从 RetrievalQA 迁移
RetrievalQA 链 通过检索增强生成，对数据源进行了自然语言问答。
切换到 LLMs 链式实现的一些优点包括：
- 更易于自定义。诸如提示和文档格式化方式等细节只能通过
RetrievalQA链中的特定参数进行配置。 - 更轻松地返回源文档。
- 对流式传输和异步操作等可运行方法提供支持。
现在让我们将它们并排进行比较。我们将使用以下摄取代码将 Lilian Weng 关于自主代理的博客文章加载到本地向量存储中：
共享设置
对于两个版本，我们需要使用 WebBaseLoader 文档加载器加 载数据，使用 RecursiveCharacterTextSplitter 进行分割，并将其添加到内存中的 FAISS 向量存储中。
我们还将实例化一个要使用的聊天模型。
%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 Reference:WebBaseLoader | FAISS | ChatOpenAI | OpenAIEmbeddings | RecursiveCharacterTextSplitter
旧 版
Details
from langchain import hub
from langchain.chains import RetrievalQA
# See full prompt at https://smith.langchain.com/hub/rlm/rag-prompt
prompt = hub.pull("rlm/rag-prompt")
qa_chain = RetrievalQA.from_llm(
llm, retriever=vectorstore.as_retriever(), prompt=prompt
)
qa_chain("What are autonomous agents?")
API Reference:hub | RetrievalQA
{'query': 'What are autonomous agents?',
'result': 'Autonomous agents are LLM-empowered agents capable of handling autonomous design, planning, and performance of complex scientific experiments. These agents can browse the Internet, read documentation, execute code, call robotics experimentation APIs, and leverage other LLMs. They can generate reasoning steps, such as developing a novel anticancer drug, based on requested tasks.'}
LCEL
Details
from langchain import hub
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough
# See full prompt at https://smith.langchain.com/hub/rlm/rag-prompt
prompt = hub.pull("rlm/rag-prompt")
def format_docs(docs):
return "\n\n".join(doc.page_content for doc in docs)
qa_chain = (
{
"context": vectorstore.as_retriever() | format_docs,
"question": RunnablePassthrough(),
}
| prompt
| llm
| StrOutputParser()
)
qa_chain.invoke("What are autonomous agents?")
'Autonomous agents are agents empowered by large language models (LLMs) that can handle autonomous design, planning, and performance of complex tasks such as scientific experiments. These agents can use tools to browse the Internet, read documentation, execute code, call robotics experimentation APIs, and leverage other LLMs for their tasks. The model can come up with reasoning steps when given a specific task, such as developing a novel anticancer drug.'
LCEL 实现暴露了围绕检索、格式化文档以及通过提示传递给 LLM 的内部情况，但它更冗长。您可以自定义此组合逻辑，并将其包装在帮助函数中，或者使用更高级的 create_retrieval_chain 和 create_stuff_documents_chain 辅助方法：
from langchain import hub
from langchain.chains import create_retrieval_chain
from langchain.chains.combine_documents import create_stuff_documents_chain
# See full prompt at https://smith.langchain.com/hub/langchain-ai/retrieval-qa-chat
retrieval_qa_chat_prompt = hub.pull("langchain-ai/retrieval-qa-chat")
combine_docs_chain = create_stuff_documents_chain(llm, retrieval_qa_chat_prompt)
rag_chain = create_retrieval_chain(vectorstore.as_retriever(), combine_docs_chain)
rag_chain.invoke({"input": "What are autonomous agents?"})
{'input': 'What are autonomous agents?',
'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='Or\n@article{weng2023agent,\n title = "LLM-powered Autonomous Agents",\n author = "Weng, Lilian",\n journal = "lilianweng.github.io",\n year = "2023",\n month = "Jun",\n url = "https://lilianweng.github.io/posts/2023-06-23-agent/"\n}\nReferences#\n[1] Wei et al. “Chain of thought prompting elicits reasoning in large language models.” NeurIPS 2022\n[2] Yao et al. “Tree of Thoughts: Dliberate Problem Solving with Large Language Models.” arXiv preprint arXiv:2305.10601 (2023).')],
'answer': 'Autonomous agents are entities capable of operating independently to perform tasks or make decisions without direct human intervention. In the context provided, autonomous agents empowered by Large Language Models (LLMs) are used for scientific discovery, including tasks like autonomous design, planning, and executing complex scientific experiments.'}
后续步骤
查阅 LCEL 概念文档 以获取关于 LangChain expression language 的更多背景信息。