Skip to main content
Open In ColabOpen on GitHub

构建一个检索增强生成（RAG）应用：第一部分

由LLMs实现的最强大的应用之一是复杂的问答（Q&A）聊天机器人。这些应用程序可以回答关于特定源信息的问题。这些应用程序使用了一种称为检索增强生成（Retrieval Augmented Generation）的技术，或RAG。

这是一个多部分教程：

  • 第1部分（本指南）介绍了RAG并逐步讲解了一个最小实现。
  • Part 2 扩展了实现，以适应对话式交互和多步检索过程。

本教程将展示如何基于文本数据源构建一个简单的问答应用。在此过程中，我们将介绍一个典型的问答架构，并强调更多高级问答技术的额外资源。我们还将看到LangSmith如何帮助我们追踪和理解我们的应用。随着应用复杂性的增加，LangSmith将变得越来越有帮助。

如果你已经熟悉了基本的检索，你可能也会对这个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。如果您对结构化数据的RAG感兴趣，请查看我们的教程关于SQL数据的问答。

概述​

一个典型的RAG应用程序有两个主要组件：

索引: 一个从源摄取数据并对其进行索引的管道。这通常是在线下进行的。

检索和生成：实际的RAG链，它在运行时接收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主要遵循语义搜索教程。

从原始数据到答案的最常见完整流程如下：

索引​

  1. 加载: 首先我们需要加载我们的数据。这是通过文档加载器完成的。
  2. 分割: 文本分割器将大型Documents分解为较小的块。这对于索引数据和将其传递到模型中都非常有用，因为较大的块更难搜索，并且无法适应模型的有限上下文窗口。
  3. 存储: 我们需要一个地方来存储和索引我们的分割，以便以后可以搜索它们。这通常使用VectorStore和Embeddings模型来完成。

index_diagram

检索与生成​

  1. 检索: 给定用户输入，使用Retriever从存储中检索相关的分割。
  2. 生成: 一个ChatModel / LLM 使用包含问题和检索到的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 笔记本​

本教程及其他教程或许在Jupyter notebooks中运行最为方便。在交互式环境中浏览指南是更好地理解它们的好方法。有关如何安装的说明，请参见这里。

安装​

本教程需要以下langchain依赖项：

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

更多详情，请参阅我们的安装指南。

LangSmith​

使用LangChain构建的许多应用程序将包含多个步骤，涉及多次LLM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。 实现这一点的最佳方法是使用LangSmith。

在您通过上述链接注册后，请确保设置您的环境变量以开始记录跟踪：

export LANGCHAIN_TRACING_V2="true"
export LANGCHAIN_API_KEY="..."

或者，如果在笔记本中，您可以通过以下方式设置它们：

import getpass
import os

os.environ["LANGCHAIN_TRACING_V2"] = "true"
os.environ["LANGCHAIN_API_KEY"] = getpass.getpass()

组件​

我们需要从LangChain的集成套件中选择三个组件。

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 ChatOpenAI

llm = ChatOpenAI(model="gpt-4o-mini")
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")
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，用于回答有关网站内容的问题。我们将使用的具体网站是Lilian Weng的LLM Powered Autonomous Agents博客文章，它允许我们就文章内容提出问题。

我们可以创建一个简单的索引管道和RAG链，用大约50行代码来完成这个任务。

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()
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 跟踪。

详细步骤​

让我们逐步浏览上述代码，以真正理解发生了什么。

1. 索引​

note

本节是语义搜索教程中内容的简略版本。 如果您已经熟悉文档加载器、嵌入和向量存储， 可以跳过本节，直接进入下一节关于检索与生成的内容。

加载文档​

我们需要首先加载博客文章内容。我们可以使用 DocumentLoaders 来实现这一点，这些对象从源中加载数据并返回一个 Document 对象的列表。

在这种情况下，我们将使用 WebBaseLoader， 它使用 urllib 从网页URL加载HTML，并使用 BeautifulSoup 将其解析为文本。我们可以通过 bs_kwargs 向 BeautifulSoup 解析器传递参数来自定义HTML -> 文本的解析（参见 BeautifulSoup 文档）。 在这种情况下，只有带有类“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 Reference: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

深入探讨​

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

  • Docs: 关于如何使用DocumentLoaders的详细文档。
  • Integrations: 160+ 集成可供选择。
  • Interface: API参考基础接口。

分割文档​

我们加载的文档超过42k字符，这对于许多模型的上下文窗口来说太长了。即使对于那些能够在其上下文窗口中容纳完整帖子的模型，模型在非常长的输入中寻找信息也可能会有困难。

为了处理这个问题，我们将把Document分成块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中最相关的部分。

正如在语义搜索教程中所述，我们使用了一个递归字符文本分割器，它将使用常见的分隔符（如换行符）递归地分割文档，直到每个块的大小合适。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.")
Split blog post into 66 sub-documents.

