Skip to main content
Open In ColabOpen on GitHub

构建一个语义搜索引擎

本教程将帮助您熟悉LangChain的文档加载器、嵌入和向量存储抽象。这些抽象旨在支持从（向量）数据库和其他来源检索数据，以便与LLM工作流集成。它们对于在模型推理过程中获取数据以进行推理的应用程序非常重要，例如在检索增强生成或RAG的情况下（请参阅我们的RAG教程这里）。

在这里，我们将构建一个基于PDF文档的搜索引擎。这将使我们能够检索与输入查询相似的PDF段落。

概念​

本指南专注于文本数据的检索。我们将涵盖以下概念：

  • 文档和文档加载器;
  • 文本分割器;
  • 嵌入;
  • 向量存储和检索器。

设置​

Jupyter 笔记本​

本教程及其他教程或许在Jupyter笔记本中运行最为方便。有关如何安装的说明，请参见这里。

安装​

本教程需要langchain-community和pypdf包：

pip install langchain-community pypdf

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()

文档和文档加载器​

LangChain 实现了一个 Document 抽象，旨在表示一个文本单元及其相关的元数据。它有三个属性：

  • page_content: 表示内容的字符串;
  • metadata: 一个包含任意元数据的字典;
  • id: （可选）文档的字符串标识符。

metadata 属性可以捕获有关文档来源的信息、它与其他文档的关系以及其他信息。请注意，单个 Document 对象通常表示较大文档的一部分。

我们可以在需要时生成示例文档：

from langchain_core.documents import Document

documents = [
    Document(
        page_content="Dogs are great companions, known for their loyalty and friendliness.",
        metadata={"source": "mammal-pets-doc"},
    ),
    Document(
        page_content="Cats are independent pets that often enjoy their own space.",
        metadata={"source": "mammal-pets-doc"},
    ),
]
API Reference:Document

然而，LangChain生态系统实现了文档加载器，这些加载器与数百种常见来源集成。这使得将这些来源的数据整合到您的AI应用程序中变得非常容易。

加载文档​

让我们将一个PDF加载到一系列Document对象中。LangChain仓库中有一个示例PDF这里 -- 2023年耐克的10-k文件。我们可以查阅LangChain文档中的可用的PDF文档加载器。让我们选择PyPDFLoader，它相当轻量级。

from langchain_community.document_loaders import PyPDFLoader

file_path = "../example_data/nke-10k-2023.pdf"
loader = PyPDFLoader(file_path)

docs = loader.load()

print(len(docs))
API Reference:PyPDFLoader
107
tip

查看本指南以获取有关PDF文档加载器的更多详细信息。

PyPDFLoader 为每个PDF页面加载一个Document对象。对于每个对象，我们可以轻松访问：

  • 页面的字符串内容;
  • 包含文件名和页码的元数据。
print(f"{docs[0].page_content[:200]}\n")
print(docs[0].metadata)
Table of Contents
UNITED STATES
SECURITIES AND EXCHANGE COMMISSION
Washington, D.C. 20549
FORM 10-K
(Mark One)
☑ ANNUAL REPORT PURSUANT TO SECTION 13 OR 15(D) OF THE SECURITIES EXCHANGE ACT OF 1934
FO

{'source': '../example_data/nke-10k-2023.pdf', 'page': 0}

分割​

对于信息检索和下游问答目的，页面可能是一个过于粗糙的表示。我们的最终目标是检索能够回答输入查询的Document对象，进一步拆分我们的PDF将有助于确保文档相关部分的含义不会被周围的文本“冲淡”。

我们可以使用文本分割器来实现这一目的。这里我们将使用一个简单的基于字符的文本分割器。我们将把文档分割成1000个字符的块，块之间有200个字符的重叠。这种重叠有助于减少将语句与其相关的重要上下文分离的可能性。我们使用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，直到每个块达到适当的大小。这是通用文本用例推荐的文本分割器。

我们设置add_start_index=True，以便将每个分割文档在初始文档中开始的字符索引保留为元数据属性“start_index”。

请参阅本指南以获取有关处理PDF的更多详细信息，包括如何从特定部分和图像中提取文本。

from langchain_text_splitters import RecursiveCharacterTextSplitter

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

len(all_splits)
514

嵌入​

向量搜索是存储和搜索非结构化数据（如非结构化文本）的常见方法。其思想是存储与文本相关联的数字向量。给定一个查询，我们可以嵌入它作为相同维度的向量，并使用向量相似度度量（如余弦相似度）来识别相关文本。

