构建检索增强生成 (RAG) 应用：第一部分

LLM 赋能的最强大的应用之一是复杂的问答 (Q&A) 聊天机器人。这些是可以回答关于特定来源信息问题的应用程序。这些应用程序使用一种称为检索增强生成的技术，或 RAG。

这是一个多部分教程

第一部分（本指南）介绍了 RAG，并逐步讲解了最简实现。
第二部分扩展了实现，以适应对话式交互和多步骤检索过程。

本教程将展示如何构建一个简单的基于文本数据源的问答应用程序。在此过程中，我们将介绍典型的问答架构，并重点介绍用于更高级问答技术的其他资源。我们还将了解 LangSmith 如何帮助我们追踪和理解我们的应用程序。随着我们的应用程序复杂性增加，LangSmith 将变得越来越有用。

如果您已经熟悉基本检索，您可能也会对这篇不同检索技术的高级概述感兴趣。

注意：这里我们专注于非结构化数据的问答。如果您对基于结构化数据的 RAG 感兴趣，请查看我们关于基于 SQL 数据进行问答的教程。

概述

典型的 RAG 应用程序具有两个主要组件

索引：一个用于从源摄取数据并对其进行索引的管道。这通常离线发生。

检索和生成：实际的 RAG 链，它在运行时获取用户查询，并从索引中检索相关数据，然后将其传递给模型。

注意：本教程的索引部分将在很大程度上遵循语义搜索教程。

从原始数据到答案的最常见完整序列如下所示

索引

加载：首先我们需要加载我们的数据。这通过文档加载器完成。
分割：文本分割器将大型 Documents 分解为更小的块。这对于索引数据和将其传递到模型中都很有用，因为大块数据更难搜索，并且无法容纳在模型的有限上下文窗口中。
存储：我们需要某个地方来存储和索引我们的分割块，以便稍后可以对其进行搜索。这通常使用向量存储和嵌入模型完成。

index_diagram

检索和生成

检索：给定用户输入，使用检索器从存储中检索相关分割块。
生成：聊天模型 / LLM 使用包含问题和检索数据的提示生成答案

retrieval_diagram

一旦我们索引了数据，我们将使用 LangGraph 作为我们的编排框架来实现检索和生成步骤。

设置

Jupyter Notebook

本教程和其他教程最好在 Jupyter notebooks 中运行。在交互式环境中学习指南是更好地理解它们的好方法。有关如何安装的说明，请参阅此处。

安装

本教程需要这些 langchain 依赖项

Pip
Conda

%pip install --quiet --upgrade langchain-text-splitters langchain-community langgraph

conda install langchain-text-splitters langchain-community langgraph -c conda-forge

有关更多详细信息，请参阅我们的安装指南。

LangSmith

您使用 LangChain 构建的许多应用程序将包含多个步骤，其中包含对 LLM 调用的多次调用。随着这些应用程序变得越来越复杂，能够检查链或代理内部究竟发生了什么变得至关重要。最好的方法是使用 LangSmith。

在上面的链接注册后，请确保设置您的环境变量以开始记录追踪

export LANGSMITH_TRACING="true"
export LANGSMITH_API_KEY="..."

或者，如果在 notebook 中，您可以使用以下命令设置它们

import getpass
import os

os.environ["LANGSMITH_TRACING"] = "true"
os.environ["LANGSMITH_API_KEY"] = getpass.getpass()

组件

我们将需要从 LangChain 的集成套件中选择三个组件。

选择聊天模型

pip install -qU "langchain[openai]"

import getpass
import os

if not os.environ.get("OPENAI_API_KEY"):
  os.environ["OPENAI_API_KEY"] = getpass.getpass("Enter API key for OpenAI: ")

from langchain.chat_models import init_chat_model

llm = init_chat_model("gpt-4o-mini", model_provider="openai")

