Pinecone Query

Pinecone Query

Certified

Query a Pinecone index by vector similarity

Queries a Pinecone index for the top-K most similar vectors. Provide either a vector (dense values) or a vectorId (query by existing vector ID). Exactly one of these two must be set. Results can be returned inline (FETCH / FETCH_ONE) or stored as an ION file (STORE).

yaml
type: io.kestra.plugin.pinecone.Query

Query top-5 vectors by a dense vector.

yaml
id: pinecone_query
namespace: company.team

tasks:
  - id: query
    type: io.kestra.plugin.pinecone.Query
    apiKey: "{{ secret('PINECONE_API_KEY') }}"
    indexName: my-embeddings
    namespace: my-namespace
    topK: 5
    vector: [0.1, 0.2, 0.3]
    includeMetadata: true
    fetchType: FETCH

Query and store results to Kestra internal storage.

yaml
id: pinecone_query_store
namespace: company.team

tasks:
  - id: query
    type: io.kestra.plugin.pinecone.Query
    apiKey: "{{ secret('PINECONE_API_KEY') }}"
    indexName: my-embeddings
    topK: 100
    vector: [0.1, 0.2, 0.3]
    fetchType: STORE
Properties

Pinecone API key

Index name

Name of the Pinecone index to operate on.

Number of results to return

DefaultFETCH
Possible Values
FETCHFETCH_ONESTORE

Fetch type

Controls how results are returned. FETCH returns all rows inline, FETCH_ONE returns only the first row, STORE writes all rows to Kestra storage as an ION file.

Metadata filter

Optional filter map applied to restrict matches by metadata fields.

Control-plane host override

Optional URL override for the Pinecone control-plane API. Defaults to https://api.pinecone.io when unset. Set this to point to a local emulator (e.g. http://localhost: 5080).

Defaultfalse

Include metadata in the response

Defaultfalse

Include vector values in the response

Namespace to query

Reference (ref) of the pluginDefaults to apply to this task.

Defaulttrue

Enable TLS for gRPC data-plane connections

Set to false when connecting to a local emulator that does not support TLS. Defaults to true (production Pinecone always requires TLS).

SubTypenumber

Query vector (dense values)

Mutually exclusive with vectorId.

ID of an existing vector to use as the query

Mutually exclusive with vector.

Single result row (FETCH_ONE mode)

SubTypeobject

All result rows (FETCH mode)

Number of matches returned

Formaturi

URI of the ION file containing all rows (STORE mode)

More Plugins in this Category

PostgreSQL
PostgreSQL

Tasks that connect to PostgreSQL via JDBC to run queries and loads.

Data

6 tasks

25 blueprints

Dataform
Dataform

Tasks that run Dataform data transformations through the Dataform CLI.

Data

1 tasks

6 blueprints