跳到主要内容
Open In ColabOpen on GitHub

如何使用每个文档的多个向量进行检索

每个文档存储多个向量通常很有用。这在多种用例中都具有优势。例如,我们可以嵌入文档的多个块,并将这些嵌入与父文档关联,从而允许检索器命中这些块时返回更大的文档。

LangChain 实现了一个基础的MultiVectorRetriever,这简化了此过程。大部分复杂性在于如何为每个文档创建多个向量。本笔记本涵盖了一些创建这些向量和使用MultiVectorRetriever的常见方法。

为每个文档创建多个向量的方法包括

  • 较小的块:将文档拆分为较小的块,并嵌入这些块(这即是ParentDocumentRetriever)。
  • 摘要:为每个文档创建一个摘要,并将其与(或代替)文档一起嵌入。
  • 假设性问题:创建每个文档适合回答的假设性问题,并将其与(或代替)文档一起嵌入。

请注意,这还支持另一种添加嵌入的方法——手动添加。这很有用,因为您可以明确添加应导致文档被检索的问题或查询,从而为您提供更多控制。

下面我们来看一个例子。首先,我们实例化一些文档。我们将使用OpenAI嵌入将它们索引到(内存中的)Chroma向量存储中,但任何 LangChain 向量存储或嵌入模型都可以。

%pip install --upgrade --quiet  langchain-chroma langchain langchain-openai > /dev/null
from langchain.storage import InMemoryByteStore
from langchain_chroma import Chroma
from langchain_community.document_loaders import TextLoader
from langchain_openai import OpenAIEmbeddings
from langchain_text_splitters import RecursiveCharacterTextSplitter

loaders = [
TextLoader("paul_graham_essay.txt"),
TextLoader("state_of_the_union.txt"),
]
docs = []
for loader in loaders:
docs.extend(loader.load())
text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000)
docs = text_splitter.split_documents(docs)

# The vectorstore to use to index the child chunks
vectorstore = Chroma(
collection_name="full_documents", embedding_function=OpenAIEmbeddings()
)

较小的块

通常,检索较大的信息块但嵌入较小的块会很有用。这使得嵌入能够尽可能准确地捕捉语义含义,同时将尽可能多的上下文传递到下游。请注意,这正是ParentDocumentRetriever所做的工作。这里我们展示其内部机制。

我们将区分向量存储(索引(子)文档的嵌入)和文档存储(保存“父”文档并将其与标识符关联)。

import uuid

from langchain.retrievers.multi_vector import MultiVectorRetriever

# The storage layer for the parent documents
store = InMemoryByteStore()
id_key = "doc_id"

# The retriever (empty to start)
retriever = MultiVectorRetriever(
vectorstore=vectorstore,
byte_store=store,
id_key=id_key,
)

doc_ids = [str(uuid.uuid4()) for _ in docs]

接下来,我们通过拆分原始文档来生成“子”文档。请注意,我们将文档标识符存储在相应Document对象的metadata中。

# The splitter to use to create smaller chunks
child_text_splitter = RecursiveCharacterTextSplitter(chunk_size=400)

sub_docs = []
for i, doc in enumerate(docs):
_id = doc_ids[i]
_sub_docs = child_text_splitter.split_documents([doc])
for _doc in _sub_docs:
_doc.metadata[id_key] = _id
sub_docs.extend(_sub_docs)

最后,我们将文档索引到我们的向量存储和文档存储中

retriever.vectorstore.add_documents(sub_docs)
retriever.docstore.mset(list(zip(doc_ids, docs)))

仅向量存储会检索小块

retriever.vectorstore.similarity_search("justice breyer")[0]
Document(page_content='Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.', metadata={'doc_id': '064eca46-a4c4-4789-8e3b-583f9597e54f', 'source': 'state_of_the_union.txt'})

而检索器将返回更大的父文档

len(retriever.invoke("justice breyer")[0].page_content)
9875

检索器在向量数据库上执行的默认搜索类型是相似性搜索。LangChain 向量存储还支持通过最大边际相关性进行搜索。这可以通过检索器的search_type参数进行控制

from langchain.retrievers.multi_vector import SearchType

retriever.search_type = SearchType.mmr

len(retriever.invoke("justice breyer")[0].page_content)
API 参考:SearchType
9875

将摘要与文档关联以进行检索

摘要能够更准确地提炼出块的含义,从而实现更好的检索。这里我们展示如何创建摘要,然后嵌入它们。

我们构建一个简单的,它将接收一个输入Document对象并使用 LLM 生成摘要。

pip install -qU "langchain[google-genai]"
import getpass
import os

if not os.environ.get("GOOGLE_API_KEY"):
os.environ["GOOGLE_API_KEY"] = getpass.getpass("Enter API key for Google Gemini: ")

from langchain.chat_models import init_chat_model

llm = init_chat_model("gemini-2.0-flash", model_provider="google_genai")
import uuid

from langchain_core.documents import Document
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate

chain = (
{"doc": lambda x: x.page_content}
| ChatPromptTemplate.from_template("Summarize the following document:\n\n{doc}")
| llm
| StrOutputParser()
)

请注意,我们可以批量处理文档链

summaries = chain.batch(docs, {"max_concurrency": 5})

