构建检索增强生成 (RAG) 应用：第一部分

由大型语言模型（LLM）支持的最强大应用之一是复杂的问答（Q&A）聊天机器人。这些应用能够针对特定的源信息回答问题。这类应用采用了一种称为检索增强生成（Retrieval Augmented Generation）的技术，简称 RAG。

这是一个多部分教程：

第 1 部分（本指南）介绍 RAG 并逐步演示一个最小化实现。
第2部分扩展了实现，以支持对话式交互和多步检索流程。

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程序。在此过程中，我们将介绍典型的问答架构，并突出更多高级问答技术的附加资源。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。随着应用程序复杂性的增加，LangSmith 将变得越来越有帮助。

如果您已经熟悉基本的检索，您可能也会对此不同检索技术的高级概述感兴趣。

注意: 此处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，了解如何对 SQL 数据进行问答。

概览

典型的 RAG 应用有两个主要组件：

索引：一个用于从源摄取数据并对其进行索引的管道。这通常是在离线状态下进行的。

检索与生成：实际的 RAG 链，它在运行时接收用户查询，从索引中检索相关数据，然后将这些数据传递给模型。

注意：本教程的索引部分将主要遵循语义搜索教程。

从原始数据到答案最常见的完整序列如下：

索引

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。
分割: 文本分割器将大型 Documents 拆分为更小的块。这对于数据索引和将其传递给模型都非常有用，因为大块数据更难搜索且无法放入模型的有限上下文窗口中。
存储: 我们需要一个地方来存储和索引我们的数据分片，以便日后可以对其进行搜索。这通常使用向量存储和嵌入模型来完成。

index_diagram

检索与生成

检索: 给定用户输入，使用检索器从存储中检索相关的分块。
生成:一个ChatModel/LLM使用包含问题与检索数据的提示来生成答案

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

本教程及其他教程最方便在 Jupyter notebooks 中运行。在交互式环境中逐步学习指南是更好地理解它们的绝佳方式。有关安装说明，请参阅此处。

安装

本教程需要以下 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

使用 LangChain 构建的许多应用程序将包含多个步骤，并多次调用 LLM。随着这些应用程序变得越来越复杂，能够检查您的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式是使用 LangSmith。

在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追踪：

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

或者，如果在笔记本中，您可以这样设置：

import getpass
import os

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

组件

我们需要从 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，用于回答有关网站内容的问题。我们将使用的特定网站是 Lilian Weng 撰写的 LLM 驱动的自主代理博客文章，它允许我们针对该文章的内容提问。

我们可以创建一个简单的索引管道和 RAG 链，仅用约 50 行代码即可完成此操作。

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:中心 |WebBaseLoader |文档 |递归字符文本分割器 |状态图

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。

详细分步指南

让我们逐步分析上面的代码，以真正理解其工作原理。

1. 索引

注意

本节是语义搜索教程中内容的缩写版本。如果您熟悉文档加载器、嵌入模型和向量存储，欢迎直接跳转到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帖子的内容。我们可以使用 DocumentLoaders 来实现这一点，它们是用于从源加载数据并返回 list of Document 对象的对象。

在此情况下，我们将使用 WebBaseLoader，它使用 urllib 从网络 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给 BeautifulSoup 解析器来自定义 HTML -> 文本的解析过程，具体做法是通过 bs_kwargs（参见 BeautifulSoup 文档）。在此情况下，只有类为“post-content

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

深入探索

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

文档: 关于如何使用 DocumentLoaders 的详细文档。
集成: 160+ 种可供选择的集成。
接口: 基础接口的 API 参考。

拆分文档

我们加载的文档超过 42k 字符，对于许多模型而言，其长度超出了上下文窗口的承载范围。即使对于那些能够将整篇帖子容纳在上下文窗口中的模型，在处理如此长的输入时，模型也可能难以定位所需信息。

为了处理这个问题，我们将把 Document 分割成块以进行嵌入和向量存储。这有助于我们在运行时仅检索博客文章中最相关的部分。

与语义搜索教程中一样，我们使用 RecursiveCharacterTextSplitter（递归字符文本分割器），它将通过常见的分隔符（如换行符）递归地分割文档，直到每个分块达到合适的尺寸。这是用于通用文本用例的推荐文本分割器。

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:递归字符文本分割器

Split blog post into 66 sub-documents.

