构建语义搜索引擎
本教程将使您熟悉 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 工作流程集成。它们对于获取数据以便在模型推理中进行推理的应用程序非常重要,例如检索增强生成或RAG(请参阅我们的 RAG 教程此处)。
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 PDF 中与输入查询相似的段落。
概念
本指南侧重于检索文本数据。我们将涵盖以下概念
- 文档和文档加载器;
- 文本拆分器;
- 嵌入;
- 向量存储和检索器。
设置
Jupyter Notebook
本教程和其他教程在 Jupyter notebook 中运行可能最为方便。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
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
你使用 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,能够检查你的链或代理内部到底发生了什么变得至关重要。最好的方法是使用 LangSmith。
在上面的链接注册后,请确保设置你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,你可以使用以下方式设置它们:
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 Document 抽象,旨在表示一段文本和相关的元数据。它具有三个属性:
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、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"},
),
]
然而,LangChain 生态系统实现了 文档加载器,这些加载器 与数百个常见来源集成。这使得将来自这些来源的数据纳入你的 AI 应用程序变得容易。
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,是 Nike 2023 年的 10-k 备案文件。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))
107
有关 PDF 文档加载器的更多详细信息,请参阅 本指南。
PyPDFLoader
为每个 PDF 页面加载一个 Document
对象。对于每一个,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}
拆分
对于信息检索和下游问答目的,页面可能过于粗糙。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 文本拆分器 来实现此目的。在这里,我们将使用一个简单的文本拆分器,它基于字符进行分区。我们将文档拆分为 1000 个字符的块,块之间有 200 个字符的重叠。重叠有助于减轻将语句与其相关的重要上下文分离的可能性。我们使用 RecursiveCharacterTextSplitter,它将递归地使用常见的分隔符(如换行符)拆分文档,直到每个块都达到适当的大小。这是通用文本用例的推荐文本拆分器。
我们设置 add_start_index=True
,以便在初始文档中每个拆分文档开始处的字符索引被保留为元数据属性“start_index”。
有关使用 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)
514
嵌入
向量搜索是一种存储和搜索非结构化数据(例如非结构化文本)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(例如余弦相似度)来识别相关文本。
LangChain 支持来自 数十家提供商 的嵌入。这些模型指定文本应如何转换为数值向量。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]
有了用于生成文本嵌入的模型,接下来我们可以将它们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 对象包含用于向存储中添加文本和 Document
对象的方法,以及使用各种相似性度量来查询它们的方法。它们通常使用 嵌入 模型初始化,这些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 的组件。一些向量存储由提供商托管(例如,各种云提供商),需要特定的凭据才能使用;一些(例如 Postgres)在单独的基础设施中运行,可以在本地或通过第三方运行;其他一些可以为轻量级工作负载在内存中运行。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你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 包括用于查询的方法:
- 同步和异步;
- 按字符串查询和按向量查询;
- 返回和不返回相似度分数;
- 按相似度和 最大边际相关性(以平衡与查询的相似性,从而在检索结果中实现多样性)。
这些方法通常在其输出中包含一个 Document 对象列表。
用法
嵌入通常将文本表示为“密集”向量,这样,具有相似含义的文本在几何上是接近的。这使我们只需传入一个问题就可以检索相关信息,而无需了解文档中使用的任何特定关键字。
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
对象不是 Runnable 的子类。LangChain Retrievers 是 Runnables,因此它们实现了一组标准方法(例如,同步和异步 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)接口。
我们可以在不继承 Retriever
的情况下自己创建一个简单的版本。如果我们选择希望用来检索文档的方法,我们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?",
],
)
[[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,特别是 VectorStoreRetriever。这些检索器包括特定的 search_type
和 search_kwargs
属性,这些属性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,我们可以使用以下方法复制上述内容:
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 "similarity"
(默认)、"mmr"
(最大边际相关性,如上所述)和 "similarity_score_threshold"
的搜索类型。我们可以使用后者通过相似性分数来阈值化检索器输出的文档。
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组合到 LLM 提示中的 检索增强生成 (RAG) 应用程序。要了解有关构建此类应用程序的更多信息,请查看 RAG 教程。
了解更多:
检索策略可能非常丰富和复杂。例如:
- 我们可以从查询中 推断硬规则和过滤器(例如,“使用 2020 年之后发布的文档”);
- 我们可以 返回以某种方式链接到 检索到的上下文的文档(例如,通过某些文档分类法);
- 我们可以为每个上下文单元生成 多个嵌入;
- 我们可以从多个检索器 集成结果;
- 我们可以为文档分配权重,例如,对 最近的文档 进行更高的加权。
操作指南的 检索器 部分涵盖了这些和其他内置检索策略。
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 这里。
下一步
你现在已经了解了如何基于 PDF 文档构建语义搜索引擎。
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: