Pinecone는 광범위한 기능을 제공하는 vector database입니다.
이 노트북에서는 Pinecone vector database와 관련된 기능을 사용하는 방법을 보여줍니다.

​
설정

PineconeSparseVectorStore를 사용하려면, 파트너 package와 이 노트북 전반에서 사용하는 다른 package들을 먼저 설치해야 합니다. 
pip install -qU "langchain-pinecone==0.2.5"

WARNING: pinecone 6.0.2 does not provide the extra 'async'

​
자격 증명

새로운 Pinecone account를 만들거나 기존 account에 로그인한 뒤, 이 노트북에서 사용할 API key를 생성하세요. 
import os
from getpass import getpass

from pinecone import Pinecone

# get API key at app.pinecone.io
os.environ["PINECONE_API_KEY"] = os.getenv("PINECONE_API_KEY") or getpass(
    "Enter your Pinecone API key: "
)

# initialize client
pc = Pinecone()

Enter your Pinecone API key: ··········

​
초기화

vector store를 초기화하기 전에 Pinecone index에 연결해 보겠습니다. 이름이 index_name인 index가 없다면 새로 생성됩니다. 
from pinecone import AwsRegion, CloudProvider, Metric, ServerlessSpec

index_name = "langchain-sparse-vector-search"  # change if desired
model_name = "pinecone-sparse-english-v0"

if not pc.has_index(index_name):
    pc.create_index_for_model(
        name=index_name,
        cloud=CloudProvider.AWS,
        region=AwsRegion.US_EAST_1,
        embed={
            "model": model_name,
            "field_map": {"text": "chunk_text"},
            "metric": Metric.DOTPRODUCT,
        },
    )

index = pc.Index(index_name)
print(f"Index `{index_name}` host: {index.config.host}")

Index `langchain-sparse-vector-search` host: https://langchain-sparse-vector-search-yrrgefy.svc.aped-4627-b74a.pinecone.io
sparse embedding model로 pinecone-sparse-english-v0를 사용하며, 다음과 같이 초기화합니다: 
from langchain_pinecone.embeddings import PineconeSparseEmbeddings

sparse_embeddings = PineconeSparseEmbeddings(model=model_name)
이제 Pinecone index와 embedding model이 준비되었으므로, LangChain에서 sparse vector store를 초기화할 수 있습니다: 
from langchain_pinecone import PineconeSparseVectorStore

vector_store = PineconeSparseVectorStore(index=index, embedding=sparse_embeddings)

​
vector store 관리

vector store를 만들었으면 항목을 추가하거나 삭제하여 상호작용할 수 있습니다.

​
vector store에 항목 추가

add_documents function을 사용해 vector store에 항목을 추가할 수 있습니다. 
from uuid import uuid4

from langchain_core.documents import Document

documents = [
    Document(
        page_content="I had chocolate chip pancakes and scrambled eggs for breakfast this morning.",
        metadata={"source": "social"},
    ),
    Document(
        page_content="The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees.",
        metadata={"source": "news"},
    ),
    Document(
        page_content="Building an exciting new project with LangChain - come check it out!",
        metadata={"source": "social"},
    ),
    Document(
        page_content="Robbers broke into the city bank and stole $1 million in cash.",
        metadata={"source": "news"},
    ),
    Document(
        page_content="Wow! That was an amazing movie. I can't wait to see it again.",
        metadata={"source": "social"},
    ),
    Document(
        page_content="Is the new iPhone worth the price? Read this review to find out.",
        metadata={"source": "website"},
    ),
    Document(
        page_content="The top 10 soccer players in the world right now.",
        metadata={"source": "website"},
    ),
    Document(
        page_content="LangGraph is the best framework for building stateful, agentic applications!",
        metadata={"source": "social"},
    ),
    Document(
        page_content="The stock market is down 500 points today due to fears of a recession.",
        metadata={"source": "news"},
    ),
    Document(
        page_content="I have a bad feeling I am going to get deleted :(",
        metadata={"source": "social"},
    ),
]

uuids = [str(uuid4()) for _ in range(len(documents))]

vector_store.add_documents(documents=documents, ids=uuids)

['95b598af-c3dc-4a8a-bdb7-5d21283e5a86',
 '838614a5-5635-4efd-9ac3-5237a37a542b',
 '093fd11f-c85b-4c83-83f0-117df64ff442',
 'fb3ba32f-f802-410a-ad79-56f7bce938fe',
 '75cde9bf-7e91-4f06-8bae-c824dab16a08',
 '9de8f769-d604-4e56-b677-ee333cbc8e34',
 'f5f4ae97-88e6-4669-bcf7-87072bb08550',
 'f9f82811-187c-4b25-85b5-7a42b4da3bff',
 'ce45957c-e8fc-41ef-819b-1bd52b6fc815',
 '66cacc6f-b8e2-441b-9f7f-468788aad88f']

​
vector store에서 항목 삭제

delete method를 사용하여 vector store에서 record를 삭제할 수 있으며, 삭제할 document ID 목록을 전달하면 됩니다. 
vector_store.delete(ids=[uuids[-1]])

