Package org.springframework.ai.vectorstore

Class PineconeVectorStore

java.lang.Object

org.springframework.ai.vectorstore.PineconeVectorStore

All Implemented Interfaces:

Consumer<List<Document>>, DocumentWriter, VectorStore

public class PineconeVectorStore
extends Object
implements VectorStore

A VectorStore implementation backed by Pinecone, a cloud-based vector database. This store supports creating, updating, deleting, and similarity searching of documents in a Pinecone index.

Author:

Christian Tzolov

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static final class	PineconeVectorStore.PineconeVectorStoreConfig	Configuration class for the PineconeVectorStore.

Field Summary

Fields

Modifier and Type	Field	Description
final PineconeFilterExpressionConverter	filterExpressionConverter

Constructor Summary

Constructors

Constructor	Description
PineconeVectorStore(PineconeVectorStore.PineconeVectorStoreConfig config, EmbeddingClient embeddingClient)	Constructs a new PineconeVectorStore.

Method Summary

Modifier and Type	Method	Description
void	add(List<Document> documents)	Adds a list of documents to the vector store.
Optional<Boolean>	delete(List<String> documentIds)	Deletes a list of documents by their IDs.
List<Document>	similaritySearch(SearchRequest request)	Retrieves documents by query embedding similarity and metadata filters to retrieve exactly the number of nearest-neighbor results that match the request criteria.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface java.util.function.Consumer

andThen

Methods inherited from interface org.springframework.ai.vectorstore.VectorStore

accept, similaritySearch

Field Details

filterExpressionConverter

public final PineconeFilterExpressionConverter filterExpressionConverter

Constructor Details

PineconeVectorStore

public PineconeVectorStore(PineconeVectorStore.PineconeVectorStoreConfig config,
 EmbeddingClient embeddingClient)

Constructs a new PineconeVectorStore.

Parameters:

config - The configuration for the store.

embeddingClient - The client for embedding operations.

Method Details

add

public void add(List<Document> documents)

Adds a list of documents to the vector store.

Specified by:

add in interface VectorStore

Parameters:

documents - The list of documents to be added.

delete

public Optional<Boolean> delete(List<String> documentIds)

Deletes a list of documents by their IDs.

Specified by:

delete in interface VectorStore

Parameters:

documentIds - The list of document IDs to be deleted.

Returns:

An optional boolean indicating the deletion status.

similaritySearch

public List<Document> similaritySearch(SearchRequest request)

Description copied from interface: VectorStore

Retrieves documents by query embedding similarity and metadata filters to retrieve exactly the number of nearest-neighbor results that match the request criteria.

Specified by:

similaritySearch in interface VectorStore

Parameters:

request - Search request for set search parameters, such as the query text, topK, similarity threshold and metadata filter expressions.

Returns:

Returns documents th match the query request conditions.