Pinecone Integration

Find the most similar vectors to a query vector (similarity search).

8 fields

Insert or overwrite vectors in an index.

3 fields

Fetch vectors by their IDs.

3 fields

Delete vectors by ID, by metadata filter, or clear a namespace.

5 fields

Partially update values or metadata on a single existing vector.

5 fields

List vector IDs in a namespace by prefix (serverless indexes only).

5 fields

Get per-namespace vector counts, total dimension, and index fullness.

2 fields

Get full details for a single index: status, host, metric, dimension, spec.

1 field

Create a new serverless index.

6 fields

Change deletion protection or pod replica/type on an existing index.

4 fields

Delete an index and all its vectors permanently.

1 field

Create a text-native index that embeds content server-side (no dimension needed).

5 fields

Upsert text records into a text-native index (server-side embedding, no vectors needed).

3 fields

Search a text-native index with a text query (server-side embedding + optional rerank).

7 fields

Generate dense embeddings using Pinecone's hosted models.

4 fields

Rerank a set of documents against a query using Pinecone's reranking model.

6 fields

Start an async bulk import of Parquet vectors from S3, GCS, or Azure Blob.

4 fields

List all bulk import operations for an index.

3 fields

Get the status and details of a specific bulk import operation.

2 fields

Cancel a pending or in-progress bulk import operation.

2 fields

Upload a document file, chunk + embed it with text-embedding-3-small, and upsert.

6 fields