Short answer: Drop the "Pinecone → Query Pinecone Vectors" action anywhere in your workflow, map the inputs from upstream nodes, and publish.
Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.
| Field | Type | Required | Description |
|---|---|---|---|
Query Vector (JSON array) vector | string | Required | The embedding vector to search with |
Top K topK | string | Required | Number of nearest results to return |
Namespace namespace | string | Optional | Namespace. Example: default |
Include Metadata includeMetadata | options | Optional | Include Metadata. Options: Yes, No |
{"vector": "[0.1, 0.2, 0.3, ...]","topK": "10","namespace": "e.g. default","includeMetadata": "{{trigger.includeMetadata}}"}
{"matches": [{"id": "doc1","score": 0.95,"metadata": {"text": "Relevant document text..."}}],"namespace": "default"}
Use these fields in downstream nodes for routing, logging, or error handling.
Any of these apps can fire this action as part of a workflow.
Triggered by anything in the catalog. Free tier available. No credit card.