内容简介

• 尝试用 FAISS 或 DocArrayInMemorySearch 将数据向量化后检索
• astream_events 的效果为 |H|arrison| worked| at| Kens|ho|.||

安装依赖

# 之前的依赖即可
pip install --upgrade --quiet  langchain-core langchain-community langchain-openai
# Win或Linux用户可以试试 FAISS
pip install faiss
# mac用户应该为
pip install faiss-cpu

编写代码

我没有用 FAISS，这里替换为：DocArrayInMemorySearch

# MacBookProM1 FAISS没有包，可能是 faiss-cpu
# from langchain_community.vectorstores import FAISS
from langchain_community.vectorstores import DocArrayInMemorySearch
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough
from langchain_core.prompts import ChatPromptTemplate
from langchain_openai import OpenAIEmbeddings
from langchain_openai.chat_models import ChatOpenAI


async def main():
    template = """Answer the question based only on the following context:
    {context}

    Question: {question}
    """
    prompt = ChatPromptTemplate.from_template(template)
    vectorstore = DocArrayInMemorySearch.from_texts(
        ["harrison worked at kensho"], embedding=OpenAIEmbeddings()
    )
    retriever = vectorstore.as_retriever()
    model = ChatOpenAI(
        model="gpt-3.5-turbo",
    )
    retrieval_chain = (
            {
                "context": retriever.with_config(run_name="Docs"),
                "question": RunnablePassthrough(),
            }
            | prompt
            | model.with_config(run_name="my_llm")
            | StrOutputParser()
    )
    async for event in retrieval_chain.astream_events(
            "where did harrison work?", version="v1", include_names=["Docs", "my_llm"]
    ):
        kind = event["event"]
        if kind == "on_chat_model_stream":
            print(event["data"]["chunk"].content, end="|")
        elif kind in {"on_chat_model_start"}:
            print()
            print("Streaming LLM:")
        elif kind in {"on_chat_model_end"}:
            print()
            print("Done streaming LLM.")
        elif kind == "on_retriever_end":
            print("--")
            print("Retrieved the following documents:")
            print(event["data"]["output"]["documents"])
        elif kind == "on_tool_end":
            print(f"Ended tool: {event['name']}")
        else:
            pass

if __name__ == "__main__":
    import asyncio
    asyncio.run(main())

运行结果

➜ python3 test03.py
/Users/wuzikang/Desktop/py/langchain_test/own_learn/env/lib/python3.12/site-packages/pydantic/_migration.py:283: UserWarning: `pydantic.error_wrappers:ValidationError` has been moved to `pydantic:ValidationError`.
  warnings.warn(f'`{import_path}` has been moved to `{new_location}`.')
/Users/wuzikang/Desktop/py/langchain_test/own_learn/env/lib/python3.12/site-packages/langchain_core/_api/beta_decorator.py:86: LangChainBetaWarning: This API is in beta and may change in the future.
  warn_beta(
--
Retrieved the following documents:
[Document(page_content='harrison worked at kensho')]

Streaming LLM:
|H|arrison| worked| at| Kens|ho|.||
Done streaming LLM.