LangChain 支持来自数十个提供商的嵌入。这些模型指定了如何将文本转换为数字向量。让我们选择一个模型：

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")
vector_1 = embeddings.embed_query(all_splits[0].page_content)
vector_2 = embeddings.embed_query(all_splits[1].page_content)

assert len(vector_1) == len(vector_2)
print(f"Generated vectors of length {len(vector_1)}\n")
print(vector_1[:10])
Generated vectors of length 1536

[-0.008586574345827103, -0.03341241180896759, -0.008936782367527485, -0.0036674530711025, 0.010564599186182022, 0.009598285891115665, -0.028587326407432556, -0.015824200585484505, 0.0030416189692914486, -0.012899317778646946]

有了生成文本嵌入的模型，我们接下来可以将它们存储在一种特殊的数据结构中，这种结构支持高效的相似性搜索。

向量存储​

LangChain VectorStore 对象包含将文本和 Document 对象添加到存储中的方法，并使用各种相似性度量进行查询。它们通常使用 embedding 模型进行初始化，这些模型决定了文本数据如何转换为数值向量。

LangChain 包含一套与不同向量存储技术的集成。一些向量存储由提供商托管（例如，各种云提供商），并且需要使用特定的凭据；一些（如Postgres）运行在可以本地或通过第三方运行的独立基础设施中；其他一些可以运行在内存中，适用于轻量级工作负载。让我们选择一个向量存储：

pip install -qU langchain-core
from langchain_core.vectorstores import InMemoryVectorStore

vector_store = InMemoryVectorStore(embeddings)

实例化我们的向量存储后，我们现在可以索引文档。

ids = vector_store.add_documents(documents=all_splits)

请注意，大多数向量存储实现将允许您连接到现有的向量存储——例如，通过提供客户端、索引名称或其他信息。有关详细信息，请参阅特定集成的文档。

一旦我们实例化了一个包含文档的VectorStore，我们就可以查询它。VectorStore 包含了查询的方法：

  • 同步和异步;
  • 通过字符串查询和向量；
  • 带和不带返回相似度分数；
  • 通过相似性和最大边际相关性（以平衡查询的相似性与检索结果的多样性）。

这些方法通常会在其输出中包含一个Document对象的列表。

用法​

嵌入通常将文本表示为“密集”向量，使得具有相似含义的文本在几何上接近。这使我们能够仅通过传递一个问题来检索相关信息，而无需了解文档中使用的任何特定关键词。

根据与字符串查询的相似性返回文档：

results = vector_store.similarity_search(
    "How many distribution centers does Nike have in the US?"
)

print(results[0])
page_content='direct to consumer operations sell products through the following number of retail stores in the United States:
U.S. RETAIL STORES NUMBER
NIKE Brand factory stores 213 
NIKE Brand in-line stores (including employee-only stores) 74 
Converse stores (including factory stores) 82 
TOTAL 369 
In the United States, NIKE has eight significant distribution centers. Refer to Item 2. Properties for further information.
2023 FORM 10-K 2' metadata={'page': 4, 'source': '../example_data/nke-10k-2023.pdf', 'start_index': 3125}

异步查询：

results = await vector_store.asimilarity_search("When was Nike incorporated?")

print(results[0])
page_content='Table of Contents
PART I
ITEM 1. BUSINESS
GENERAL
NIKE, Inc. was incorporated in 1967 under the laws of the State of Oregon. As used in this Annual Report on Form 10-K (this "Annual Report"), the terms "we," "us," "our,"
"NIKE" and the "Company" refer to NIKE, Inc. and its predecessors, subsidiaries and affiliates, collectively, unless the context indicates otherwise.
Our principal business activity is the design, development and worldwide marketing and selling of athletic footwear, apparel, equipment, accessories and services. NIKE is
the largest seller of athletic footwear and apparel in the world. We sell our products through NIKE Direct operations, which are comprised of both NIKE-owned retail stores
and sales through our digital platforms (also referred to as "NIKE Brand Digital"), to retail accounts and to a mix of independent distributors, licensees and sales' metadata={'page': 3, 'source': '../example_data/nke-10k-2023.pdf', 'start_index': 0}