选择嵌入模型

pip install -qU langchain-openai

import getpass
import os

if not os.environ.get("OPENAI_API_KEY"):
  os.environ["OPENAI_API_KEY"] = getpass.getpass("Enter API key for OpenAI: ")

from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings(model="text-embedding-3-large")

选择向量存储

pip install -qU langchain-core

from langchain_core.vectorstores import InMemoryVectorStore

vector_store = InMemoryVectorStore(embeddings)

预览

在本指南中，我们将构建一个应用程序，用于回答关于网站内容的问题。我们将使用的具体网站是 Lilian Weng 的 LLM Powered Autonomous Agents 博客文章，这使我们能够询问有关帖子内容的问题。

我们可以创建一个简单的索引管道和 RAG 链，用大约 50 行代码来完成这项工作。

import bs4
from langchain import hub
from langchain_community.document_loaders import WebBaseLoader
from langchain_core.documents import Document
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langgraph.graph import START, StateGraph
from typing_extensions import List, TypedDict

# Load and chunk contents of the blog
loader = WebBaseLoader(
    web_paths=("https://lilianweng.github.io/posts/2023-06-23-agent/",),
    bs_kwargs=dict(
        parse_only=bs4.SoupStrainer(
            class_=("post-content", "post-title", "post-header")
        )
    ),
)
docs = loader.load()

text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
all_splits = text_splitter.split_documents(docs)

# Index chunks
_ = vector_store.add_documents(documents=all_splits)

# Define prompt for question-answering
prompt = hub.pull("rlm/rag-prompt")


# Define state for application
class State(TypedDict):
    question: str
    context: List[Document]
    answer: str


# Define application steps
def retrieve(state: State):
    retrieved_docs = vector_store.similarity_search(state["question"])
    return {"context": retrieved_docs}


def generate(state: State):
    docs_content = "\n\n".join(doc.page_content for doc in state["context"])
    messages = prompt.invoke({"question": state["question"], "context": docs_content})
    response = llm.invoke(messages)
    return {"answer": response.content}


# Compile application and test
graph_builder = StateGraph(State).add_sequence([retrieve, generate])
graph_builder.add_edge(START, "retrieve")
graph = graph_builder.compile()

API 参考：hub | WebBaseLoader | Document | RecursiveCharacterTextSplitter | StateGraph

response = graph.invoke({"question": "What is Task Decomposition?"})
print(response["answer"])

Task Decomposition is the process of breaking down a complicated task into smaller, manageable steps to facilitate easier execution and understanding. Techniques like Chain of Thought (CoT) and Tree of Thoughts (ToT) guide models to think step-by-step, allowing them to explore multiple reasoning possibilities. This method enhances performance on complex tasks and provides insight into the model's thinking process.

查看 LangSmith 追踪。

详细演练

让我们逐步浏览上面的代码，以真正理解发生了什么。

1. 索引

注意

本节是语义搜索教程中内容的缩写版本。如果您对文档加载器、嵌入和向量存储感到满意，请随意跳到关于检索和生成的下一节。

加载文档

我们首先需要加载博客文章内容。我们可以为此使用 DocumentLoaders，它们是从源加载数据并返回 Document 对象列表的对象。

在本例中，我们将使用 WebBaseLoader，它使用 urllib 从 Web URL 加载 HTML，并使用 BeautifulSoup 将其解析为文本。我们可以通过将参数传递到 BeautifulSoup 解析器（通过 bs_kwargs）来自定义 HTML -> 文本解析（请参阅 BeautifulSoup 文档）。在本例中，只有类为“post-content”、“post-title”或“post-header”的 HTML 标签是相关的，因此我们将删除所有其他标签。

import bs4
from langchain_community.document_loaders import WebBaseLoader

# Only keep post title, headers, and content from the full HTML.
bs4_strainer = bs4.SoupStrainer(class_=("post-title", "post-header", "post-content"))
loader = WebBaseLoader(
    web_paths=("https://lilianweng.github.io/posts/2023-06-23-agent/",),
    bs_kwargs={"parse_only": bs4_strainer},
)
docs = loader.load()

assert len(docs) == 1
print(f"Total characters: {len(docs[0].page_content)}")

