Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
99 changes: 99 additions & 0 deletions .generator/schemas/v2/openapi.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -52338,6 +52338,10 @@ components:
LLMObsCustomEvalConfigBedrockOptions:
description: AWS Bedrock-specific options for LLM provider configuration.
properties:
inference_profile:
description: Bedrock inference profile identifier, such as an application inference profile ARN.
example: "arn:aws:bedrock:us-east-1:123456789012:application-inference-profile/abc123"
type: string
region:
description: AWS region for Bedrock.
example: "us-east-1"
Expand Down Expand Up @@ -52428,6 +52432,11 @@ components:
properties:
assessment_criteria:
$ref: "#/components/schemas/LLMObsCustomEvalConfigAssessmentCriteria"
context_query:
description: Query used to extract additional context for the evaluation.
example: "@input.context"
nullable: true
type: string
inference_params:
$ref: "#/components/schemas/LLMObsCustomEvalConfigInferenceParams"
last_used_library_prompt_template_name:
Expand All @@ -52452,6 +52461,15 @@ components:
items:
$ref: "#/components/schemas/LLMObsCustomEvalConfigPromptMessage"
type: array
target_query:
description: Query used to extract the target value to evaluate.
example: "@output.value"
nullable: true
type: string
user_specified_json_post_processing_function:
description: User-provided function applied to post-process the JSON output of the LLM judge.
nullable: true
type: string
required:
- inference_params
type: object
Expand All @@ -52473,16 +52491,29 @@ components:
vertex_ai:
$ref: "#/components/schemas/LLMObsCustomEvalConfigVertexAIOptions"
type: object
LLMObsCustomEvalConfigListResponse:
description: Response containing a list of custom LLM Observability evaluator configurations.
properties:
data:
description: List of custom evaluator configuration data objects.
items:
$ref: "#/components/schemas/LLMObsCustomEvalConfigData"
type: array
required:
- data
type: object
LLMObsCustomEvalConfigParsingType:
description: Output parsing type for a custom LLM judge evaluator.
enum:
- structured_output
- json
- keyword_search
example: "structured_output"
type: string
x-enum-varnames:
- STRUCTURED_OUTPUT
- JSON
- KEYWORD_SEARCH
LLMObsCustomEvalConfigPromptContent:
description: A content block within a prompt message.
properties:
Expand Down Expand Up @@ -52589,6 +52620,13 @@ components:
eval_scope:
$ref: "#/components/schemas/LLMObsCustomEvalConfigEvalScope"
nullable: true
experiment_project_ids:
description: Experiment project IDs this evaluator is scoped to.
items:
description: An experiment project ID.
format: uuid
type: string
type: array
filter:
description: Filter expression to select which spans to evaluate.
example: "@service:my-service"
Expand Down Expand Up @@ -116425,6 +116463,67 @@ paths:
x-unstable: |-
This endpoint is in Preview and may introduce breaking changes.
If you have any feedback, contact [Datadog support](https://docs.datadoghq.com/help/).
/api/unstable/llm-obs/config/evaluators/custom:
get:
description: List all custom LLM Observability evaluator configurations for the organization.
operationId: ListLLMObsCustomEvalConfigs
responses:
"200":
content:
application/json:
examples:
default:
value:
data:
- attributes:
category: "Custom"
created_at: "2024-01-15T10:30:00Z"
created_by:
email: "user@example.com"
eval_name: "my-custom-evaluator"
last_updated_by:
email: "user@example.com"
llm_judge_config:
inference_params:
max_tokens: 1024
temperature: 0.7
parsing_type: "structured_output"
llm_provider:
integration_provider: "openai"
model_name: "gpt-4o"
target:
application_name: "my-llm-app"
enabled: true
sampling_percentage: 50.0
updated_at: "2024-01-15T10:30:00Z"
id: "my-custom-evaluator"
type: "evaluator_config"
schema:
$ref: "#/components/schemas/LLMObsCustomEvalConfigListResponse"
description: OK
"401":
content:
application/json:
schema:
$ref: "#/components/schemas/JSONAPIErrorResponse"
description: Unauthorized
"403":
content:
application/json:
schema:
$ref: "#/components/schemas/JSONAPIErrorResponse"
description: Forbidden
"429":
$ref: "#/components/responses/TooManyRequestsResponse"
security:
- apiKeyAuth: []
appKeyAuth: []
summary: List custom evaluator configurations
tags:
- LLM Observability
x-unstable: |-
**Note**: This endpoint is in preview and is subject to change.
If you have any feedback, contact [Datadog support](https://docs.datadoghq.com/help/).
/api/unstable/llm-obs/config/evaluators/custom/{eval_name}:
delete:
description: Delete a custom LLM Observability evaluator configuration by its name.
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,8 @@
# List custom evaluator configurations returns "OK" response

require "datadog_api_client"
DatadogAPIClient.configure do |config|
config.unstable_operations["v2.list_llm_obs_custom_eval_configs".to_sym] = true
end
api_instance = DatadogAPIClient::V2::LLMObservabilityAPI.new
p api_instance.list_llm_obs_custom_eval_configs()
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,7 @@
],
pass_when: true,
}),
context_query: "@input.context",
inference_params: DatadogAPIClient::V2::LLMObsCustomEvalConfigInferenceParams.new({
frequency_penalty: 0.0,
max_tokens: 1024,
Expand Down Expand Up @@ -59,9 +60,12 @@
role: "user",
}),
],
target_query: "@output.value",
user_specified_json_post_processing_function: nil,
}),
llm_provider: DatadogAPIClient::V2::LLMObsCustomEvalConfigLLMProvider.new({
bedrock: DatadogAPIClient::V2::LLMObsCustomEvalConfigBedrockOptions.new({
inference_profile: "arn:aws:bedrock:us-east-1:123456789012:application-inference-profile/abc123",
region: "us-east-1",
}),
integration_account_id: "my-account-id",
Expand All @@ -76,6 +80,7 @@
application_name: "my-llm-app",
enabled: true,
eval_scope: DatadogAPIClient::V2::LLMObsCustomEvalConfigEvalScope::SPAN,
experiment_project_ids: [],
filter: "@service:my-service",
root_spans_only: true,
sampling_percentage: 50.0,
Expand Down
Loading
Loading