如何使用上下文壓縮進行檢索

檢索的一個挑戰是，通常您在將資料攝取到系統時，不知道文件儲存系統將面臨的特定查詢。這表示與查詢最相關的資訊可能埋藏在包含大量無關文本的文件中。將完整文件傳遞到您的應用程式可能會導致更昂貴的 LLM 調用和較差的回應。

上下文壓縮旨在解決此問題。這個想法很簡單：您可以利用給定查詢的上下文壓縮檢索到的文件，而不是立即按原樣返回它們，以便僅返回相關資訊。「壓縮」在此處指的是壓縮單個文件的內容和完全過濾掉文件。

要使用上下文壓縮檢索器，您需要

一個基礎檢索器
一個文件壓縮器

上下文壓縮檢索器將查詢傳遞給基礎檢索器，取得初始文件並將其傳遞到文件壓縮器。文件壓縮器接收文件列表，並通過減少文件內容或完全刪除文件來縮短列表。

開始使用

# Helper function for printing docs


def pretty_print_docs(docs):
    print(
        f"\n{'-' * 100}\n".join(
            [f"Document {i+1}:\n\n" + d.page_content for i, d in enumerate(docs)]
        )
    )

使用原始向量儲存檢索器

讓我們從初始化一個簡單的向量儲存檢索器並儲存 2023 年國情咨文演講（以塊為單位）開始。我們可以發現，對於一個範例問題，我們的檢索器返回一兩個相關文件和一些不相關文件。即使是相關文件也包含大量無關資訊。

from langchain_community.document_loaders import TextLoader
from langchain_community.vectorstores import FAISS
from langchain_openai import OpenAIEmbeddings
from langchain_text_splitters import CharacterTextSplitter

documents = TextLoader("state_of_the_union.txt").load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
texts = text_splitter.split_documents(documents)
retriever = FAISS.from_documents(texts, OpenAIEmbeddings()).as_retriever()

docs = retriever.invoke("What did the president say about Ketanji Brown Jackson")
pretty_print_docs(docs)

API 參考：TextLoader | FAISS | OpenAIEmbeddings | CharacterTextSplitter

Document 1:

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.
----------------------------------------------------------------------------------------------------
Document 2:

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.
----------------------------------------------------------------------------------------------------
Document 3:

And for our LGBTQ+ Americans, let’s finally get the bipartisan Equality Act to my desk. The onslaught of state laws targeting transgender Americans and their families is wrong. 

As I said last year, especially to our younger transgender Americans, I will always have your back as your President, so you can be yourself and reach your God-given potential. 

While it often appears that we never agree, that isn’t true. I signed 80 bipartisan bills into law last year. From preventing government shutdowns to protecting Asian-Americans from still-too-common hate crimes to reforming military justice. 

And soon, we’ll strengthen the Violence Against Women Act that I first wrote three decades ago. It is important for us to show the nation that we can come together and do big things. 

So tonight I’m offering a Unity Agenda for the Nation. Four big things we can do together.  

First, beat the opioid epidemic.
----------------------------------------------------------------------------------------------------
Document 4:

Tonight, I’m announcing a crackdown on these companies overcharging American businesses and consumers. 

And as Wall Street firms take over more nursing homes, quality in those homes has gone down and costs have gone up.  

That ends on my watch. 

Medicare is going to set higher standards for nursing homes and make sure your loved ones get the care they deserve and expect. 

We’ll also cut costs and keep the economy going strong by giving workers a fair shot, provide more training and apprenticeships, hire them based on their skills not degrees. 

Let’s pass the Paycheck Fairness Act and paid leave.  

Raise the minimum wage to $15 an hour and extend the Child Tax Credit, so no one has to raise a family in poverty. 

Let’s increase Pell Grants and increase our historic support of HBCUs, and invest in what Jill—our First Lady who teaches full-time—calls America’s best-kept secret: community colleges.

使用 `LLMChainExtractor` 添加上下文壓縮

現在讓我們用 ContextualCompressionRetriever 包裝我們的基礎檢索器。我們將添加一個 LLMChainExtractor，它將迭代最初返回的文件，並僅從每個文件中提取與查詢相關的內容。

from langchain.retrievers import ContextualCompressionRetriever
from langchain.retrievers.document_compressors import LLMChainExtractor
from langchain_openai import OpenAI

llm = OpenAI(temperature=0)
compressor = LLMChainExtractor.from_llm(llm)
compression_retriever = ContextualCompressionRetriever(
    base_compressor=compressor, base_retriever=retriever
)

compressed_docs = compression_retriever.invoke(
    "What did the president say about Ketanji Jackson Brown"
)
pretty_print_docs(compressed_docs)

API 參考：ContextualCompressionRetriever | LLMChainExtractor | OpenAI

Document 1:

I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson.