API 参考：WebBaseLoader

Total characters: 43131

print(docs[0].page_content[:500])

      LLM Powered Autonomous Agents
    
Date: June 23, 2023  |  Estimated Reading Time: 31 min  |  Author: Lilian Weng


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.
Agent System Overview#
In

深入了解

DocumentLoader：从源加载数据作为 Documents 列表的对象。

文档：关于如何使用 DocumentLoaders 的详细文档。
集成：160 多个集成可供选择。
接口：基本接口的 API 参考。

分割文档

我们加载的文档超过 42k 个字符，这太长了，无法容纳到许多模型的上下文窗口中。即使对于那些可以容纳完整帖子在其上下文窗口中的模型，模型也可能难以在非常长的输入中找到信息。

为了处理这个问题，我们将把 Document 分割成块，以便进行嵌入和向量存储。这应该有助于我们在运行时仅检索博客文章的最相关部分。

与语义搜索教程中一样，我们使用 RecursiveCharacterTextSplitter，它将使用常见的分隔符（如换行符）递归地分割文档，直到每个块都达到适当的大小。这是通用文本用例推荐的文本分割器。

from langchain_text_splitters import RecursiveCharacterTextSplitter

text_splitter = RecursiveCharacterTextSplitter(
    chunk_size=1000,  # chunk size (characters)
    chunk_overlap=200,  # chunk overlap (characters)
    add_start_index=True,  # track index in original document
)
all_splits = text_splitter.split_documents(docs)

print(f"Split blog post into {len(all_splits)} sub-documents.")

API 参考：RecursiveCharacterTextSplitter

Split blog post into 66 sub-documents.

深入了解

TextSplitter：将 Document 列表分割成更小块的对象。DocumentTransformer 的子类。

通过阅读操作文档，了解有关使用不同方法分割文本的更多信息
代码（py 或 js）
科学论文
接口：基本接口的 API 参考。

DocumentTransformer：对 Document 对象列表执行转换的对象。

文档：关于如何使用 DocumentTransformers 的详细文档
集成
接口：基本接口的 API 参考。

存储文档

现在我们需要索引我们的 66 个文本块，以便我们可以在运行时搜索它们。按照语义搜索教程，我们的方法是嵌入每个文档分割的内容，并将这些嵌入插入到向量存储中。给定输入查询，我们可以使用向量搜索来检索相关文档。

我们可以使用在教程开始时选择的向量存储和嵌入模型，通过单个命令嵌入和存储我们所有的文档分割块。

document_ids = vector_store.add_documents(documents=all_splits)

print(document_ids[:3])

['07c18af6-ad58-479a-bfb1-d508033f9c64', '9000bf8e-1993-446f-8d4d-f4e507ba4b8f', 'ba3b5d14-bed9-4f5f-88be-44c88aedc2e6']

深入了解

Embeddings：文本嵌入模型的包装器，用于将文本转换为嵌入。

文档：关于如何使用嵌入的详细文档。
集成：30 多个集成可供选择。
接口：基本接口的 API 参考。

VectorStore：向量数据库的包装器，用于存储和查询嵌入。

文档：关于如何使用向量存储的详细文档。
集成：40 多个集成可供选择。
接口：基本接口的 API 参考。

这完成了管道的索引部分。此时，我们有一个可查询的向量存储，其中包含我们博客文章的块状内容。给定用户问题，我们理想情况下应该能够返回博客文章中回答该问题的片段。

2. 检索和生成

现在让我们编写实际的应用程序逻辑。我们想要创建一个简单的应用程序，它接受用户问题，搜索与该问题相关的文档，将检索到的文档和原始问题传递给模型，并返回答案。

对于生成，我们将使用在教程开始时选择的聊天模型。

我们将使用已签入 LangChain 提示中心（此处）的 RAG 提示。

from langchain import hub

prompt = hub.pull("rlm/rag-prompt")

example_messages = prompt.invoke(
    {"context": "(context goes here)", "question": "(question goes here)"}
).to_messages()

assert len(example_messages) == 1
print(example_messages[0].content)

