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, Adam Bchouti

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 FilterExpressionConverter	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.
void	add(List<Document> documents, String namespace)	Adds a list of documents to the vector store based on the namespace.
Optional<Boolean>	delete(List<String> documentIds)	Deletes a list of documents by their IDs.
Optional<Boolean>	delete(List<String> documentIds, String namespace)	Deletes a list of documents by their IDs based on the namespace.
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.
List<Document>	similaritySearch(SearchRequest request, String namespace)

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 FilterExpressionConverter 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,
 String namespace)

Adds a list of documents to the vector store based on the namespace.

Parameters:

documents - The list of documents to be added.

namespace - The namespace to add the documents to

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,
 String namespace)

Deletes a list of documents by their IDs based on the namespace.

Parameters:

documentIds - The list of document IDs to be deleted.

namespace - The namespace of the document IDs.

Returns:

An optional boolean indicating the deletion status.

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,
 String namespace)

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.