如何使用父文档检索器

在为检索拆分文档时，常常存在相互冲突的需求：

你可能希望文档尽量短小，以便其嵌入向量能够最准确地反映其含义。如果文档过长，嵌入向量可能会丢失语义。
您希望文档足够长，以确保每个片段的上下文都能被保留。

ParentDocumentRetriever 通过拆分和存储小块数据来实现这种平衡。在检索过程中，它首先获取小块数据，然后查找这些数据块的父ID，并返回这些较大的文档。

请注意，“父文档”指的是小段文本的原始来源文档。这可以是整个原始文档，也可以是较大的文本块。

from langchain.retrievers import ParentDocumentRetriever

API 参考：ParentDocumentRetriever

from langchain.storage import InMemoryStore
from langchain_chroma import Chroma
from langchain_community.document_loaders import TextLoader
from langchain_openai import OpenAIEmbeddings
from langchain_text_splitters import RecursiveCharacterTextSplitter

API 参考：InMemoryStore | TextLoader | OpenAIEmbeddings | RecursiveCharacterTextSplitter

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

正在检索完整文档

在此模式下，我们希望检索完整的文档。因此，我们仅指定一个子拆分器。

# This text splitter is used to create the child documents
child_splitter = RecursiveCharacterTextSplitter(chunk_size=400)
# The vectorstore to use to index the child chunks
vectorstore = Chroma(
    collection_name="full_documents", embedding_function=OpenAIEmbeddings()
)
# The storage layer for the parent documents
store = InMemoryStore()
retriever = ParentDocumentRetriever(
    vectorstore=vectorstore,
    docstore=store,
    child_splitter=child_splitter,
)

retriever.add_documents(docs, ids=None)

这应该会产生两个键，因为我们添加了两份文档。

list(store.yield_keys())

['9a63376c-58cc-42c9-b0f7-61f0e1a3a688',
 '40091598-e918-4a18-9be0-f46413a95ae4']

现在让我们调用向量存储的搜索功能——我们应该看到它返回的是小段落（因为我们存储的是小段落）。

sub_docs = vectorstore.similarity_search("justice breyer")

print(sub_docs[0].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. 

One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.

现在让我们从整体检索器中获取内容。这应该返回较大的文档——因为返回的是较小片段所在的文档。

retrieved_docs = retriever.invoke("justice breyer")

len(retrieved_docs[0].page_content)

检索更大的数据块

有时，完整的文档可能过大，不希望直接检索整个文档。在这种情况下，我们真正想要做的是：首先将原始文档拆分为较大的段落，然后再将这些段落进一步拆分为更小的片段。接着，我们对较小的片段进行索引，但在检索时，我们只获取较大的段落（但仍不会获取完整的文档）。

# This text splitter is used to create the parent documents
parent_splitter = RecursiveCharacterTextSplitter(chunk_size=2000)
# This text splitter is used to create the child documents
# It should create documents smaller than the parent
child_splitter = RecursiveCharacterTextSplitter(chunk_size=400)
# The vectorstore to use to index the child chunks
vectorstore = Chroma(
    collection_name="split_parents", embedding_function=OpenAIEmbeddings()
)
# The storage layer for the parent documents
store = InMemoryStore()

retriever = ParentDocumentRetriever(
    vectorstore=vectorstore,
    docstore=store,
    child_splitter=child_splitter,
    parent_splitter=parent_splitter,
)

retriever.add_documents(docs)

我们可以看到，现在文档数量远超两个——这些是较大的文本块。

len(list(store.yield_keys()))

让我们确保底层向量存储仍然能够检索到小块数据。

sub_docs = vectorstore.similarity_search("justice breyer")

print(sub_docs[0].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. 

One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.

retrieved_docs = retriever.invoke("justice breyer")

len(retrieved_docs[0].page_content)

print(retrieved_docs[0].page_content)

In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. 

We cannot let this happen. 

Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. 

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. 

One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. 

And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence. 

A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. 

And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. 

We can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling.  

We’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers.  

We’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. 

We’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.

正在检索完整文档​

检索更大的数据块​

正在检索完整文档

检索更大的数据块