API 参考：hub

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, just say that you don't know. Use three sentences maximum and keep the answer concise.
Question: (question goes here) 
Context: (context goes here) 
Answer:

我们将使用 LangGraph 将检索和生成步骤绑定到一个应用程序中。这将带来许多好处

我们可以定义一次应用程序逻辑，并自动支持多种调用模式，包括流式传输、异步和批量调用。
我们通过 LangGraph 平台获得简化的部署。
LangSmith 将自动一起跟踪我们应用程序的步骤。
我们可以轻松地向我们的应用程序添加关键功能，包括持久性和人工参与审批，只需进行最少的代码更改。

要使用 LangGraph，我们需要定义三件事

我们应用程序的状态；
我们应用程序的节点（即，应用程序步骤）；
我们应用程序的“控制流”（例如，步骤的排序）。

状态：

我们应用程序的状态控制着哪些数据输入到应用程序、在步骤之间传输以及由应用程序输出。它通常是 TypedDict，但也可是 Pydantic BaseModel。

对于简单的 RAG 应用程序，我们可以只跟踪输入问题、检索到的上下文和生成的答案

from langchain_core.documents import Document
from typing_extensions import List, TypedDict


class State(TypedDict):
    question: str
    context: List[Document]
    answer: str

API 参考：Document

节点（应用程序步骤）

让我们从两个步骤的简单序列开始：检索和生成。

def retrieve(state: State):
    retrieved_docs = vector_store.similarity_search(state["question"])
    return {"context": retrieved_docs}


def generate(state: State):
    docs_content = "\n\n".join(doc.page_content for doc in state["context"])
    messages = prompt.invoke({"question": state["question"], "context": docs_content})
    response = llm.invoke(messages)
    return {"answer": response.content}

我们的检索步骤只是使用输入问题运行相似性搜索，而生成步骤将检索到的上下文和原始问题格式化为聊天模型的提示。

控制流

最后，我们将我们的应用程序编译成单个 graph 对象。在本例中，我们只是将检索和生成步骤连接成一个序列。

from langgraph.graph import START, StateGraph

graph_builder = StateGraph(State).add_sequence([retrieve, generate])
graph_builder.add_edge(START, "retrieve")
graph = graph_builder.compile()

API 参考：StateGraph

LangGraph 还附带内置实用程序，用于可视化您应用程序的控制流

from IPython.display import Image, display

display(Image(graph.get_graph().draw_mermaid_png()))

我需要使用 LangGraph 吗？

构建 RAG 应用程序不需要 LangGraph。实际上，我们可以通过调用各个组件来实现相同的应用程序逻辑

question = "..."

retrieved_docs = vector_store.similarity_search(question)
docs_content = "\n\n".join(doc.page_content for doc in retrieved_docs)
prompt = prompt.invoke({"question": question, "context": docs_content})
answer = llm.invoke(prompt)

LangGraph 的好处包括

支持多种调用模式：如果我们想要流式传输输出令牌，或流式传输各个步骤的结果，则需要重写此逻辑；
通过 LangSmith 自动支持追踪，并通过 LangGraph 平台进行部署；
支持持久性、人工参与环节和其他功能。

许多用例需要在对话体验中使用 RAG，这样用户可以通过有状态的对话接收上下文知情的答案。正如我们将在教程的第二部分中看到的那样，LangGraph 对状态的管理和持久性极大地简化了这些应用程序。

用法

让我们测试一下我们的应用程序！LangGraph 支持多种调用模式，包括同步、异步和流式传输。

调用

result = graph.invoke({"question": "What is Task Decomposition?"})

print(f'Context: {result["context"]}\n\n')
print(f'Answer: {result["answer"]}')

