從 ConversationalRetrievalChain 遷移

ConversationalRetrievalChain 是一種結合檢索增強生成和聊天歷史記錄的一體化方法，讓您可以「與」您的文件「聊天」。

切換到 LCEL 實作的優點與 RetrievalQA 遷移指南 類似

• 更清晰的內部結構。ConversationalRetrievalChain 鏈隱藏了整個問題重新措辭步驟，該步驟會針對聊天歷史記錄取消引用初始查詢。
  • 這表示該類別包含兩組可配置的提示、LLM 等。
• 更輕鬆地返回來源文件。
• 支援像串流和非同步操作這樣的 runnable 方法。

以下是使用自訂提示的等效實作。我們將使用以下擷取程式碼將 Lilian Weng 關於自主代理的 部落格文章 載入到本機向量儲存中

共用設定

對於這兩個版本，我們都需要使用 WebBaseLoader 文件載入器載入資料，使用 RecursiveCharacterTextSplitter 分割資料，並將其添加到記憶體中的 FAISS 向量儲存中。

我們還將實例化一個聊天模型來使用。

%pip install --upgrade --quiet langchain-community langchain langchain-openai faiss-cpu beautifulsoup4

import os
from getpass import getpass

if "OPENAI_API_KEY" not in os.environ:
    os.environ["OPENAI_API_KEY"] = getpass()

# Load docs
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
from langchain_text_splitters import RecursiveCharacterTextSplitter

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

# Split
text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)
all_splits = text_splitter.split_documents(data)

# Store splits
vectorstore = FAISS.from_documents(documents=all_splits, embedding=OpenAIEmbeddings())

# LLM
llm = ChatOpenAI()

API 參考：WebBaseLoader | FAISS | ChatOpenAI | OpenAIEmbeddings | RecursiveCharacterTextSplitter

舊版

詳細資訊

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,
    },
)

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

API 參考：ConversationalRetrievalChain | ChatPromptTemplate

{'question': 'What are autonomous agents?',
 'chat_history': '',
 'answer': 'Autonomous agents are entities empowered with capabilities like planning, task decomposition, and memory to perform complex tasks independently. These agents can leverage tools like browsing the internet, reading documentation, executing code, and calling APIs to achieve their objectives. They are designed to handle tasks like scientific discovery and experimentation autonomously.'}

LCEL

詳細資訊

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)

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

API 參考：create_history_aware_retriever | create_retrieval_chain | create_stuff_documents_chain

{'input': 'What are autonomous agents?',
 'chat_history': [],
 'context': [Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': "LLM Powered Autonomous Agents | Lil'Log", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}, page_content='Boiko et al. (2023) also looked into LLM-empowered agents for scientific discovery, to handle autonomous design, planning, and performance of complex scientific experiments. This agent can use tools to browse the Internet, read documentation, execute code, call robotics experimentation APIs and leverage other LLMs.\nFor example, when requested to "develop a novel anticancer drug", the model came up with the following reasoning steps:'),
  Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': "LLM Powered Autonomous Agents | Lil'Log", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}, page_content='Weng, Lilian. (Jun 2023). “LLM-powered Autonomous Agents”. Lil’Log. https://lilianweng.github.io/posts/2023-06-23-agent/.'),
  Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': "LLM Powered Autonomous Agents | Lil'Log", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}, page_content='Fig. 1. Overview of a LLM-powered autonomous agent system.\nComponent One: Planning#\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\nTask Decomposition#'),
  Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': "LLM Powered Autonomous Agents | Lil'Log", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}, page_content="LLM Powered Autonomous Agents | Lil'Log\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nLil'Log\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nPosts\n\n\n\n\nArchive\n\n\n\n\nSearch\n\n\n\n\nTags\n\n\n\n\nFAQ\n\n\n\n\nemojisearch.app\n\n\n\n\n\n\n\n\n\n      LLM Powered Autonomous Agents\n    \nDate: June 23, 2023  |  Estimated Reading Time: 31 min  |  Author: Lilian Weng\n\n\n \n\n\nTable of Contents\n\n\n\nAgent System Overview\n\nComponent One: Planning\n\nTask Decomposition\n\nSelf-Reflection\n\n\nComponent Two: Memory\n\nTypes of Memory\n\nMaximum Inner Product Search (MIPS)")],
 'answer': 'Autonomous agents are entities that can act independently to achieve specific goals or tasks without direct human intervention. These agents have the ability to perceive their environment, make decisions, and take actions based on their programming or learning. They can perform tasks such as planning, execution, and problem-solving autonomously.'}

下一步

您現在已經了解如何將一些舊版鏈的現有用法遷移到 LCEL。

接下來，查看 LCEL 概念文件 以取得更多背景資訊。