构建语义搜索引擎

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进行推理的应用程序非常重要，例如检索增强生成（RAG）（请参阅我们的RAG教程此处）。

在这里，我们将在PDF文档上构建一个搜索引擎。这将使我们能够检索PDF中与输入查询相似的段落。

概念

本指南侧重于文本数据的检索。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 Notebook

本教程和其他教程或许在Jupyter Notebook中运行最为方便。有关如何安装的说明，请参见此处。

安装

本教程需要 langchain-community 和 pypdf 软件包

Pip
Conda

pip install langchain-community pypdf

conda install langchain-community pypdf -c conda-forge

更多详情，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，并多次调用LLM。随着这些应用程序变得越来越复杂，检查您的链或代理内部究竟发生了什么是至关重要的。做到这一点的最佳方式是使用LangSmith。

在上述链接注册后，请务必设置您的环境变量以开始记录跟踪日志

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

或者，如果在Notebook中，您可以这样设置

import getpass
import os

os.environ["LANGSMITH_TRACING"] = "true"
os.environ["LANGSMITH_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元数据。它有三个属性

page_content：表示内容的字符串；
metadata：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、其与其他文档的关系以及其他信息。请注意，单个 Document 对象通常代表一个更大文档的片段。

我们可以根据需要生成示例文档

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 参考：Document

然而，LangChain生态系统实现了文档加载器，可与数百种常见来源集成。这使得将这些来源的数据轻松集成到您的AI应用程序中变得简单。

加载文档

让我们将一个PDF文件加载到一系列 Document 对象中。LangChain仓库中有一个示例文档PDF此处——一份2023年耐克的10-k文件。我们可以查阅LangChain文档，了解可用的PDF文档加载器。让我们选择PyPDFLoader，它相当轻量。

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 参考：PyPDFLoader

提示

有关PDF文档加载器的更多详情，请参阅本指南。

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

无论是为了信息检索还是下游的问答目的，一个页面可能都是一个过于粗粒度的表示。我们最终的目标是检索能够回答输入查询的 Document 对象，进一步分割PDF将有助于确保文档中相关部分的含义不会被周围文本“冲淡”。

为此，我们可以使用文本分割器。这里我们将使用一个简单的文本分割器，它根据字符进行分割。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。重叠有助于减少将语句与其重要上下文分离的可能性。我们使用RecursiveCharacterTextSplitter，它将使用换行符等常见分隔符递归分割文档，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，以便每个分割后的Document在原始Document中开始的字符索引作为元数据属性“start_index”被保留。

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，请参阅本指南。

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)

API 参考：RecursiveCharacterTextSplitter

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）的常用方法。其思想是存储与文本关联的数值向量。给定一个查询，我们可以将其嵌入为相同维度的向量，并使用向量相似性度量（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值向量。让我们选择一个模型

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")

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]

有了用于生成文本嵌入的模型，我们接下来可以将其存储在支持高效相似性搜索的特殊数据结构中。

向量存储

LangChain VectorStore 对象包含将文本和 Document 对象添加到存储库以及使用各种相似性度量查询它们的方法。它们通常使用嵌入模型进行初始化，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集成的集成。一些向量存储由提供商（例如，各种云提供商）托管，需要特定的凭据才能使用；一些（例如Postgres）在可以本地运行或通过第三方运行的独立基础设施中运行；其他则可以在内存中运行，用于轻量级工作负载。让我们选择一个向量存储

选择向量存储

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，我们现在可以对文档进行索引。

ids = vector_store.add_documents(documents=all_splits)

请注意，大多数向量存储实现都允许您连接到现有向量存储——例如，通过提供客户端、索引名称或其他信息。更多详情请参阅特定集成的文档。

一旦我们实例化了一个 VectorStore，其中包含文档，我们就可以查询它。VectorStore 包含了查询方法，支持

同步和异步；
通过字符串查询和通过向量查询；
返回或不返回相似度分数；
通过相似度和最大边际相关性（以平衡查询相似性和检索结果的多样性）。

这些方法通常会在其输出中包含一个Document对象列表。

使用

嵌入通常将文本表示为“密集”向量，使得含义相似的文本在几何上接近。这使我们只需输入一个问题，即可检索相关信息，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的 VectorStore 对象不继承自 Runnable。LangChain的检索器（Retrievers）是Runnable，因此它们实现了一套标准方法（例如，同步和异步的 invoke 和 batch 操作）。尽管我们可以从向量存储构建检索器，但检索器也可以与非向量存储数据源（例如外部API）进行交互。

我们可以自己创建一个简单的版本，而无需继承 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（runnable）对象。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 参考：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 as_retriever 方法，该方法将生成一个检索器（Retriever），特别是VectorStoreRetriever。这些检索器包含特定的 search_type 和 search_kwargs 属性，用于标识要调用底层向量存储的哪些方法以及如何对其进行参数化。例如，我们可以用以下方式复制上述操作

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

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

了解更多：

检索策略可以丰富且复杂。例如

我们可以从查询中推断出硬性规则和过滤器（例如，“使用2020年后发布的文档”）；
我们可以返回以某种方式（例如，通过某种文档分类）与检索到的上下文链接的文档；
我们可以为每个上下文单元生成多个嵌入；
我们可以整合来自多个检索器的结果；
我们可以为文档分配权重，例如，给予最新文档更高的权重。

操作指南的检索器部分涵盖了这些和其他内置的检索策略。

扩展 BaseRetriever 类以实现自定义检索器也很简单。请参阅我们的操作指南此处。

下一步

您现在已经了解了如何在PDF文档上构建语义搜索引擎。

更多关于文档加载器

更多关于嵌入

更多关于向量存储

更多关于RAG，请参见

概念​

设置​

Jupyter Notebook​

安装​

LangSmith​

文档和文档加载器​

加载文档​

分割​

嵌入​

向量存储​

使用​

检索器​

了解更多：​

下一步​

概念

设置