Context: [Document(id='a42dc78b-8f76-472a-9e25-180508af74f3', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'start_index': 1585}, 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#\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.'), Document(id='c0e45887-d0b0-483d-821a-bb5d8316d51d', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'start_index': 2192}, page_content='Tree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\nTask decomposition can be done (1) by LLM with simple prompting like "Steps for XYZ.\\n1.", "What are the subgoals for achieving XYZ?", (2) by using task-specific instructions; e.g. "Write a story outline." for writing a novel, or (3) with human inputs.'), Document(id='4cc7f318-35f5-440f-a4a4-145b5f0b918d', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'start_index': 29630}, page_content='Resources:\n1. Internet access for searches and information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your actions to ensure you are performing to the best of your abilities.\n2. Constructively self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions and strategies to refine your approach.\n4. Every command has a cost, so be smart and efficient. Aim to complete tasks in the least number of steps.'), Document(id='f621ade4-9b0d-471f-a522-44eb5feeba0c', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'start_index': 19373}, page_content="(3) Task execution: Expert models execute on the specific tasks and log results.\nInstruction:\n\nWith the input and the inference results, the AI assistant needs to describe the process and results. The previous stages can be formed as - User Input: {{ User Input }}, Task Planning: {{ Tasks }}, Model Selection: {{ Model Assignment }}, Task Execution: {{ Predictions }}. You must first answer the user's request in a straightforward manner. Then describe the task process and show your analysis and model inference results to the user in the first person. If inference results contain a file path, must tell the user the complete file path.")]

Answer: Task decomposition is a technique used to break down complex tasks into smaller, manageable steps, allowing for more efficient problem-solving. This can be achieved through methods like chain of thought prompting or the tree of thoughts approach, which explores multiple reasoning possibilities at each step. It can be initiated through simple prompts, task-specific instructions, or human inputs.

流式传输步骤

for step in graph.stream(
    {"question": "What is Task Decomposition?"}, stream_mode="updates"
):
    print(f"{step}\n\n----------------\n")

{'retrieve': {'context': [Document(id='a42dc78b-8f76-472a-9e25-180508af74f3', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'start_index': 1585}, 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#\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.'), Document(id='c0e45887-d0b0-483d-821a-bb5d8316d51d', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'start_index': 2192}, page_content='Tree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\nTask decomposition can be done (1) by LLM with simple prompting like "Steps for XYZ.\\n1.", "What are the subgoals for achieving XYZ?", (2) by using task-specific instructions; e.g. "Write a story outline." for writing a novel, or (3) with human inputs.'), Document(id='4cc7f318-35f5-440f-a4a4-145b5f0b918d', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'start_index': 29630}, page_content='Resources:\n1. Internet access for searches and information gathering.\n2. Long Term memory management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your actions to ensure you are performing to the best of your abilities.\n2. Constructively self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions and strategies to refine your approach.\n4. Every command has a cost, so be smart and efficient. Aim to complete tasks in the least number of steps.'), Document(id='f621ade4-9b0d-471f-a522-44eb5feeba0c', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'start_index': 19373}, page_content="(3) Task execution: Expert models execute on the specific tasks and log results.\nInstruction:\n\nWith the input and the inference results, the AI assistant needs to describe the process and results. The previous stages can be formed as - User Input: {{ User Input }}, Task Planning: {{ Tasks }}, Model Selection: {{ Model Assignment }}, Task Execution: {{ Predictions }}. You must first answer the user's request in a straightforward manner. Then describe the task process and show your analysis and model inference results to the user in the first person. If inference results contain a file path, must tell the user the complete file path.")]}}

----------------

{'generate': {'answer': 'Task decomposition is the process of breaking down a complex task into smaller, more manageable steps. This technique, often enhanced by methods like Chain of Thought (CoT) or Tree of Thoughts, allows models to reason through tasks systematically and improves performance by clarifying the thought process. It can be achieved through simple prompts, task-specific instructions, or human inputs.'}}