深入探讨​

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

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

  • Docs: 关于如何使用DocumentTransformers的详细文档
  • 集成
  • Interface: 基础接口的API参考。

存储文档​

现在我们需要索引我们的66个文本块，以便在运行时可以搜索它们。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。给定一个输入查询，我们可以使用向量搜索来检索相关文档。

我们可以在一个命令中嵌入并存储所有的文档分割，使用在教程开始时选择的向量存储和嵌入模型。

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']

深入探讨​

Embeddings: 文本嵌入模型的包装器，用于将文本转换为嵌入。

  • Docs: 关于如何使用嵌入的详细文档。
  • Integrations: 30多种集成可供选择。
  • Interface: 基础接口的API参考。

VectorStore: 向量数据库的包装器，用于存储和查询嵌入。

  • Docs: 关于如何使用向量存储的详细文档。
  • Integrations: 40+ 集成可供选择。
  • Interface: 基础接口的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分块内容。给定一个用户问题，理想情况下我们应该能够返回回答该问题的博客文章片段。

2. 检索与生成​

现在让我们编写实际的应用程序逻辑。我们希望创建一个简单的应用程序，该应用程序接收用户的问题，搜索与该问题相关的文档，将检索到的文档和初始问题传递给模型，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。

我们将使用一个用于RAG的提示，该提示已提交到LangChain提示中心 (这里)。

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 Reference: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将检索和生成步骤结合到一个单一应用程序中。这将带来许多好处：

  • 我们可以定义一次我们的应用逻辑，并自动支持多种调用模式，包括流式、异步和批量调用。
  • 我们通过LangGraph Platform获得简化的部署。
  • LangSmith 将自动追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：

  1. 我们应用程序的状态;
  2. 我们应用程序的节点（即应用程序步骤）；
  3. 我们应用程序的“控制流程”（例如，步骤的顺序）。

状态:​

我们应用程序的状态控制着输入到应用程序的数据、在步骤之间传输的数据以及应用程序输出的数据。它通常是一个TypedDict，但也可以是一个Pydantic BaseModel。

对于一个简单的RAG应用程序，我们只需要跟踪输入的问题、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 Reference:Document

节点（应用步骤）​

让我们从一个简单的两步序列开始：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}

我们的检索步骤简单地使用输入问题进行相似性搜索，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。

控制流程​

最后，我们将应用程序编译成一个单一的graph对象。在这种情况下，我们只是将检索和生成步骤连接成一个单一的序列。

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 Reference:StateGraph

LangGraph 还内置了用于可视化应用程序控制流的实用工具：

from IPython.display import Image, display

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

Do I need to use LangGraph?

构建RAG应用程序并不需要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：如果我们想要流式输出令牌，或者流式输出各个步骤的结果，这个逻辑需要重写；
  • 通过LangSmith自动支持追踪，并通过LangGraph Platform进行部署；
  • 支持持久化、人在回路和其他功能。

许多用例需要在对话体验中使用RAG，以便用户可以通过有状态的对话接收基于上下文的答案。正如我们将在教程的第2部分中看到的那样，LangGraph的状态管理和持久化极大地简化了这些应用程序。

用法​

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

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 tokens:

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|.||
tip

对于异步调用，请使用：

result = await graph.ainvoke(...)

和

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

返回源​

请注意，通过将检索到的上下文存储在图表的状态中，我们可以在状态的"context"字段中恢复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。

深入探讨​

Chat models 接收一系列消息并返回一条消息。

自定义提示

如上所示，我们可以从提示中心加载提示（例如，这个RAG提示）。提示也可以轻松定制。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 Reference: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。然而，允许模型生成查询以用于检索目的有一些优势。例如：

  • 除了语义搜索，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”）；
  • 该模型可以将用户查询重写为更有效的搜索查询，这些查询可能是多方面的或包含不相关的语言。

Query analysis 使用模型从原始用户输入中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集成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（人为设计的）部分，以便稍后进行过滤。

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'}

我们需要更新向量存储中的文档。我们将使用一个简单的InMemoryVectorStore，因为我们将使用它的一些特定功能（例如，元数据过滤）。请参考向量存储的集成文档以了解您选择的向量存储的相关功能。

from langchain_core.vectorstores import InMemoryVectorStore

vector_store = InMemoryVectorStore(embeddings)
_ = vector_store.add_documents(all_splits)
API Reference:InMemoryVectorStore

接下来，让我们为我们的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，我们定义了一个查询，包含一个字符串查询和一个文档部分（可以是“开始”、“中间”或“结束”），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，我们在LangGraph应用程序中添加一个步骤，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()
display(Image(graph.get_graph().draw_mermaid_png()))

我们可以通过特别要求从帖子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了不同的信息。

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输入到检索步骤的结构化查询。

查询分析是一个丰富的问题，有广泛的方法。请参考操作指南以获取更多示例。

下一步​

我们已经介绍了构建一个基于数据的基本问答应用的步骤：

在第二部分的教程中，我们将扩展这里的实现，以适应对话式交互和多步检索过程。

进一步阅读：

这个页面有帮助吗？