Allowing different types of search in the vector DB chain Previously, the VectorDB QA chain only used similarity search to fetch documents You can now configure this to use `mmr`: max marginal relevance https://
github.com/hwchase17/lang
chain/blob/b9045f7e0df357d608700e91dc3039433f652d61/langchain/chains/vector_db_qa/base.py#L44
…

→ View original post on X — @langchain,