Skip to main content
Pinecone is a vector database with broad functionality.
This notebook shows how to use functionality related to the Pinecone vector database.

​
Setup

To use the PineconeSparseVectorStore you first need to install the partner package, as well as the other packages used throughout this notebook. 
pip install -qU "langchain-pinecone==0.2.5"

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

​
Credentials

Create a new Pinecone account, or sign into your existing one, and create an API key to use in this notebook. 
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: ··········

​
Initialization

Before initializing our vector store, let’s connect to a Pinecone index. If one named index_name doesn’t exist, it will be created. 
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
For our sparse embedding model we use pinecone-sparse-english-v0, we initialize it like so: 
from langchain_pinecone.embeddings import PineconeSparseEmbeddings

sparse_embeddings = PineconeSparseEmbeddings(model=model_name)
Now that our Pinecone index and embedding model are both ready, we can initialize our sparse vector store in LangChain: 
from langchain_pinecone import PineconeSparseVectorStore

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

​
Manage vector store

Once you have created your vector store, we can interact with it by adding and deleting different items.

​
Add items to vector store

We can add items to our vector store by using the add_documents function. 
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']

​
Delete items from vector store

We can delete records from our vector store using the delete method, providing it with a list of document IDs to delete. 
vector_store.delete(ids=[uuids[-1]])

​
Query vector store

Once we have loaded our documents into the vector store we’re most likely ready to begin querying. There are various method for doing this in LangChain. First, we’ll see how to perform a simple vector search by querying our vector_store directly via the similarity_search method: 
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'}]
We can also add metadata filtering to our query to limit our search based on various criteria. Let’s try a simple filter to limit our search to include only records with source=="social": 
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'}]
When comparing these results, we can see that our first query returned a different record from the "website" source. In our latter, filtered, query — this is no longer the case.

​
Similarity Search and Scores

We can also search while returning the similarity score in a list of (document, score) tuples. Where the document is a LangChain Document object containing our text content and metadata. 
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'}]

​
As a Retriever

In our chains and agents we’ll often use the vector store as a VectorStoreRetriever. To create that, we use the as_retriever method: 
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})
We can now query our retriever using the invoke method: 
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!')]

​
Usage for retrieval-augmented generation

For guides on how to use this vector store for retrieval-augmented generation (RAG), see the following sections:

​
API reference

For detailed documentation of all features and configurations head to the API reference: 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