Process large documents with OCR using SubworkflowAI and Gemini
Documents & extraction workflow for n8n with 10 active steps. Starts with Manual Trigger. Uses Google Gemini. Integrations include Google Drive, Google Gemini.
What it does
10 active nodes · Starts with Manual Trigger.
Steps in the template include:
- Wait (Wait)
- Check Job Status (HTTP Request)
- Get Dataset Items (HTTP Request)
- Get Dataset (HTTP Request)
Nodes and integrations
- Wait
- HTTP Request ×4
- Manual Trigger
- Google Drive
- Split Out
- If
- Google Gemini
See the author’s step names
- Wait (Wait)
- Check Job Status (HTTP Request)
- Get Dataset Items (HTTP Request)
- Get Dataset (HTTP Request)
- When clicking ‘Execute workflow’ (Manual Trigger)
- Download file (Google Drive) — download
- Split Out (Split Out)
- Extract API (HTTP Request)
- Job Complete? (If)
- Document OCR via VLM (Google Gemini) — image / analyze
Accounts and credentials
- Google Drive
- Google Gemini access
Credential types in the graph: httpHeaderAuth, googleDriveOAuth2Api, googlePalmApi
Check the HTTP request steps for any additional service accounts or API keys.
AI models and swaps
Google Gemini · Model or API operation
models/gemini-2.5-flash in Document OCR via VLM. Provider-specific step. A different provider requires edits and testing.
Resource information
- Credit basis
- Author listed by n8n
- Pricing
- Template access shown on n8n
- License
- Not specified
- Last record update
- Nov 5, 2026