False, # Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -4195,6 +4412,23 @@ Method Details
"flipEnabled": True or False, # Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -4414,6 +4648,23 @@ Method Details
"flipEnabled": True or False, # Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -4571,6 +4822,23 @@ Method Details
"flipEnabled": True or False, # Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -4781,6 +5049,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -4903,6 +5182,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -5541,6 +5831,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -5853,6 +6154,17 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -5939,6 +6251,23 @@ Method Details
"flipEnabled": True or False, # Optional. Default is true. Whether to flip the candidate and baseline responses. This is only applicable to the pairwise metric. If enabled, also provide PairwiseMetricSpec.candidate_response_field_name and PairwiseMetricSpec.baseline_response_field_name. When rendering PairwiseMetricSpec.metric_prompt_template, the candidate and baseline fields will be flipped for half of the samples to reduce bias.
"generationConfig": { # Configuration for content generation. This message contains all the parameters that control how the model generates content. It allows you to influence the randomness, length, and structure of the output. # Optional. Configuration options for model generation and outputs.
"audioTimestamp": True or False, # Optional. If enabled, audio timestamps will be included in the request to the model. This can be useful for synchronizing audio with other modalities in the response.
+ "audioTranscriptionConfig": { # Configuration for speech recognition (transcription). # Optional. Config for audio transcription (speech recognition).
+ "adaptationPhrases": [ # Optional. A list of phrases to bias the ASR model towards.
+ "A String",
+ ],
+ "customVocabulary": [ # Optional. A list of custom vocabulary phrases to bias the speech recognition model toward recognizing specific terms.
+ "A String",
+ ],
+ "diarization": True or False, # Optional. Configures speaker diarization.
+ "languageAuto": { # Indicates the language of the audio should be automatically detected. # Optional. The model will detect the language automatically.
+ },
+ "languageHints": { # Provides hints to the model about possible languages present in the audio. # Optional. Specifies one or more languages in the audio.
+ "languageCodes": [ # Required. BCP-47 language codes. At least one must be specified.
+ "A String",
+ ],
+ },
+ "wordTimestamp": True or False, # Optional. Configures word-level timestamp generation.
+ },
"candidateCount": 42, # Optional. The number of candidate responses to generate. A higher `candidate_count` can provide more options to choose from, but it also consumes more resources. This can be useful for generating a variety of responses and selecting the best one.
"enableAffectiveDialog": True or False, # Optional. If enabled, the model will detect emotions and adapt its responses accordingly. For example, if the model detects that the user is frustrated, it may provide a more empathetic response.
"frequencyPenalty": 3.14, # Optional. Penalizes tokens based on their frequency in the generated text. A positive value helps to reduce the repetition of words and phrases. Valid values can range from [-2.0, 2.0].
@@ -6643,6 +6972,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -7212,6 +7552,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -7780,6 +8131,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response).
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -7867,6 +8229,17 @@ Method Details
"a_key": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -8018,6 +8391,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The actual content or value for this field. This can be text, images, or other types of data.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -8122,6 +8506,17 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The actual content or value for this field. This can be text, images, or other types of data.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
"codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
@@ -8559,6 +8954,9 @@ Method Details
"createTime": "A String", # Output only. Timestamp when this SemanticGovernancePolicyEngine was created.
"gatewayConfigs": { # Optional. Configurations for gateways. The keys are user-defined names for each gateway. At most 5 gateway configurations are allowed.
"a_key": { # Configuration for a single gateway.
+ "allowedProjects": [ # Optional. Additional consumer projects permitted to attach their own PSC endpoint to this gateway's ServiceAttachment. This is the "decoupled" mode, where the customer creates the PSC endpoint in a project other than this gateway's `network` project. Each listed project is VPC-SC enforced: it must be within the caller's service perimeter. The owning SemanticGovernancePolicyEngine's own project is always permitted implicitly and need not be listed. Format: project ID or number.
+ "A String",
+ ],
"dnsRecord": "A String", # Output only. The fully qualified record name of the created A-record in Cloud DNS.
"dnsZoneName": "A String", # Optional. FQDN of the private DNS zone to create DNS record set for PSC endpoint.
"ipAddress": "A String", # Output only. The private IP address of the PSC endpoint.