----------------

流式传输令牌

for message, metadata in graph.stream(
    {"question": "What is Task Decomposition?"}, stream_mode="messages"
):
    print(message.content, end="|")

|Task| decomposition| is| the| process| of| breaking| down| complex| tasks| into| smaller|,| more| manageable| steps|.| It| can| be| achieved| through| techniques| like| Chain| of| Thought| (|Co|T|)| prompting|,| which| encourages| the| model| to| think| step| by| step|,| or| through| more| structured| methods| like| the| Tree| of| Thoughts|.| This| approach| not| only| simplifies| task| execution| but| also| provides| insights| into| the| model|'s| reasoning| process|.||

提示

对于异步调用，请使用

result = await graph.ainvoke(...)

和

async for step in graph.astream(...):

返回来源

请注意，通过将检索到的上下文存储在图的状态中，我们在状态的 "context" 字段中恢复了模型生成答案的来源。有关返回来源的更多详细信息，请参阅本指南。

深入了解

聊天模型接收消息序列并返回一条消息。

文档
集成：25 多个集成可供选择。
接口：基本接口的 API 参考。

自定义提示

如上所示，我们可以从提示中心加载提示（例如，此 RAG 提示）。提示也可以轻松自定义。例如

from langchain_core.prompts import PromptTemplate

template = """Use the following pieces of context to answer the question at the end.
If you don't know the answer, just say that you don't know, don't try to make up an answer.
Use three sentences maximum and keep the answer as concise as possible.
Always say "thanks for asking!" at the end of the answer.

{context}

Question: {question}

Helpful Answer:"""
custom_rag_prompt = PromptTemplate.from_template(template)

API 参考：PromptTemplate

查询分析

到目前为止，我们正在使用原始输入查询执行检索。但是，允许模型生成用于检索目的的查询有一些优势。例如

除了语义搜索之外，我们还可以构建结构化过滤器（例如，“查找自 2020 年以来的文档。”）；
模型可以将用户查询（可能是多方面的或包含不相关的语言）重写为更有效的搜索查询。

查询分析使用模型从原始用户输入转换或构建优化的搜索查询。我们可以轻松地将查询分析步骤合并到我们的应用程序中。为了说明目的，让我们向向量存储中的文档添加一些元数据。我们将向文档添加一些（人为的）部分，我们稍后可以在其上进行过滤。

total_documents = len(all_splits)
third = total_documents // 3

for i, document in enumerate(all_splits):
    if i < third:
        document.metadata["section"] = "beginning"
    elif i < 2 * third:
        document.metadata["section"] = "middle"
    else:
        document.metadata["section"] = "end"


all_splits[0].metadata

{'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/',
 'start_index': 8,
 'section': 'beginning'}

我们将需要更新向量存储中的文档。我们将为此使用简单的 InMemoryVectorStore，因为我们将使用它的一些特定功能（即，元数据过滤）。有关您选择的向量存储的相关功能，请参阅向量存储集成文档。

from langchain_core.vectorstores import InMemoryVectorStore

vector_store = InMemoryVectorStore(embeddings)
_ = vector_store.add_documents(all_splits)

API 参考：InMemoryVectorStore

接下来，让我们为搜索查询定义一个模式。我们将为此目的使用结构化输出。在这里，我们将查询定义为包含一个字符串查询和一个文档部分（“开头”、“中间”或“结尾”），但这可以根据您的喜好进行定义。

from typing import Literal

from typing_extensions import Annotated


class Search(TypedDict):
    """Search query."""

    query: Annotated[str, ..., "Search query to run."]
    section: Annotated[
        Literal["beginning", "middle", "end"],
        ...,
        "Section to query.",
    ]