深入探索

TextSplitter: 将 Documents 列表拆分为较小块的对象。是 DocumentTransformers 的子类。

通过阅读操操作指南文档，了解更多关于使用不同方法分割文本的内容。
代码 (py 或 js)
科学论文
接口: 基础接口的 API 参考。

DocumentTransformer: 对列表中的 Document 个对象执行转换的对象。

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，以便在运行时能够搜索它们。遵循语义搜索教程，我们的方法是将每个文档切片的內容进行嵌入，并将这些嵌入插入到向量存储中。给定一个输入查询后，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头选择的向量存储和嵌入模型，通过一条命令嵌入并存储我们所有的文档分片。

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']

深入探索

Embeddings: 文本嵌入模型的包装器，用于将文本转换为嵌入向量。

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

VectorStore: 围绕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+ 种可供选择的集成。
接口: 基础接口的 API 参考。

这完成了管道的索引部分。此时，我们拥有一个可查询的向量存储库，其中包含我们博客文章的分块内容。给定用户的问题，我们理想情况下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逻辑。我们要创建一个简单的应用程序，该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。

我们将使用一个已提交到 LangChain prompt hub 的 RAG 提示词 (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 参考:中心枢纽

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 将检索和生成步骤整合到一个单一的应用程序中。这将带来诸多优势：

我们可以定义一次应用逻辑，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 Platform 实现 streamlined 部署。
LangSmith 将自动追踪我们应用程序的步骤。
我们可以轻松地为我们的应用程序添加关键功能，包括持久化和人工介入审批，且只需极少的代码更改。

要使用 LangGraph，我们需要定义三件事：

我们应用程序的状态；
我们应用的节点（即应用步骤）；
我们应用程序的"控制流"（例如，步骤的顺序）。

状态:

应用程序的状态控制输入到应用程序的数据、在步骤之间传输的数据以及由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，我们只需跟踪输入问题、检索到的上下文以及生成的答案：

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:文档

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}

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

控制流

最后，我们将应用程序编译为单个 graph 对象。在此情况下，我们只是将检索和生成步骤连接成一个单一序列。

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:状态图

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()))

我需要不使用 LangGraph 吗？

LangGraph 并非构建 RAG（检索增强生成）应用的必需组件。事实上，我们可以通过调用各个独立组件来实现相同的应用逻辑：

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 的优势包括：

支持多种调用模式：如果我们想要流式输出令牌，或流式输出各个步骤的结果，则此逻辑需要重写；
自动支持通过 LangSmith 进行追踪，以及通过 LangGraph Platform 进行部署；
支持持久化、人工介入循环以及其他功能。

许多应用场景需要在对话体验中实现 RAG，以便用户能够通过有状态的对话接收基于上下文的回答。正如我们将在教程的第 2 部分中看到的那样，LangGraph 对状态的管理和持久化极大地简化了这些应用。

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，请参阅此指南。

深入探索

聊天模型接收一系列消息并返回一条消息。

文档
集成: 25+ 种可供选择的集成。
接口: 基础接口的 API 参考。

自定义提示词

如上所示，我们可以从提示词中心加载提示词（例如：此 RAG 提示词）。提示词也可以轻松自定义。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:提示模板

查询分析

到目前为止，我们一直使用原始输入查询执行检索。然而，允许模型为检索目的生成查询存在一些优势。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（这些查询可能涉及多个方面或包含无关语言）重写为更有效的搜索查询。

查询分析利用模型将原始用户输入转换或构建为优化的搜索查询。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（虚构的）部分，以便稍后对其进行过滤。

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。我们将为此使用一个简单的 InMemoryVectorStore，因为我们会用到它的一些特定功能（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:内存向量存储

让我们接下来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。在此，我们定义一个查询包含一个字符串查询和一个文档部分（可以是"beginning"、"middle"或"end"），但您可以根据需要自由定义。

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，我们为我们的 LangGraph 应用程序添加了一个步骤，用于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()))

我们可以通过明确要求从帖子末尾获取上下文来测试我们的实现。注意，模型在其回答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 追踪中，我们现在可以观察到被送入检索步骤的结构化查询。

查询分析是一个内容丰富的问题，有多种方法。请参考操操作指南获取更多示例。

下一步

我们已经介绍了如何构建基于数据的简单问答应用：

使用文档加载器加载数据
通过文本分割器对索引数据进行分块处理，使其更易于被模型使用
嵌入数据并将数据存储到向量存储中
检索之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。

在教程的第二部分中，我们将扩展此处实现以支持对话式交互和多步检索流程。

进一步阅读：

返回来源: 了解如何返回源文档
流式传输: 了解如何流式输出和中间步骤
添加聊天历史: 了解如何将聊天历史添加到您的应用中
检索概念指南: 特定检索技术的高级概述

概览​

索引​

检索与生成​

设置​

Jupyter Notebook​

安装​

LangSmith​

组件​

预览​

详细分步指南​

1. 索引​

加载文档​

深入探索​

拆分文档​

深入探索​

存储文档​

深入探索​

2. 检索与生成​

状态:​

节点（应用步骤）​

控制流​

用法​

返回来源​

深入探索​

查询分析​

下一步​

概览

索引

检索与生成

设置

Jupyter Notebook

安装

LangSmith

组件

预览

详细分步指南

1. 索引

加载文档

深入探索

拆分文档

深入探索

存储文档

深入探索

2. 检索与生成

状态:

节点（应用步骤）

控制流

用法

返回来源

深入探索

查询分析

下一步