更多內建壓縮器：篩選器

`LLMChainFilter`

LLMChainFilter 是一個稍微簡單但更穩健的壓縮器，它使用 LLM 鏈來決定要過濾掉哪些初始檢索到的文件以及要返回哪些文件，而無需操作文件內容。

from langchain.retrievers.document_compressors import LLMChainFilter

_filter = LLMChainFilter.from_llm(llm)
compression_retriever = ContextualCompressionRetriever(
    base_compressor=_filter, base_retriever=retriever
)

compressed_docs = compression_retriever.invoke(
    "What did the president say about Ketanji Jackson Brown"
)
pretty_print_docs(compressed_docs)

API 參考：LLMChainFilter

Document 1:

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.

`LLMListwiseRerank`

LLMListwiseRerank 使用零樣本列表式文件重新排序，其功能與 LLMChainFilter 類似，作為一個穩健但更昂貴的選項。建議使用更強大的 LLM。

請注意，LLMListwiseRerank 需要實作 with_structured_output 方法的模型。

from langchain.retrievers.document_compressors import LLMListwiseRerank
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)

_filter = LLMListwiseRerank.from_llm(llm, top_n=1)
compression_retriever = ContextualCompressionRetriever(
    base_compressor=_filter, base_retriever=retriever
)

compressed_docs = compression_retriever.invoke(
    "What did the president say about Ketanji Jackson Brown"
)
pretty_print_docs(compressed_docs)

API 參考：LLMListwiseRerank | ChatOpenAI

Document 1:

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.

`EmbeddingsFilter`

對每個檢索到的文件額外進行 LLM 調用既昂貴又緩慢。EmbeddingsFilter 提供了一個更便宜、更快速的選項，透過嵌入文件和查詢，僅返回那些與查詢具有足夠相似嵌入的文件。

from langchain.retrievers.document_compressors import EmbeddingsFilter
from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings()
embeddings_filter = EmbeddingsFilter(embeddings=embeddings, similarity_threshold=0.76)
compression_retriever = ContextualCompressionRetriever(
    base_compressor=embeddings_filter, base_retriever=retriever
)

compressed_docs = compression_retriever.invoke(
    "What did the president say about Ketanji Jackson Brown"
)
pretty_print_docs(compressed_docs)

API 參考：EmbeddingsFilter | OpenAIEmbeddings

Document 1:

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.
----------------------------------------------------------------------------------------------------
Document 2:

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.

將壓縮器和文件轉換器串聯在一起

使用 DocumentCompressorPipeline，我們也可以輕鬆地按順序組合多個壓縮器。除了壓縮器之外，我們還可以在管道中添加 BaseDocumentTransformer，它們不執行任何上下文壓縮，而只是對一組文件執行一些轉換。例如，TextSplitter 可以用作文件轉換器，將文件分割成更小的塊，而 EmbeddingsRedundantFilter 可以用於根據文件之間嵌入相似性來過濾掉冗餘文件。

下面我們建立一個壓縮器管道，首先將我們的文件分割成更小的塊，然後移除冗餘文件，然後根據與查詢的相關性進行篩選。

from langchain.retrievers.document_compressors import DocumentCompressorPipeline
from langchain_community.document_transformers import EmbeddingsRedundantFilter
from langchain_text_splitters import CharacterTextSplitter

splitter = CharacterTextSplitter(chunk_size=300, chunk_overlap=0, separator=". ")
redundant_filter = EmbeddingsRedundantFilter(embeddings=embeddings)
relevant_filter = EmbeddingsFilter(embeddings=embeddings, similarity_threshold=0.76)
pipeline_compressor = DocumentCompressorPipeline(
    transformers=[splitter, redundant_filter, relevant_filter]
)

API 參考：DocumentCompressorPipeline | EmbeddingsRedundantFilter | CharacterTextSplitter

compression_retriever = ContextualCompressionRetriever(
    base_compressor=pipeline_compressor, base_retriever=retriever
)

compressed_docs = compression_retriever.invoke(
    "What did the president say about Ketanji Jackson Brown"
)
pretty_print_docs(compressed_docs)

Document 1:

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
----------------------------------------------------------------------------------------------------
Document 2:

As I said last year, especially to our younger transgender Americans, I will always have your back as your President, so you can be yourself and reach your God-given potential. 

While it often appears that we never agree, that isn’t true. I signed 80 bipartisan bills into law last year
----------------------------------------------------------------------------------------------------
Document 3:

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
----------------------------------------------------------------------------------------------------
Document 4:

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

開始使用​

使用原始向量儲存檢索器​

使用 LLMChainExtractor 添加上下文壓縮​

更多內建壓縮器：篩選器​

LLMChainFilter​

LLMListwiseRerank​

EmbeddingsFilter​

將壓縮器和文件轉換器串聯在一起​

此頁面是否對您有幫助？