最后，我们向 LangGraph 应用程序添加一个步骤，以从用户的原始输入生成查询

class State(TypedDict):
    question: str
    query: Search
    context: List[Document]
    answer: str


def analyze_query(state: State):
    structured_llm = llm.with_structured_output(Search)
    query = structured_llm.invoke(state["question"])
    return {"query": query}


def retrieve(state: State):
    query = state["query"]
    retrieved_docs = vector_store.similarity_search(
        query["query"],
        filter=lambda doc: doc.metadata.get("section") == query["section"],
    )
    return {"context": retrieved_docs}


def generate(state: State):
    docs_content = "\n\n".join(doc.page_content for doc in state["context"])
    messages = prompt.invoke({"question": state["question"], "context": docs_content})
    response = llm.invoke(messages)
    return {"answer": response.content}


graph_builder = StateGraph(State).add_sequence([analyze_query, retrieve, generate])
graph_builder.add_edge(START, "analyze_query")
graph = graph_builder.compile()

完整代码

from typing import Literal

import bs4
from langchain import hub
from langchain_community.document_loaders import WebBaseLoader
from langchain_core.documents import Document
from langchain_core.vectorstores import InMemoryVectorStore
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langgraph.graph import START, StateGraph
from typing_extensions import Annotated, List, TypedDict

# Load and chunk contents of the blog
loader = WebBaseLoader(
    web_paths=("https://lilianweng.github.io/posts/2023-06-23-agent/",),
    bs_kwargs=dict(
        parse_only=bs4.SoupStrainer(
            class_=("post-content", "post-title", "post-header")
        )
    ),
)
docs = loader.load()

text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
all_splits = text_splitter.split_documents(docs)


# Update metadata (illustration purposes)
total_documents = len(all_splits)
third = total_documents // 3

for i, document in enumerate(all_splits):
    if i < third:
        document.metadata["section"] = "beginning"
    elif i < 2 * third:
        document.metadata["section"] = "middle"
    else:
        document.metadata["section"] = "end"


# Index chunks
vector_store = InMemoryVectorStore(embeddings)
_ = vector_store.add_documents(all_splits)


# Define schema for search
class Search(TypedDict):
    """Search query."""

    query: Annotated[str, ..., "Search query to run."]
    section: Annotated[
        Literal["beginning", "middle", "end"],
        ...,
        "Section to query.",
    ]

# Define prompt for question-answering
prompt = hub.pull("rlm/rag-prompt")


# Define state for application
class State(TypedDict):
    question: str
    query: Search
    context: List[Document]
    answer: str


def analyze_query(state: State):
    structured_llm = llm.with_structured_output(Search)
    query = structured_llm.invoke(state["question"])
    return {"query": query}


def retrieve(state: State):
    query = state["query"]
    retrieved_docs = vector_store.similarity_search(
        query["query"],
        filter=lambda doc: doc.metadata.get("section") == query["section"],
    )
    return {"context": retrieved_docs}


def generate(state: State):
    docs_content = "\n\n".join(doc.page_content for doc in state["context"])
    messages = prompt.invoke({"question": state["question"], "context": docs_content})
    response = llm.invoke(messages)
    return {"answer": response.content}


graph_builder = StateGraph(State).add_sequence([analyze_query, retrieve, generate])
graph_builder.add_edge(START, "analyze_query")
graph = graph_builder.compile()

display(Image(graph.get_graph().draw_mermaid_png()))

我们可以通过专门要求从文章末尾获取上下文来测试我们的实现。请注意，模型在其答案中包含不同的信息。

for step in graph.stream(
    {"question": "What does the end of the post say about Task Decomposition?"},
    stream_mode="updates",
):
    print(f"{step}\n\n----------------\n")

