langchain/templates/rag-aws-bedrock

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 FAISS as our vectorstore.

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

Code here uses the boto3 library to connect with the Bedrock service. See this page for setting up and configuring boto3 to work with an AWS account.

FAISS

You need to install the faiss-cpu package to work with the FAISS vector store.

pip install faiss-cpu

LLM and Embeddings

The code assumes that you are working with the default AWS profile and us-east-1 region. If not, specify these environment variables to reflect the correct region and AWS profile.

• AWS_DEFAULT_REGION
• AWS_PROFILE

Environment variables

You need (if not using default) to define the following environment variables

AWS_DEFAULT_REGION=<YOUR_AWS_DEFAULT_REGION>
AWS_PROFILE=<YOUR_AWS_PROFILE>