- Triggers bring documents in
- Actions process them
- Outputs deliver the results
Triggers
Trigger nodes define how documents enter the pipeline. Every pipeline must have at least one trigger.Upload trigger
Accept documents uploaded through the UI
Email trigger
Receive documents via an auto-generated email address
HTTP trigger
Accept documents submitted via the API
Actions
Action nodes process documents and transform data. You can chain multiple actions together.Parse action
Extract raw text from documents using OCR
Extract action
Pull structured data from documents using AI
Review action
Pause for human review and approval
Transform action
Convert data to CSV, JSON, XML, or Excel
Route action
Send documents down different paths based on conditions
Merge action
Combine data from multiple branches
Validation action
Validate data against rules
Outputs
Output nodes deliver results outside DocPipe. They are always the last step in a pipeline path.Summary
| Node | Category | Credit cost | Description |
|---|---|---|---|
| Upload trigger | Trigger | 0 | Accept documents uploaded through the UI |
| Email trigger | Trigger | 0 | Receive documents via email |
| HTTP trigger | Trigger | 0 | Accept documents via the API |
| Parse action | Action | 1–2 per page | OCR text extraction |
| Extract action | Action | 1–5 per page | AI-powered structured data extraction |
| Review action | Action | 0 | Human-in-the-loop review step |
| Transform action | Action | 0 | Format conversion (CSV, JSON, XML, Excel) |
| Route action | Action | 0–0.5 | Conditional routing |
| Merge action | Action | 0 | Multi-branch data merge |
| Validation action | Action | 0 | Data validation (coming soon) |
| Callback output | Output | 0 | Webhook delivery |
| Email output | Output | 0 | Email delivery |