{'analyze_query': {'query': {'query': 'Task Decomposition', 'section': 'end'}}}

----------------

{'retrieve': {'context': [Document(id='d6cef137-e1e8-4ddc-91dc-b62bd33c6020', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'start_index': 39221, 'section': 'end'}, page_content='Finite context length: The restricted context capacity limits the inclusion of historical information, detailed instructions, API call context, and responses. The design of the system has to work with this limited communication bandwidth, while mechanisms like self-reflection to learn from past mistakes would benefit a lot from long or infinite context windows. Although vector stores and retrieval can provide access to a larger knowledge pool, their representation power is not as powerful as full attention.\n\n\nChallenges in long-term planning and task decomposition: Planning over a lengthy history and effectively exploring the solution space remain challenging. LLMs struggle to adjust plans when faced with unexpected errors, making them less robust compared to humans who learn from trial and error.'), Document(id='d1834ae1-eb6a-43d7-a023-08dfa5028799', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'start_index': 39086, 'section': 'end'}, page_content='}\n]\nChallenges#\nAfter going through key ideas and demos of building LLM-centered agents, I start to see a couple common limitations:'), Document(id='ca7f06e4-2c2e-4788-9a81-2418d82213d9', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'start_index': 32942, 'section': 'end'}, page_content='}\n]\nThen after these clarification, the agent moved into the code writing mode with a different system message.\nSystem message:'), Document(id='1fcc2736-30f4-4ef6-90f2-c64af92118cb', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'start_index': 35127, 'section': 'end'}, page_content='"content": "You will get instructions for code to write.\\nYou will write a very long answer. Make sure that every detail of the architecture is, in the end, implemented as code.\\nMake sure that every detail of the architecture is, in the end, implemented as code.\\n\\nThink step by step and reason yourself to the right decisions to make sure we get it right.\\nYou will first lay out the names of the core classes, functions, methods that will be necessary, as well as a quick comment on their purpose.\\n\\nThen you will output the content of each file including ALL code.\\nEach file must strictly follow a markdown code block format, where the following tokens must be replaced such that\\nFILENAME is the lowercase file name including the file extension,\\nLANG is the markup code block language for the code\'s language, and CODE is the code:\\n\\nFILENAME\\n\`\`\`LANG\\nCODE\\n\`\`\`\\n\\nYou will start with the \\"entrypoint\\" file, then go to the ones that are imported by that file, and so on.\\nPlease')]}}

----------------

{'generate': {'answer': 'The end of the post highlights that task decomposition faces challenges in long-term planning and adapting to unexpected errors. LLMs struggle with adjusting their plans, making them less robust compared to humans who learn from trial and error. This indicates a limitation in effectively exploring the solution space and handling complex tasks.'}}

----------------

在流式步骤和 LangSmith 跟踪中，我们现在可以观察到被馈送到检索步骤的结构化查询。

查询分析是一个内容丰富的问题，有广泛的方法。有关更多示例，请参阅操作指南。

下一步

我们已经介绍了构建基于数据的基本问答应用程序的步骤

使用文档加载器加载数据
使用文本分割器对索引数据进行分块，使其更易于模型使用
嵌入数据并将数据存储在向量存储中
检索先前存储的块以响应传入的问题
使用检索到的块作为上下文生成答案。

在本教程的第 2 部分中，我们将扩展此处的实现以适应对话式交互和多步骤检索过程。

进一步阅读

返回来源：了解如何返回源文档
流式处理：了解如何流式传输输出和中间步骤
添加聊天记录：了解如何向您的应用程序添加聊天记录
检索概念指南：特定检索技术的高级概述

概述​

索引​

检索和生成​

设置​

Jupyter Notebook​

安装​

LangSmith​

组件​

预览​

详细演练​

1. 索引​

加载文档​

深入了解​

分割文档​

深入了解​

存储文档​

深入了解​

2. 检索和生成​

状态：​

节点（应用程序步骤）​

控制流​

用法​

返回来源​

深入了解​

查询分析​

下一步​

此页面对您有帮助吗？

概述

索引

检索和生成

设置

Jupyter Notebook

安装

LangSmith

组件

预览

详细演练

1. 索引

加载文档

深入了解

分割文档

深入了解

存储文档

深入了解

2. 检索和生成

状态：

节点（应用程序步骤）

控制流

用法

返回来源

深入了解

查询分析

下一步