langchain.chains.history_aware_retriever.create_history_aware_retriever¶

langchain.chains.history_aware_retriever.create_history_aware_retriever(llm: Runnable[Union[PromptValue, str, Sequence[Union[BaseMessage, Tuple[str, str], str, Dict[str, Any]]]], Union[BaseMessage, str]], retriever: Runnable[str, List[Document]], prompt: BasePromptTemplate) → Runnable[Any, List[Document]][source]¶

Create a chain that takes conversation history and returns documents.

If there is no chat_history, then the input is just passed directly to the retriever. If there is chat_history, then the prompt and LLM will be used to generate a search query. That search query is then passed to the retriever.

Parameters

  • llm (Runnable[Union[PromptValue, str, Sequence[Union[BaseMessage, Tuple[str, str], str, Dict[str, Any]]]], Union[BaseMessage, str]]) – Language model to use for generating a search term given chat history

  • retriever (Runnable[str, List[Document]]) – RetrieverLike object that takes a string as input and outputs a list of Documents.

  • prompt (BasePromptTemplate) – The prompt used to generate the search query for the retriever.

Returns

An LCEL Runnable. The runnable input must take in input, and if there is chat history should take it in the form of chat_history. The Runnable output is a list of Documents

Return type

Runnable[Any, List[Document]]

Example

# pip install -U langchain langchain-community

from langchain_community.chat_models import ChatOpenAI
from langchain.chains import create_history_aware_retriever
from langchain import hub

rephrase_prompt = hub.pull("langchain-ai/chat-langchain-rephrase")
llm = ChatOpenAI()
retriever = ...
chat_retriever_chain = create_history_aware_retriever(
    llm, retriever, rephrase_prompt
)

chain.invoke({"input": "...", "chat_history": })