pinec

An end-to-end Retrieval-Augmented Generation (RAG) system built with Haystack for pipeline orchestration, Pinecone as the vector database, Sentence-Transformers for embeddings, and Mistral-7B (served via the Hugging Face Inference API) for answer generation — all exposed through a FastAPI web application.

RAG powered AI assistant that answers questions about LangChain documentation using Gemini, Pinecone and LangChain