Nodes are the building blocks of pipelines. You connect them with edges to define how data flows from start to finish. Nodes are divided into three categories that follow the natural flow of data:Documentation Index
Fetch the complete documentation index at: https://docs.ingestly.ai/llms.txt
Use this file to discover all available pages before exploring further.
- 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
Webhook trigger
Accept documents submitted via the API
Forward trigger
Accept documents forwarded from another pipeline
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
Classify action
Classify documents by content type using rules or AI
Review action
Pause for human review and approval
Transform action
Reshape, convert, or script-process data
Route action
Send documents down different paths based on conditions
Merge action
Combine data from multiple branches
Validation action
Validate data with rules, schemas, endpoints, scripts, or AI
HTTP action
Call an external HTTP endpoint and use the response
Outputs
Output nodes deliver results outside Ingestly. They are always the last step in a pipeline path.Callback output
Send results to an external webhook URL
Email output
Send results via email
Forward output
Forward the document to another pipeline
Beta nodes
Some nodes are marked with a Beta badge in the pipeline editor. Beta nodes are fully functional but may change in future releases. Currently, the merge action and HTTP action are in beta.Summary
| Node | Category | Description |
|---|---|---|
| Upload trigger | Trigger | Accept documents uploaded through the UI |
| Email trigger | Trigger | Receive documents via email |
| Webhook trigger | Trigger | Accept documents via the API |
| Forward trigger | Trigger | Accept documents forwarded from another pipeline |
| Parse action | Action | OCR text extraction |
| Extract action | Action | AI-powered structured data extraction |
| Classify action | Action | Document classification by rules or AI similarity |
| Review action | Action | Human-in-the-loop review step |
| Transform action | Action | Format conversion, field mapping, or custom script |
| Route action | Action | Conditional routing |
| Merge action | Action | Multi-branch data merge |
| Validation action | Action | Data validation with rules, schemas, endpoints, scripts, or AI |
| HTTP action | Action | External HTTP endpoint integration |
| Callback output | Output | Webhook delivery |
| Email output | Output | Email delivery |
| Forward output | Output | Forward the document to another pipeline |