Actions13
- Agent Actions
- Datastore Actions
- Query Actions
- Reranker Actions
- LMUnit Actions
- Parser Actions
Datastore → Ingest Document
AI-generatedSummary
Ingest documents into a datastore from binary input fields, with optional metadata.
Inputs
- datastoreId (required) — ID of the datastore to ingest the document into
- binaryPropertyName — Binary field name(s) on the input item to ingest. Leave empty to use all binary fields.
- metadata — Metadata request in stringified JSON format. custom_metadata is a flat dictionary containing key-value pairs.
- authentication — Choose which authentication method to use
Output shape
{ datastoreId: string, uploaded: [{ itemIndex, property, documentId, fileName?, error? }] }
Returns per-item upload status including document IDs, filenames, and any errors encountered during ingestion.