Query
pinecone.query
ActionDatabases & warehousesconnection required
Calls the Pinecone data API POST /query.
Find the nearest vectors to a query vector in a Pinecone index.
Connection
- Required
- Yes — the node will not save without one
- Auth type
- API key
- Providers
- Pinecone
- Secret shape
- the Pinecone API key
- Config it needs
- index_host, namespace
- Resolved by
- config.connection_id, else node.connection_id
Configuration
4 fields, 1 required. A dotted path is a nested object and name[] an array of objects — the editor renders the same tree.
| Field | Type | Required | Default | Constraints | Example |
|---|---|---|---|---|---|
vector Query vector (array of floats). JSON or {{ }}. | array | Yes | — | array of number | — |
top_k Number of matches (1-1000). | number | No | 5 | 1–10000 | — |
namespace Namespace (overrides connection). | string | No | — | — | — |
filter Optional metadata filter (JSON). | object | No | — | — | — |
Example configuration
Every value below is the contract’s own example or default — nothing invented.
{
"top_k": 5
}Output
One shape.
result
| Field | Type | Example |
|---|---|---|
matches | array | — |
count | number | — |
{
"count": 0,
"matches": []
}Related Pinecone nodes
See Query run in a workflow.
In a technical demo we add the Pinecone connection, drop the node on the canvas and let Workflow Health pre-flight it before the first real run.