返回分数：

# Note that providers implement different scores; the score here
# is a distance metric that varies inversely with similarity.

results = vector_store.similarity_search_with_score("What was Nike's revenue in 2023?")
doc, score = results[0]
print(f"Score: {score}\n")
print(doc)
Score: 0.23699893057346344

page_content='Table of Contents
FISCAL 2023 NIKE BRAND REVENUE HIGHLIGHTS
The following tables present NIKE Brand revenues disaggregated by reportable operating segment, distribution channel and major product line:
FISCAL 2023 COMPARED TO FISCAL 2022
•NIKE, Inc. Revenues were $51.2 billion in fiscal 2023, which increased 10% and 16% compared to fiscal 2022 on a reported and currency-neutral basis, respectively.
The increase was due to higher revenues in North America, Europe, Middle East & Africa ("EMEA"), APLA and Greater China, which contributed approximately 7, 6,
2 and 1 percentage points to NIKE, Inc. Revenues, respectively.
•NIKE Brand revenues, which represented over 90% of NIKE, Inc. Revenues, increased 10% and 16% on a reported and currency-neutral basis, respectively. This
increase was primarily due to higher revenues in Men's, the Jordan Brand, Women's and Kids' which grew 17%, 35%,11% and 10%, respectively, on a wholesale
equivalent basis.' metadata={'page': 35, 'source': '../example_data/nke-10k-2023.pdf', 'start_index': 0}

根据与嵌入查询的相似性返回文档：

embedding = embeddings.embed_query("How were Nike's margins impacted in 2023?")

results = vector_store.similarity_search_by_vector(embedding)
print(results[0])
page_content='Table of Contents
GROSS MARGIN
FISCAL 2023 COMPARED TO FISCAL 2022
For fiscal 2023, our consolidated gross profit increased 4% to $22,292 million compared to $21,479 million for fiscal 2022. Gross margin decreased 250 basis points to
43.5% for fiscal 2023 compared to 46.0% for fiscal 2022 due to the following:
*Wholesale equivalent
The decrease in gross margin for fiscal 2023 was primarily due to:
•Higher NIKE Brand product costs, on a wholesale equivalent basis, primarily due to higher input costs and elevated inbound freight and logistics costs as well as
product mix;
•Lower margin in our NIKE Direct business, driven by higher promotional activity to liquidate inventory in the current period compared to lower promotional activity in
the prior period resulting from lower available inventory supply;
•Unfavorable changes in net foreign currency exchange rates, including hedges; and
•Lower off-price margin, on a wholesale equivalent basis.
This was partially offset by:' metadata={'page': 36, 'source': '../example_data/nke-10k-2023.pdf', 'start_index': 0}

了解更多：

检索器​

LangChain VectorStore 对象不继承 Runnable。LangChain Retrievers 是 Runnables，因此它们实现了一组标准方法（例如，同步和异步的 invoke 和 batch 操作）。虽然我们可以从向量存储中构建检索器，但检索器也可以与非向量存储的数据源（如外部API）进行交互。

我们可以自己创建一个简单的版本，而不需要子类化Retriever。如果我们选择希望用于检索文档的方法，我们可以轻松创建一个可运行的实例。下面我们将围绕similarity_search方法构建一个：

from typing import List

from langchain_core.documents import Document
from langchain_core.runnables import chain


@chain
def retriever(query: str) -> List[Document]:
    return vector_store.similarity_search(query, k=1)


