Short answer: Drop the "Weaviate → Insert Object" 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 |
|---|---|---|---|
Collection collection | string | Required | Document |
Properties properties | object | Required | Object data. Keys must match schema. |
Vector (optional) vector | array | Optional | Precomputed embedding. Skip to let Weaviate's vectorizer compute it. |
UUID (optional) id | string | Optional | Custom UUID. Weaviate auto-generates if omitted. |
{"collection": "Document","properties": "{ \"content\": \"...\", \"source\": \"doc.pdf\" }","vector": "{{trigger.vector}}","id": "{{trigger.id}}"}
{"id": "abc-123-def-456","class": "Document","properties": {"content": "..."}}
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.