@@ -8771,6 +9169,9 @@ Method Details
"createTime": "A String", # Output only. Timestamp when this SemanticGovernancePolicyEngine was created.
"gatewayConfigs": { # Optional. Configurations for gateways. The keys are user-defined names for each gateway. At most 5 gateway configurations are allowed.
"a_key": { # Configuration for a single gateway.
+ "allowedProjects": [ # Optional. Additional consumer projects permitted to attach their own PSC endpoint to this gateway's ServiceAttachment. This is the "decoupled" mode, where the customer creates the PSC endpoint in a project other than this gateway's `network` project. Each listed project is VPC-SC enforced: it must be within the caller's service perimeter. The owning SemanticGovernancePolicyEngine's own project is always permitted implicitly and need not be listed. Format: project ID or number.
+ "A String",
+ ],
"dnsRecord": "A String", # Output only. The fully qualified record name of the created A-record in Cloud DNS.
"dnsZoneName": "A String", # Optional. FQDN of the private DNS zone to create DNS record set for PSC endpoint.
"ipAddress": "A String", # Output only. The private IP address of the PSC endpoint.
diff --git a/docs/dyn/aiplatform_v1.projects.locations.indexEndpoints.html b/docs/dyn/aiplatform_v1.projects.locations.indexEndpoints.html
index e2b908bab3..f299ee9972 100644
--- a/docs/dyn/aiplatform_v1.projects.locations.indexEndpoints.html
+++ b/docs/dyn/aiplatform_v1.projects.locations.indexEndpoints.html
@@ -104,7 +104,7 @@ Instance Methods
list_next()
Retrieves the next page of results.
- mutateDeployedIndex(indexEndpoint, body=None, x__xgafv=None)
+ mutateDeployedIndex(indexEndpoint, body=None, updateMask=None, x__xgafv=None)
Update an existing DeployedIndex under an IndexEndpoint.
patch(name, body=None, updateMask=None, x__xgafv=None)
@@ -837,7 +837,7 @@ Method Details
-
mutateDeployedIndex(indexEndpoint, body=None, x__xgafv=None)
+
mutateDeployedIndex(indexEndpoint, body=None, updateMask=None, x__xgafv=None)
Update an existing DeployedIndex under an IndexEndpoint.
Args:
@@ -921,6 +921,7 @@ Method Details
],
}
+ updateMask: string, Optional. The update mask applies to the resource. The supported paths are `automatic_resources`, `dedicated_resources`, `enable_access_logging` and `deployed_index_auth_config`. When omitted, the service will perform a full update of all fields. See google.protobuf.FieldMask.
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
diff --git a/docs/dyn/aiplatform_v1.projects.locations.memoryBanks.html b/docs/dyn/aiplatform_v1.projects.locations.memoryBanks.html
index 869428ee88..af6a5b8a84 100644
--- a/docs/dyn/aiplatform_v1.projects.locations.memoryBanks.html
+++ b/docs/dyn/aiplatform_v1.projects.locations.memoryBanks.html
@@ -87,10 +87,175 @@ Instance Methods
close()
Close httplib2 connections.
+
+ ingestEvents(parent, body=None, x__xgafv=None)
+Ingests events for a Memory Bank.
Method Details
close()
Close httplib2 connections.
+
+
ingestEvents(parent, body=None, x__xgafv=None)
+
Ingests events for a Memory Bank.
+
+Args:
+ parent: string, Required. The resource name of the ReasoningEngine to ingest events to. Format: `projects/{project}/locations/{location}/reasoningEngines/{reasoning_engine}` (required)
+ body: object, The request body.
+ The object takes the form of:
+
+{ # Request message for MemoryBankService.IngestEvents.
+ "directContentsSource": { # Ingest events directly from the request. # Ingest events directly from the request.
+ "events": [ # Required. The events to ingest.
+ { # A single event to ingest.
+ "content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event.
+ "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
+ { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+ "audioTranscription": { # The transcription of an audio part. For multi-speaker audio, each speaker segment is a separate Part with its own AudioTranscription carrying the speaker_label. # Optional. Audio (input or output) transcription. This is only set when this Part contains audio data.
+ "speakerLabel": "A String", # Optional. A label identifying the speaker of this audio segment (e.g. "spk_1", "spk_2"). Present when diarization is set.
+ "text": "A String", # Required. The transcription text of this audio segment.
