Skip to main content

Class: PineconeVectorStore

Provides support for writing and querying vector data in Pinecone.

Extends​

Implements​

Constructors​

new PineconeVectorStore()​

new PineconeVectorStore(params?): PineconeVectorStore

Parameters​

• params?: PineconeParams

Returns​

PineconeVectorStore

Overrides​

VectorStoreBase.constructor

Defined in​

packages/llamaindex/src/vector-store/PineconeVectorStore.ts:51

Properties​

chunkSize​

chunkSize: number

Defined in​

packages/llamaindex/src/vector-store/PineconeVectorStore.ts:48

db?​

optional db: Pinecone

Defined in​

packages/llamaindex/src/vector-store/PineconeVectorStore.ts:45

embedModel​

embedModel: BaseEmbedding

Inherited from​

VectorStoreBase.embedModel

Defined in​

packages/llamaindex/src/vector-store/types.ts:104

indexName​

indexName: string

Defined in​

packages/llamaindex/src/vector-store/PineconeVectorStore.ts:46

namespace​

namespace: string

Defined in​

packages/llamaindex/src/vector-store/PineconeVectorStore.ts:47

storesText​

storesText: boolean = true

Implementation of​

VectorStoreNoEmbedModel.storesText

Defined in​

packages/llamaindex/src/vector-store/PineconeVectorStore.ts:35

textKey​

textKey: string

Defined in​

packages/llamaindex/src/vector-store/PineconeVectorStore.ts:49

Methods​

add()​

add(embeddingResults): Promise<string[]>

Adds vector record(s) to the table.

Parameters​

• embeddingResults: BaseNode<Metadata>[]

The Nodes to be inserted, optionally including metadata tuples.

Returns​

Promise<string[]>

Due to limitations in the Pinecone client, does not return the upserted ID list, only a Promise resolve/reject.

TODO​

Does not create or insert sparse vectors.

Implementation of​

VectorStoreNoEmbedModel.add

Defined in​

packages/llamaindex/src/vector-store/PineconeVectorStore.ts:101

clearIndex()​

clearIndex(): Promise<void>

Delete all records for the current index. NOTE: This operation is not supported by Pinecone for "Starter" (free) indexes.

Returns​

Promise<void>

The result of the delete query.

Defined in​

packages/llamaindex/src/vector-store/PineconeVectorStore.ts:90

client()​

client(): Promise<Pinecone>

Connects to the Pinecone account specified in environment vars. This method also checks and creates the named index if not found.

Returns​

Promise<Pinecone>

Pinecone client, or the error encountered while connecting/setting up.

Implementation of​

VectorStoreNoEmbedModel.client

Defined in​

packages/llamaindex/src/vector-store/PineconeVectorStore.ts:76

delete()​

delete(refDocId, deleteKwargs?): Promise<void>

Deletes a single record from the database by id. NOTE: Uses the collection property controlled by setCollection/getCollection.

Parameters​

• refDocId: string

Unique identifier for the record to delete.

• deleteKwargs?: any

Required by VectorStore interface. Currently ignored.

Returns​

Promise<void>

Promise that resolves if the delete query did not throw an error.

Implementation of​

VectorStoreNoEmbedModel.delete

Defined in​

packages/llamaindex/src/vector-store/PineconeVectorStore.ts:137

index()​

index(): Promise<Index<RecordMetadata>>

Returns​

Promise<Index<RecordMetadata>>

Defined in​

packages/llamaindex/src/vector-store/PineconeVectorStore.ts:80

metaWithoutText()​

metaWithoutText(meta): any

Parameters​

• meta: Metadata

Returns​

any

Defined in​

packages/llamaindex/src/vector-store/PineconeVectorStore.ts:216

nodeToRecord()​

nodeToRecord(node): object

Parameters​

• node: BaseNode<Metadata>

Returns​

object

id​

id: any

metadata​

metadata: Metadata

values​

values: number[]

Defined in​

packages/llamaindex/src/vector-store/PineconeVectorStore.ts:225

persist()​

persist(persistPath): Promise<void>

Required by VectorStore interface. Currently ignored.

Parameters​

• persistPath: string

Returns​

Promise<void>

Resolved Promise.

Defined in​

packages/llamaindex/src/vector-store/PineconeVectorStore.ts:197

query()​

query(query, _options?): Promise<VectorStoreQueryResult>

Query the vector store for the closest matching data to the query embeddings

Parameters​

• query: VectorStoreQuery

The VectorStoreQuery to be used

• _options?: any

Returns​

Promise<VectorStoreQueryResult>

Zero or more Document instances with data from the vector store.

TODO​

QUERY TYPES

Implementation of​

VectorStoreNoEmbedModel.query

Defined in​

packages/llamaindex/src/vector-store/PineconeVectorStore.ts:149

saveChunk()​

protected saveChunk(idx, chunk): Promise<boolean>

Parameters​

• idx: Index<RecordMetadata>

• chunk: any

Returns​

Promise<boolean>

Defined in​

packages/llamaindex/src/vector-store/PineconeVectorStore.ts:119

textFromResultRow()​

textFromResultRow(row): string

Parameters​

• row: ScoredPineconeRecord<Metadata>

Returns​

string

Defined in​

packages/llamaindex/src/vector-store/PineconeVectorStore.ts:212

toPineconeFilter()​

toPineconeFilter(stdFilters?): any

Parameters​

• stdFilters?: MetadataFilters

Returns​

any

Defined in​

packages/llamaindex/src/vector-store/PineconeVectorStore.ts:201