langchain/templates/rag-aws-bedrock/README.md

RAG AWS Bedrock

AWS Bedrock is a managed serve that offers a set of foundation models.

Here we will use Anthropic Claude for text generation and Amazon Titan for text embedding.

We will use Pinecode as our vectorstore.

(See this notebook for additional context on the RAG pipeline.)

(See this notebook for additional context on setup.)

Pinecone

This connects to a hosted Pinecone vectorstore.

Be sure that you have set a few env variables in chain.py:

• PINECONE_API_KEY
• PINECONE_ENV
• index_name

LLM and Embeddings

Be sure to set AWS enviorment variables:

• AWS_DEFAULT_REGION
• AWS_PROFILE
• BEDROCK_ASSUME_ROLE