然后,我们可以像之前一样初始化一个MultiVectorRetriever,在我们的向量存储中索引摘要,并在我们的文档存储中保留原始文档

# The vectorstore to use to index the child chunks
vectorstore = Chroma(collection_name="summaries", embedding_function=OpenAIEmbeddings())
# The storage layer for the parent documents
store = InMemoryByteStore()
id_key = "doc_id"
# The retriever (empty to start)
retriever = MultiVectorRetriever(
vectorstore=vectorstore,
byte_store=store,
id_key=id_key,
)
doc_ids = [str(uuid.uuid4()) for _ in docs]

summary_docs = [
Document(page_content=s, metadata={id_key: doc_ids[i]})
for i, s in enumerate(summaries)
]

retriever.vectorstore.add_documents(summary_docs)
retriever.docstore.mset(list(zip(doc_ids, docs)))
# # We can also add the original chunks to the vectorstore if we so want
# for i, doc in enumerate(docs):
# doc.metadata[id_key] = doc_ids[i]
# retriever.vectorstore.add_documents(docs)

查询向量存储将返回摘要

sub_docs = retriever.vectorstore.similarity_search("justice breyer")

sub_docs[0]
Document(page_content="President Biden recently nominated Judge Ketanji Brown Jackson to serve on the United States Supreme Court, emphasizing her qualifications and broad support. The President also outlined a plan to secure the border, fix the immigration system, protect women's rights, support LGBTQ+ Americans, and advance mental health services. He highlighted the importance of bipartisan unity in passing legislation, such as the Violence Against Women Act. The President also addressed supporting veterans, particularly those impacted by exposure to burn pits, and announced plans to expand benefits for veterans with respiratory cancers. Additionally, he proposed a plan to end cancer as we know it through the Cancer Moonshot initiative. President Biden expressed optimism about the future of America and emphasized the strength of the American people in overcoming challenges.", metadata={'doc_id': '84015b1b-980e-400a-94d8-cf95d7e079bd'})

而检索器将返回更大的源文档

retrieved_docs = retriever.invoke("justice breyer")

len(retrieved_docs[0].page_content)
9194

假设性查询

LLM 也可以用于生成一份针对特定文档的假设性问题列表,这些问题可能与 RAG 应用程序中的相关查询具有紧密的语义相似性。然后,这些问题可以被嵌入并与文档关联以改进检索。

下面,我们使用with_structured_output方法将 LLM 输出结构化为字符串列表。

from typing import List

from pydantic import BaseModel, Field


class HypotheticalQuestions(BaseModel):
"""Generate hypothetical questions."""

questions: List[str] = Field(..., description="List of questions")


chain = (
{"doc": lambda x: x.page_content}
# Only asking for 3 hypothetical questions, but this could be adjusted
| ChatPromptTemplate.from_template(
"Generate a list of exactly 3 hypothetical questions that the below document could be used to answer:\n\n{doc}"
)
| ChatOpenAI(max_retries=0, model="gpt-4o").with_structured_output(
HypotheticalQuestions
)
| (lambda x: x.questions)
)

在单个文档上调用该链表明它输出一个问题列表

chain.invoke(docs[0])
["What impact did the IBM 1401 have on the author's early programming experiences?",
"How did the transition from using the IBM 1401 to microcomputers influence the author's programming journey?",
"What role did Lisp play in shaping the author's understanding and approach to AI?"]

然后,我们可以对所有文档进行批量处理,并像之前一样组装我们的向量存储和文档存储

# Batch chain over documents to generate hypothetical questions
hypothetical_questions = chain.batch(docs, {"max_concurrency": 5})


# The vectorstore to use to index the child chunks
vectorstore = Chroma(
collection_name="hypo-questions", embedding_function=OpenAIEmbeddings()
)
# The storage layer for the parent documents
store = InMemoryByteStore()
id_key = "doc_id"
# The retriever (empty to start)
retriever = MultiVectorRetriever(
vectorstore=vectorstore,
byte_store=store,
id_key=id_key,
)
doc_ids = [str(uuid.uuid4()) for _ in docs]


# Generate Document objects from hypothetical questions
question_docs = []
for i, question_list in enumerate(hypothetical_questions):
question_docs.extend(
[Document(page_content=s, metadata={id_key: doc_ids[i]}) for s in question_list]
)


retriever.vectorstore.add_documents(question_docs)
retriever.docstore.mset(list(zip(doc_ids, docs)))

请注意,查询底层向量存储将检索到与输入查询语义相似的假设性问题

sub_docs = retriever.vectorstore.similarity_search("justice breyer")

sub_docs
[Document(page_content='What might be the potential benefits of nominating Circuit Court of Appeals Judge Ketanji Brown Jackson to the United States Supreme Court?', metadata={'doc_id': '43292b74-d1b8-4200-8a8b-ea0cb57fbcdb'}),
Document(page_content='How might the Bipartisan Infrastructure Law impact the economic competition between the U.S. and China?', metadata={'doc_id': '66174780-d00c-4166-9791-f0069846e734'}),
Document(page_content='What factors led to the creation of Y Combinator?', metadata={'doc_id': '72003c4e-4cc9-4f09-a787-0b541a65b38c'}),
Document(page_content='How did the ability to publish essays online change the landscape for writers and thinkers?', metadata={'doc_id': 'e8d2c648-f245-4bcc-b8d3-14e64a164b64'})]

调用检索器将返回相应的文档

retrieved_docs = retriever.invoke("justice breyer")
len(retrieved_docs[0].page_content)
9194