이 노트북은 문서 압축 및 검색을 위해 Jina Reranker를 사용하는 방법을 보여줍니다. 
pip install -qU langchain langchain-openai langchain-community langchain-text-splitters langchainhub

pip install -qU  faiss

# OR  (depending on Python version)

pip install -qU  faiss_cpu

# 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)]
        )
    )

​
기본 vector store retriever 설정하기

간단한 vector store retriever를 초기화하고 2023년 국정연설문을 (청크 단위로) 저장하는 것부터 시작하겠습니다. retriever가 많은 수(20개)의 문서를 검색하도록 설정할 수 있습니다.
Jina 및 OpenAI API key 설정하기
import getpass
import os

os.environ["OPENAI_API_KEY"] = getpass.getpass()
os.environ["JINA_API_KEY"] = getpass.getpass()

from langchain_community.document_loaders import TextLoader
from langchain_community.embeddings import JinaEmbeddings
from langchain_community.vectorstores import FAISS
from langchain_text_splitters import RecursiveCharacterTextSplitter

documents = TextLoader(
    "../../how_to/state_of_the_union.txt",
).load()
text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)
texts = text_splitter.split_documents(documents)

embedding = JinaEmbeddings(model_name="jina-embeddings-v2-base-en")
retriever = FAISS.from_documents(texts, embedding).as_retriever(search_kwargs={"k": 20})

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

​
JinaRerank로 reranking 수행하기

이제 기본 retriever를 ContextualCompressionRetriever로 래핑하고, Jina Reranker를 compressor로 사용하겠습니다. 
from langchain.retrievers import ContextualCompressionRetriever
from langchain_community.document_compressors import JinaRerank

compressor = JinaRerank()
compression_retriever = ContextualCompressionRetriever(
    base_compressor=compressor, base_retriever=retriever
)

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

pretty_print_docs(compressed_docs)

​
Jina Reranker를 사용한 QA reranking

from langchain_classic import hub
from langchain.chains import create_retrieval_chain
from langchain.chains.combine_documents import create_stuff_documents_chain

retrieval_qa_chat_prompt = hub.pull("langchain-ai/retrieval-qa-chat")
retrieval_qa_chat_prompt.pretty_print()

================================ System Message ================================

Answer any use questions based solely on the context below:

<context>
{context}
</context>

============================= Messages Placeholder =============================

{chat_history}

================================ Human Message =================================

{input}

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
combine_docs_chain = create_stuff_documents_chain(llm, retrieval_qa_chat_prompt)
chain = create_retrieval_chain(compression_retriever, combine_docs_chain)

chain.invoke({"input": query})
Edit the source of this page on GitHub.
Connect these docs programmatically to Claude, VSCode, and more via MCP for real-time answers.
⌘I