AmazonKnowledgeBasesRetriever

Setup:

Install langchain-aws:

.. code-block:: bash

pip install -U langchain-aws

Key init args:

knowledge_base_id: Knowledge Base ID. region_name: The aws region e.g., us-west-2. Fallback to AWS_DEFAULT_REGION env variable or region specified in ~/.aws/config. credentials_profile_name: The name of the profile in the ~/.aws/credentials or ~/.aws/config files, which has either access keys or role information specified. If not specified, the default credential profile or, if on an EC2 instance, credentials from IMDS will be used. client: boto3 client for bedrock agent runtime. retrieval_config: Configuration for retrieval.

Instantiate:

.. code-block:: python

from langchain_community.retrievers import AmazonKnowledgeBasesRetriever

retriever = AmazonKnowledgeBasesRetriever( knowledge_base_id="", retrieval_config={ "vectorSearchConfiguration": { "numberOfResults": 4 } }, )

Usage:

.. code-block:: python

query = "..."

retriever.invoke(query)

Use within a chain:

.. code-block:: python

from langchain_aws import ChatBedrockConverse from langchain_core.output_parsers import StrOutputParser from langchain_core.prompts import ChatPromptTemplate from langchain_core.runnables import RunnablePassthrough from langchain_openai import ChatOpenAI

prompt = ChatPromptTemplate.from_template( """Answer the question based only on the context provided.

Context: {context}

Question: {question}""" )

llm = ChatBedrockConverse( model_id="anthropic.claude-3-5-sonnet-20240620-v1:0" )

def format_docs(docs): return "\n\n".join(doc.page_content for doc in docs)

chain = ( {"context": retriever | format_docs, "question": RunnablePassthrough()} | prompt | llm | StrOutputParser() )

chain.invoke("...")