Migrating from RetrievalQA

https://python.langchain.com/v0.2/docs/versions/migrating_chains/retrieval_qa/

LCELへ移行

For both versions, we'll need to load the data with the WebBaseLoader document loader, split it with RecursiveCharacterTextSplitter, and add it to an in-memory FAISS vector store.

プロンプト

https://smith.langchain.com/hub/rlm/rag-prompt

https://smith.langchain.com/hub/langchain-ai/retrieval-qa-chat

2つのヘルパー

the higher-level create_retrieval_chain and create_stuff_documents_chain helper method

inputを入れると、answerだけでなくcontextも含んで返ってくるようになる。どうやっている？（実装見たい）

https://api.python.langchain.com/en/latest/chains/langchain.chains.retrieval_qa.base.RetrievalQA.html