+ "words": [ # Optional. Detailed word-level transcriptions and timing details. Present when word_timestamp is set.
+ { # Information about a single recognized word.
+ "endOffset": "A String", # Optional. End offset in time of the word relative to the start of the audio.
+ "startOffset": "A String", # Optional. Start offset in time of the word relative to the start of the audio.
+ "word": "A String", # Required. Transcript of the word.
+ },
+ ],
+ },
+ "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
+ "outcome": "A String", # Required. Outcome of the code execution.
+ "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
+ },
+ "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed.
+ "code": "A String", # Required. The code to be executed.
+ "language": "A String", # Required. Programming language of the `code`.
+ },
+ "fileData": { # URI-based data. A FileData message contains a URI pointing to data of a specific media type. It is used to represent images, audio, and video stored in Google Cloud Storage. # Optional. The URI-based data of the part. This can be used to include files from Google Cloud Storage.
+ "displayName": "A String", # Optional. The display name of the file. Used to provide a label or filename to distinguish files. This field is only returned in `PromptMessage` for prompt management. It is used in the Gemini calls only when server side tools (`code_execution`, `google_search`, and `url_context`) are enabled.
+ "fileUri": "A String", # Required. The URI of the file in Google Cloud Storage.
+ "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
+ },
+ "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
+ "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details.
+ "a_key": "", # Properties of the object.
+ },
+ "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name.
+ "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally.
+ { # Partial argument value of the function call.
+ "boolValue": True or False, # Optional. Represents a boolean value.
+ "jsonPath": "A String", # Required. A JSON Path (RFC 9535) to the argument being streamed. https://datatracker.ietf.org/doc/html/rfc9535. e.g. "$.foo.bar[0].data".
+ "nullValue": "A String", # Optional. Represents a null value.
+ "numberValue": 3.14, # Optional. Represents a double value.
+ "stringValue": "A String", # Optional. Represents a string value.
+ "willContinue": True or False, # Optional. Whether this is not the last part of the same json_path. If true, another PartialArg message for the current json_path is expected to follow.
+ },
+ ],
+ "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow.
+ },
+ "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
+ "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name.
+ "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types.
+ { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes.
+ "fileData": { # URI based data for function response. # URI based data.
+ "displayName": "A String", # Optional. Display name of the file data. Used to provide a label or filename to distinguish file datas. This field is only returned in PromptMessage for prompt management. It is currently used in the Gemini GenerateContent calls only when server side tools (code_execution, google_search, and url_context) are enabled.
+ "fileUri": "A String", # Required. URI.
+ "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
+ },
+ "inlineData": { # Raw media bytes for function response. Text should not be sent as raw bytes, use the 'text' field. # Inline media bytes.
+ "data": "A String", # Required. Raw bytes.
+ "displayName": "A String", # Optional. Display name of the blob. Used to provide a label or filename to distinguish blobs. This field is only returned in PromptMessage for prompt management. It is currently used in the Gemini GenerateContent calls only when server side tools (code_execution, google_search, and url_context) are enabled.
+ "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
+ },
+ },
+ ],
+ "response": { # Required. The function response in JSON object format. Use "output" key to specify function output and "error" key to specify error details (if any). If "output" and "error" keys are not specified, then whole "response" is treated as function output.
+ "a_key": "", # Properties of the object.
+ },
+ "scheduling": "A String", # Optional. Specifies how the response should be scheduled in the conversation. Only applicable to NON_BLOCKING function calls, is ignored otherwise. Defaults to WHEN_IDLE.
+ },
+ "inlineData": { # A content blob. A Blob contains data of a specific media type. It is used to represent images, audio, and video. # Optional. The inline data content of the part. This can be used to include images, audio, or video in a request.
+ "data": "A String", # Required. The raw bytes of the data.
+ "displayName": "A String", # Optional. The display name of the blob. Used to provide a label or filename to distinguish blobs. This field is only returned in `PromptMessage` for prompt management. It is used in the Gemini calls only when server-side tools (`code_execution`, `google_search`, and `url_context`) are enabled.
+ "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
+ },
+ "mediaResolution": { # per part media resolution. Media resolution for the input media. # per part media resolution. Media resolution for the input media.
+ "level": "A String", # The tokenization quality used for given media.
