从ConversationalRetrievalChain迁移到LCEL：更清晰、更强大的实现

nseejrukjhad

于 2024-10-04 05:57:22 发布

阅读量114

点赞数 2

文章标签： python linux 人工智能

本文链接：https://blog.csdn.net/nseejrukjhad/article/details/142698836

版权

引言

ConversationalRetrievalChain是一种结合检索增强生成和聊天历史的全能型方法，允许用户与文档进行对话。然而，迁移到LCEL（LangChain Enhanced Library）实现有许多优点，包括更清晰的内部实现、更易于返回源文档以及对流式和异步操作的支持。本文将详细讨论这些优点，并提供相应的代码示例。

主要内容

1. ConversationalRetrievalChain的缺点

ConversationalRetrievalChain隐藏了整个问题重构步骤，这一步将初始查询与聊天历史进行反向引用。这意味着该类包含两套可配置的提示、LLM等。此外，这种实现方式使得返回源文档更加困难。

2. LCEL的优势

LCEL带来了如下几个显著的优势：

更清晰的内部实现： LCEL将问题重构步骤明确化，使得调试和配置更为方便。
更易于返回源文档： LCEL支持直接返回相关文档，提供更多的上下文信息。
支持流式和异步操作： LCEL设计上更加现代，支持运行流式和异步操作，提升了处理效率。

3. 实现细节

安装必要的库

%pip install --upgrade --quiet langchain-community langchain langchain-openai faiss-cpu

载入文档和向量存储

import os
from getpass import getpass

os.environ["OPENAI_API_KEY"] = getpass()

# 加载文档
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.document_loaders import WebBaseLoader
from langchain_community.vectorstores import FAISS
from langchain_openai.chat_models import ChatOpenAI
from langchain_openai.embeddings import OpenAIEmbeddings

loader = WebBaseLoader("https://lilianweng.github.io/posts/2023-06-23-agent/")
data = loader.load()

# 文本分割
text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)
all_splits = text_splitter.split_documents(data)

# 存储分割后的文本
vectorstore = FAISS.from_documents(documents=all_splits, embedding=OpenAIEmbeddings())

# LLM
llm = ChatOpenAI()

4. ConversationalRetrievalChain实现

from langchain.chains import ConversationalRetrievalChain
from langchain_core.prompts import ChatPromptTemplate

condense_question_template = """
Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question.

Chat History:
{chat_history}
Follow Up Input: {question}
Standalone question:"""

condense_question_prompt = ChatPromptTemplate.from_template(condense_question_template)

qa_template = """
You are an assistant for question-answering tasks.
Use the following pieces of retrieved context to answer
the question. If you don't know the answer, say that you
don't know. Use three sentences maximum and keep the
answer concise.

Chat History:
{chat_history}

Other context:
{context}

Question: {question}
"""

qa_prompt = ChatPromptTemplate.from_template(qa_template)

convo_qa_chain = ConversationalRetrievalChain.from_llm(
    llm,
    vectorstore.as_retriever(),
    condense_question_prompt=condense_question_prompt,
    combine_docs_chain_kwargs={
        "prompt": qa_prompt,
    },
)

response = convo_qa_chain(
    {
        "question": "What are autonomous agents?",
        "chat_history": "",
    }
)

print(response)

5. LCEL实现

from langchain.chains import create_history_aware_retriever, create_retrieval_chain
from langchain.chains.combine_documents import create_stuff_documents_chain

condense_question_system_template = (
    "Given a chat history and the latest user question "
    "which might reference context in the chat history, "
    "formulate a standalone question which can be understood "
    "without the chat history. Do NOT answer the question, "
    "just reformulate it if needed and otherwise return it as is."
)

condense_question_prompt = ChatPromptTemplate.from_messages(
    [
        ("system", condense_question_system_template),
        ("placeholder", "{chat_history}"),
        ("human", "{input}"),
    ]
)

history_aware_retriever = create_history_aware_retriever(
    llm, vectorstore.as_retriever(), condense_question_prompt
)

system_prompt = (
    "You are an assistant for question-answering tasks. "
    "Use the following pieces of retrieved context to answer "
    "the question. If you don't know the answer, say that you "
    "don't know. Use three sentences maximum and keep the "
    "answer concise."
    "\n\n"
    "{context}"
)

qa_prompt = ChatPromptTemplate.from_messages(
    [
        ("system", system_prompt),
        ("placeholder", "{chat_history}"),
        ("human", "{input}"),
    ]
)

qa_chain = create_stuff_documents_chain(llm, qa_prompt)

convo_qa_chain = create_retrieval_chain(history_aware_retriever, qa_chain)

response = convo_qa_chain.invoke(
    {
        "input": "What are autonomous agents?",
        "chat_history": [],
    }
)

print(response)