retriever.batch(
    [
        "How many distribution centers does Nike have in the US?",
        "When was Nike incorporated?",
    ],
)
API Reference:Document | chain
[[Document(metadata={'page': 4, 'source': '../example_data/nke-10k-2023.pdf', 'start_index': 3125}, page_content='direct to consumer operations sell products through the following number of retail stores in the United States:\nU.S. RETAIL STORES NUMBER\nNIKE Brand factory stores 213 \nNIKE Brand in-line stores (including employee-only stores) 74 \nConverse stores (including factory stores) 82 \nTOTAL 369 \nIn the United States, NIKE has eight significant distribution centers. Refer to Item 2. Properties for further information.\n2023 FORM 10-K 2')],
 [Document(metadata={'page': 3, 'source': '../example_data/nke-10k-2023.pdf', 'start_index': 0}, page_content='Table of Contents\nPART I\nITEM 1. BUSINESS\nGENERAL\nNIKE, Inc. was incorporated in 1967 under the laws of the State of Oregon. As used in this Annual Report on Form 10-K (this "Annual Report"), the terms "we," "us," "our,"\n"NIKE" and the "Company" refer to NIKE, Inc. and its predecessors, subsidiaries and affiliates, collectively, unless the context indicates otherwise.\nOur principal business activity is the design, development and worldwide marketing and selling of athletic footwear, apparel, equipment, accessories and services. NIKE is\nthe largest seller of athletic footwear and apparel in the world. We sell our products through NIKE Direct operations, which are comprised of both NIKE-owned retail stores\nand sales through our digital platforms (also referred to as "NIKE Brand Digital"), to retail accounts and to a mix of independent distributors, licensees and sales')]]

向量存储实现了一个as_retriever方法，该方法将生成一个检索器，具体来说是一个VectorStoreRetriever。这些检索器包括特定的search_type和search_kwargs属性，用于标识要调用的底层向量存储的方法以及如何对其进行参数化。例如，我们可以通过以下方式复制上述内容：

retriever = vector_store.as_retriever(
    search_type="similarity",
    search_kwargs={"k": 1},
)

retriever.batch(
    [
        "How many distribution centers does Nike have in the US?",
        "When was Nike incorporated?",
    ],
)
[[Document(metadata={'page': 4, 'source': '../example_data/nke-10k-2023.pdf', 'start_index': 3125}, page_content='direct to consumer operations sell products through the following number of retail stores in the United States:\nU.S. RETAIL STORES NUMBER\nNIKE Brand factory stores 213 \nNIKE Brand in-line stores (including employee-only stores) 74 \nConverse stores (including factory stores) 82 \nTOTAL 369 \nIn the United States, NIKE has eight significant distribution centers. Refer to Item 2. Properties for further information.\n2023 FORM 10-K 2')],
 [Document(metadata={'page': 3, 'source': '../example_data/nke-10k-2023.pdf', 'start_index': 0}, page_content='Table of Contents\nPART I\nITEM 1. BUSINESS\nGENERAL\nNIKE, Inc. was incorporated in 1967 under the laws of the State of Oregon. As used in this Annual Report on Form 10-K (this "Annual Report"), the terms "we," "us," "our,"\n"NIKE" and the "Company" refer to NIKE, Inc. and its predecessors, subsidiaries and affiliates, collectively, unless the context indicates otherwise.\nOur principal business activity is the design, development and worldwide marketing and selling of athletic footwear, apparel, equipment, accessories and services. NIKE is\nthe largest seller of athletic footwear and apparel in the world. We sell our products through NIKE Direct operations, which are comprised of both NIKE-owned retail stores\nand sales through our digital platforms (also referred to as "NIKE Brand Digital"), to retail accounts and to a mix of independent distributors, licensees and sales')]]

VectorStoreRetriever 支持搜索类型 "similarity"（默认）、"mmr"（最大边际相关性，如上所述）和 "similarity_score_threshold"。我们可以使用后者来根据相似度分数对检索器输出的文档进行阈值筛选。

检索器可以轻松地集成到更复杂的应用程序中，例如检索增强生成（RAG）应用程序，这些应用程序将给定问题与检索到的上下文结合到LLM的提示中。要了解更多关于构建此类应用程序的信息，请查看RAG教程教程。

了解更多:​

检索策略可以非常丰富和复杂。例如：

操作指南中的retrievers部分涵盖了这些以及其他内置的检索策略。

扩展BaseRetriever类以实现自定义检索器也非常简单。请参阅我们的操作指南这里。

下一步​

你现在已经看到了如何在一个PDF文档上构建一个语义搜索引擎。

有关文档加载器的更多信息：

有关嵌入的更多信息：

有关向量存储的更多信息：

有关RAG的更多信息，请参阅：

这个页面有帮助吗？