Upload RAG Document

mindee.upload_rag_document
ActionAI & modelsconnection required

Calls the Mindee API with the connection's credentials.

Index one document against an extraction model so later inferences can retrieve it for better accuracy.

Connection

Required
Yes — the node will not save without one
Auth type
API key
Providers
Mindee
Secret shape
the V2 API key, or {"api_key": "…"}
Config it needs
base_url, model_id
Resolved by
config.connection_id, else node.connection_id

Configuration

3 fields, 1 required. A dotted path is a nested object and name[] an array of objects — the editor renders the same tree.

FieldTypeRequiredDefaultConstraintsExample
model_id
UUID of the Mindee model to run. Defaults to the connection's model_id, which is how one credential can drive an invoice model from one node and a passport model from the next.
stringNo——a1b2c3d4-0000-4000-8000-000000000000
file_content
The document to index, base64-encoded.
stringYes——JVBERi0xLjQK
filename
Name to store the document under; defaults to document.pdf.
stringNodocument.pdf——

Example configuration

Every value below is the contract’s own example or default — nothing invented.

{
  "file_content": "JVBERi0xLjQK",
  "filename": "document.pdf",
  "model_id": "a1b2c3d4-0000-4000-8000-000000000000"
}

Output

One shape.

result

FieldTypeExample
id
UUID of the RAG document.
string—
model_id
UUID of the extraction model it is indexed against.
string—
filename
Original file name of the indexed document.
string—
created_at
When the document was indexed, ISO 8601.
string—
status
Processing, Failed, Draft or Active.
string—
total_matches
How many inferences have used this document.
number—
last_match_at
When it was last used by an inference, ISO 8601.
string—
{
  "created_at": "",
  "filename": "",
  "id": "",
  "last_match_at": "",
  "model_id": "",
  "status": "",
  "total_matches": 0
}

Notes

  • This is the one Mindee route that only accepts multipart/form-data, so the file is uploaded as bytes rather than as a URL.
  • A freshly uploaded document is created in Draft; use mindee.update_rag_document to make it Active.

See Upload RAG Document run in a workflow.

In a technical demo we add the Mindee connection, drop the node on the canvas and let Workflow Health pre-flight it before the first real run.