​
vector store 쿼리

document를 vector store에 적재했으면 보통 쿼리를 시작할 준비가 된 것입니다. LangChain에는 이를 위한 다양한 methods가 있습니다. 먼저 similarity_search method를 통해 vector_store를 직접 쿼리하여 간단한 vector search를 수행하는 방법을 보겠습니다: 
results = vector_store.similarity_search("I'm building a new LangChain project!", k=3)

for res in results:
    print(f"* {res.page_content} [{res.metadata}]")

* Building an exciting new project with LangChain - come check it out! [{'source': 'social'}]
* Building an exciting new project with LangChain - come check it out! [{'source': 'social'}]
* LangGraph is the best framework for building stateful, agentic applications! [{'source': 'social'}]
쿼리에 metadata filtering을 추가하여 다양한 기준에 따라 검색 범위를 제한할 수도 있습니다. source=="social"인 record만 포함하도록 검색을 제한하는 간단한 filter를 적용해 보겠습니다: 
results = vector_store.similarity_search(
    "I'm building a new LangChain project!",
    k=3,
    filter={"source": "social"},
)
for res in results:
    print(f"* {res.page_content} [{res.metadata}]")

* Building an exciting new project with LangChain - come check it out! [{'source': 'social'}]
* Building an exciting new project with LangChain - come check it out! [{'source': 'social'}]
* LangGraph is the best framework for building stateful, agentic applications! [{'source': 'social'}]
이 결과들을 비교해 보면 첫 번째 쿼리는 "website" source에서 다른 record를 반환했음을 알 수 있습니다. 이후의 filter가 적용된 쿼리에서는 더 이상 그렇지 않습니다.

​
Similarity Search와 점수

검색 시 (document, score) tuple 목록과 함께 similarity score를 반환하도록 할 수도 있습니다. 여기서 document는 텍스트 내용과 metadata를 포함하는 LangChain Document object입니다. 
results = vector_store.similarity_search_with_score(
    "I'm building a new LangChain project!", k=3, filter={"source": "social"}
)
for doc, score in results:
    print(f"[SIM={score:3f}] {doc.page_content} [{doc.metadata}]")

[SIM=12.959961] Building an exciting new project with LangChain - come check it out! [{'source': 'social'}]
[SIM=12.959961] Building an exciting new project with LangChain - come check it out! [{'source': 'social'}]
[SIM=1.942383] LangGraph is the best framework for building stateful, agentic applications! [{'source': 'social'}]

​
Retriever로 사용하기

chain과 agent에서는 vector store를 VectorStoreRetriever로 자주 사용합니다. 이를 생성하려면 as_retriever method를 사용합니다: 
retriever = vector_store.as_retriever(
    search_type="similarity_score_threshold",
    search_kwargs={"k": 3, "score_threshold": 0.5},
)
retriever

VectorStoreRetriever(tags=['PineconeSparseVectorStore', 'PineconeSparseEmbeddings'], vectorstore=<langchain_pinecone.vectorstores_sparse.PineconeSparseVectorStore object at 0x7c8087b24290>, search_type='similarity_score_threshold', search_kwargs={'k': 3, 'score_threshold': 0.5})
이제 invoke method를 사용해 retriever를 쿼리할 수 있습니다: 
retriever.invoke(
    input="I'm building a new LangChain project!", filter={"source": "social"}
)

/usr/local/lib/python3.11/dist-packages/langchain_core/vectorstores/base.py:1082: UserWarning: Relevance scores must be between 0 and 1, got [(Document(id='093fd11f-c85b-4c83-83f0-117df64ff442', metadata={'source': 'social'}, page_content='Building an exciting new project with LangChain - come check it out!'), 6.97998045), (Document(id='54f8f645-9f77-4aab-b9fa-709fd91ae3b3', metadata={'source': 'social'}, page_content='Building an exciting new project with LangChain - come check it out!'), 6.97998045), (Document(id='f9f82811-187c-4b25-85b5-7a42b4da3bff', metadata={'source': 'social'}, page_content='LangGraph is the best framework for building stateful, agentic applications!'), 1.471191405)]
  self.vectorstore.similarity_search_with_relevance_scores(

[Document(id='093fd11f-c85b-4c83-83f0-117df64ff442', metadata={'source': 'social'}, page_content='Building an exciting new project with LangChain - come check it out!'),
 Document(id='54f8f645-9f77-4aab-b9fa-709fd91ae3b3', metadata={'source': 'social'}, page_content='Building an exciting new project with LangChain - come check it out!'),
 Document(id='f9f82811-187c-4b25-85b5-7a42b4da3bff', metadata={'source': 'social'}, page_content='LangGraph is the best framework for building stateful, agentic applications!')]

​
retrieval-augmented generation에서의 사용

이 vector store를 retrieval-augmented generation(RAG)에 사용하는 방법은 다음 섹션을 참조하세요:

​
API reference

모든 기능과 설정에 대한 자세한 문서는 API reference를 확인하세요: python.langchain.com/api_reference/pinecone/vectorstores_sparse/langchain_pinecone.vectorstores_sparse.PineconeSparseVectorStore.html#langchain_pinecone.vectorstores_sparse.PineconeSparseVectorStore Sparse Embeddings: python.langchain.com/api_reference/pinecone/embeddings/langchain_pinecone.embeddings.PineconeSparseEmbeddings.html
Edit the source of this page on GitHub.
Connect these docs programmatically to Claude, VSCode, and more via MCP for real-time answers.
⌘I