+ },
+ "text": "A String", # Optional. The text content of the part. When sent from the VSCode Gemini Code Assist extension, references to @mentioned items will be converted to markdown boldface text. For example `@my-repo` will be converted to and sent as `**my-repo**` by the IDE agent.
+ "thought": True or False, # Optional. Indicates whether the `part` represents the model's thought process or reasoning.
+ "thoughtSignature": "A String", # Optional. An opaque signature for the thought so it can be reused in subsequent requests.
+ "videoMetadata": { # Provides metadata for a video, including the start and end offsets for clipping and the frame rate. # Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
+ "endOffset": "A String", # Optional. The end offset of the video.
+ "fps": 3.14, # Optional. The frame rate of the video sent to the model. If not specified, the default value is 1.0. The valid range is (0.0, 24.0].
+ "startOffset": "A String", # Optional. The start offset of the video.
+ },
+ },
+ ],
+ "role": "A String", # Optional. The producer of the content. Must be either 'user' or 'model'. If not set, the service will default to 'user'.
+ },
+ "eventId": "A String", # Optional. A unique identifier for the event. If an event with the same event_id is ingested multiple times, it will be de-duplicated.
+ "eventTime": "A String", # Optional. The time at which the event occurred. If provided, this timestamp will be used for ordering events within a stream. If not provided, the server-side ingestion time will be used.
+ },
+ ],
+ },
+ "disableMemoryRevisions": True or False, # Optional. If true, no revisions will be created for this request.
+ "forceFlush": True or False, # Optional. Forces a flush of all pending events in the stream and triggers memory generation immediately bypassing any conditions configured in the `generation_trigger_config`.
+ "generationTriggerConfig": { # Represents configuration for triggering generation. # Optional. Configuration for triggering memory generation from this ingestion. If not set, then the stream will be force flushed immediately.
+ "generationRule": { # Represents the active rule that determines when to flush the buffer. # Optional. Represents the active rule that determines when to flush the buffer. If not set, then the stream will be force flushed immediately.
+ "eventCount": 42, # Optional. Specifies to trigger generation when the event count reaches this limit.
+ "fixedInterval": "A String", # Optional. Specifies to trigger generation at a fixed interval. The duration must have a minute-level granularity.
+ "idleDuration": "A String", # Optional. Specifies to trigger generation if the stream is inactive for the specified duration after the most recent event. The duration must have a minute-level granularity.
+ "overlapEventCount": 42, # Optional. Re-include the last N already-processed events in the next window.
+ },
+ },
+ "metadata": { # Optional. User-provided metadata for the generated memories. This is not generated by Memory Bank.
+ "a_key": { # Memory metadata.
+ "boolValue": True or False, # Represents a boolean value.
+ "doubleValue": 3.14, # Represents a double value.
+ "stringValue": "A String", # Represents a string value.
+ "timestampValue": "A String", # Represents a timestamp value. When filtering on timestamp values, only the seconds field will be compared.
+ },
+ },
+ "metadataMergeStrategy": "A String", # Optional. The strategy to use when applying metadata to existing memories.
+ "revisionExpireTime": "A String", # Optional. Timestamp of when the revision is considered expired. If not set, the memory revision will be kept until manually deleted.
+ "revisionLabels": { # Optional. Labels to be applied to the generated memory revisions. For example, you can use this to label a revision with its data source.
+ "a_key": "A String",
+ },
+ "revisionTtl": "A String", # Optional. The TTL for the revision. The expiration time is computed: now + TTL.
+ "scope": { # Required. The scope of the memories that should be generated from the stream. Memories will be consolidated across memories with the same scope. Scope values cannot contain the wildcard character '*'.
+ "a_key": "A String",
+ },
+ "streamId": "A String", # Optional. The ID of the stream to ingest events into. If not provided, a new one will be created.
+}
+
+ x__xgafv: string, V1 error format.
+ Allowed values
+ 1 - v1 error format
+ 2 - v2 error format
+
+Returns:
+ An object of the form:
+
+ { # This resource represents a long-running operation that is the result of a network API call.
+ "done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
+ "error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
+ "code": 42, # The status code, which should be an enum value of google.rpc.Code.
+ "details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
+ {
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+ ],
+ "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
+ },
+ "metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+ "name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
+ "response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+}
+
+