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，以便与大型语言模型工作流集成。它们对于需要获取数据并在模型推理过程中进行推理的应用至关重要，例如检索增强生成（RAG），或参见我们的 RAG 教程此处（RAG）。

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;
向量存储与检索器。

设置

Jupyter Notebook

此教程及其他教程最方便在 Jupyter notebook 中运行。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

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以及多次 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()

文档和文档加载器

LangChain 实现了一个文档抽象层，旨在表示一段文本及其关联的元数据。它包含三个属性：

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 属性可以捕获关于文档来源、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 参考:文档

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数据源集成。这使得将来自这些源的数据轻松整合到您的 AI 应用中变得非常容易。

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，点击这里 -- 这是耐克公司 2023 年的 10-K filings 文件。我们可以查阅 LangChain 文档以了解可用的 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 参考:PyPDFLoader

提示

有关 PDF 文档加载器的更多详细信息，请参见本指南。

PyPDFLoader loads one Document object per PDF page. For each, we can easily access:

该页面的字符串内容；
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任务而言，单个页面可能过于粗糙。我们的最终目标是检索Document个能够回答输入查询的对象，而进一步拆分我们的PDF文档将有助于确保相关部分的意义不会被周围文本“稀释”。

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。我们将文档拆分为每块1000个字符，且块与块之间保留200个字符的重叠部分。重叠部分有助于降低将某句话与其相关的重要上下文分离开来的可能性。我们使用RecursiveCharacterTextSplitter，它将通过常用的分隔符（如换行符）递归地分割文档，直到每个块的尺寸合适为止。这是针对通用文本用例推荐的文本分割器。

我们设置 add_start_index=True，以便每个拆分后的文档在初始文档中的起始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，请参阅此指南。

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:递归字符文本分割器

嵌入

向量搜索是一种存储和检索非结构化数据（如非结构化文本）的常用方法。其核心思想是存储与文本关联的数值向量。给定一个查询时，我们可以将其嵌入为相同维度的向量，并利用向量相似度度量（如余弦相似度）来识别相关的文本。

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]

借助用于生成文本嵌入的模型，我们可以将它们存储在一个支持高效相似度搜索的特殊数据结构中。

向量存储

LangChain 向量存储对象包含用于向存储中添加文本和Document对象的方法，并使用各种相似度指标对其进行查询。它们通常使用嵌入模型进行初始化，该模型决定如何将文本数据转换为数值向量。

LangChain 包含一套与不同向量存储技术集成的集成。某些向量存储由提供商托管（例如，各种云提供商），需要使用特定凭据；某些（如 Postgres）运行在独立的基础设施中，可在本地或通过第三方运行；其他则可以在内存中运行以支持轻量级工作负载。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)

在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。有关更多详细信息，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包含用于查询的方法：

同步和异步；
通过字符串查询和通过向量；
带和不带返回相似度分数；
通过相似性和最大边际相关性（以在检索结果中平衡与查询的相似性和多样性）。

这些方法在其输出中通常将包含一个 Document 对象列表。

用法

嵌入（Embeddings）通常将文本表示为“稠密”向量，使得含义相似的文本在几何上彼此接近。这使得我们只需传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度返回文档：

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 对象不继承自可运行（Runnable）。LangChain 检索器（Retrievers）是可运行的，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）。虽然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的数据源接口（例如外部 API）。

我们可以自己创建一个简单的版本，而无需子类化Retriever。如果我们选择希望使用哪种方法来检索文档，就可以轻松创建一个可运行对象。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:文档 |Chains

[[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')]]

Vectorstores 实现了一个 as_retriever 方法，该方法将生成一个 Retriever，具体为 VectorStoreRetriever。这些检索器包含特定的 search_type 和 search_kwargs 属性，用于标识应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，我们可以使用以下内容来复制上述操作：

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" 类型的搜索。我们可以使用最后一种类型，根据相似度分数对检索器输出的文档进行阈值过滤。

检索器可以轻松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，它将给定问题与检索到的上下文结合到 LLM 的提示中。若要了解如何构建此类应用程序，请查看RAG 教程。

了解更多:

检索策略可以丰富而复杂。例如：

我们可以从查询中推断出硬规则和过滤器（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，通过某种文档分类法）与检索到的上下文相关联的文档；
我们可以为每个上下文单元生成多个嵌入；
我们可以集成来自多个检索器的结果；
我们可以为文档分配权重，例如，使近期文档具有更高的权重。

《指南》中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同样简单明了。请参阅我们的操操作指南此处。

下一步

您现在已了解如何为 PDF 文档构建语义搜索引擎。

有关文档加载器的更多信息：

关于嵌入的更多信息：

关于向量存储的更多信息：

关于 RAG 的更多信息，请查看：

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​

用法​

检索器​

了解更多:​

下一步​

概念

设置