Process Document
document_ai.process_document
ActionGoogle Cloudconnection required
Calls the Document AI API POST /v1/.../processors/{id}:process.
Run a Document AI processor on a PDF/image; emits text and entities.
Connection
- Required
- Yes — the node will not save without one
- Auth type
- OAuth 2.0
- Providers
- Google Document AI
- Secret shape
- {"client_id", "client_secret", "refresh_token"}
- Config it needs
- project_id, location, processor_id
- Resolved by
- config.connection_id, else node.connection_id
Configuration
5 fields, none 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 |
|---|---|---|---|---|---|
project_id GCP project id (overrides connection). | string | No | — | — | — |
location Processor location: us or eu (overrides connection). | string | No | — | — | — |
processor_id Processor id (overrides connection). | string | No | — | — | — |
file_content Document as base64. Leave empty to use the upstream file envelope. | string | No | — | — | — |
mime_type MIME type (defaults to the upstream file's, else application/pdf). | string | No | — | — | — |
Input
| Field | Type | Example |
|---|---|---|
file_content The file, base64-encoded. | string | — |
content_encoding | string | base64 |
filename | string | app-main.zip |
content_type | string | application/zip |
size Raw size in bytes (before base64). | number | — |
Output
One shape.
result
| Field | Type | Example |
|---|---|---|
ok | boolean | — |
text Full extracted text. | string | — |
entities[].type | string | — |
entities[].mention_text | string | — |
entities[].confidence | number | — |
entities[].normalized_value | any | — |
entity_count | number | — |
pages Page count. | number | — |
{
"entities": [
{
"confidence": 0,
"mention_text": "",
"normalized_value": null,
"type": ""
}
],
"entity_count": 0,
"ok": false,
"pages": 0,
"text": ""
}Notes
- Inline documents are capped at 20 MB / 15 pages by Google; use Batch Process beyond.
Related Google Document AI nodes
Solutions with Google Document AI
See Process Document run in a workflow.
In a technical demo we add the Google Document AI connection, drop the node on the canvas and let Workflow Health pre-flight it before the first real run.