Skip to main content

Class: PineconeVectorStore

Defined in: packages/agentos/src/rag/implementations/vector_stores/PineconeVectorStore.ts:62

Interface​

IVectorStore

Description​

Defines the contract for interacting with a specific vector database or storage backend. Implementations will wrap specific clients (e.g., Pinecone client, Weaviate client, in-memory store logic).

Implements​

Constructors​

Constructor​

new PineconeVectorStore(config): PineconeVectorStore

Defined in: packages/agentos/src/rag/implementations/vector_stores/PineconeVectorStore.ts:66

Parameters​

config​

PineconeVectorStoreConfig

Returns​

PineconeVectorStore

Methods​

close()​

close(): Promise<void>

Defined in: packages/agentos/src/rag/implementations/vector_stores/PineconeVectorStore.ts:89

No-op — Pinecone is cloud-managed.

Returns​

Promise<void>

createCollection()​

createCollection(_name, _options?): Promise<void>

Defined in: packages/agentos/src/rag/implementations/vector_stores/PineconeVectorStore.ts:111

Create a "collection" — in Pinecone this maps to a namespace. Namespaces are created implicitly on first upsert, so this is a no-op.

Parameters​

_name​

string

_options?​

CreateCollectionOptions

Returns​

Promise<void>

Implementation of​

IVectorStore.createCollection

delete()​

delete(collectionName, options): Promise<DeleteResult>

Defined in: packages/agentos/src/rag/implementations/vector_stores/PineconeVectorStore.ts:274

Delete vectors by ID or delete all in namespace.

Parameters​

collectionName​

string

options​

DeleteOptions

Returns​

Promise<DeleteResult>

Implementation of​

IVectorStore.delete

dropCollection()​

dropCollection(name): Promise<void>

Defined in: packages/agentos/src/rag/implementations/vector_stores/PineconeVectorStore.ts:122

Drop a "collection" — deletes all vectors in the namespace.

Parameters​

name​

string

Returns​

Promise<void>

healthCheck()​

healthCheck(): Promise<boolean>

Defined in: packages/agentos/src/rag/implementations/vector_stores/PineconeVectorStore.ts:94

Health check — verify index is reachable.

Returns​

Promise<boolean>

hybridSearch()​

hybridSearch(collectionName, queryEmbedding, _queryText, options?): Promise<QueryResult>

Defined in: packages/agentos/src/rag/implementations/vector_stores/PineconeVectorStore.ts:257

Hybrid search is not natively supported by Pinecone in a single call. Falls back to dense-only query. For true hybrid search, use Postgres or Qdrant backends which support server-side RRF fusion.

Parameters​

collectionName​

string

queryEmbedding​

number[]

_queryText​

string

options?​

QueryOptions

Returns​

Promise<QueryResult>

Implementation of​

IVectorStore.hybridSearch

initialize()​

initialize(): Promise<void>

Defined in: packages/agentos/src/rag/implementations/vector_stores/PineconeVectorStore.ts:75

Verify connectivity by calling the describe index stats endpoint.

Returns​

Promise<void>

Implementation of​

IVectorStore.initialize

query()​

query(collectionName, queryEmbedding, options?): Promise<QueryResult>

Defined in: packages/agentos/src/rag/implementations/vector_stores/PineconeVectorStore.ts:188

Query for top-K nearest neighbors via Pinecone's query endpoint. Supports metadata filtering via Pinecone's native filter syntax.

Parameters​

collectionName​

string

queryEmbedding​

number[]

options?​

QueryOptions

Returns​

Promise<QueryResult>

Implementation of​

IVectorStore.query

upsert()​

upsert(collectionName, documents, _options?): Promise<UpsertResult>

Defined in: packages/agentos/src/rag/implementations/vector_stores/PineconeVectorStore.ts:139

Upsert vectors into Pinecone. Batches automatically in chunks of 100 (Pinecone's max batch size).

Parameters​

collectionName​

string

documents​

VectorDocument[]

_options?​

UpsertOptions

Returns​

Promise<UpsertResult>

Implementation of​

IVectorStore.upsert