The classify node sends each document page to a specific output branch based on its content. Use it to sort incoming documents by type, topic, or any other classification criteria before applying downstream processing.Documentation Index
Fetch the complete documentation index at: https://docs.docpipe.ai/llms.txt
Use this file to discover all available pages before exploring further.
When to use classify
- You receive mixed document types through one trigger and need to apply different processing to each.
- Different document types call for different extract schemas. Classifying upstream lets each branch use a focused schema instead of one mega-schema covering everything.
- You want to drop or quarantine documents that don’t fit any expected type. Use the
otheroutput for unmatched pages. - Use route instead when you’re filtering on a metadata condition that doesn’t require reading the document content.
Configuration
| Field | Type | Required | Description |
|---|---|---|---|
| Mode | select | Yes | Classification method: Rules or AI |
| Routing Rules | rule editor | When mode is Rules | Conditions that determine which output branch each page follows |
| Target Pipes | pipe picker | When mode is AI | Pipes to match pages against. Only pipes with a Forward Trigger are selectable |
| Confidence Threshold | number | When mode is AI | Minimum similarity score (0–1). Pages below it route to the other output. Defaults to 0.7 |
| Force OCR | toggle | No | Forces OCR processing on the document before classification, even when it contains selectable text |
Modes
Rules
Define conditions that match page content or page numbers. Each rule maps to a different output edge. Rules accept Contains text, Not contains text, and Page numbers.AI
Uses AI embedding similarity to match pages against reference documents in your target pipes. Select one or more Target Pipes. Each target pipe must have a Forward Trigger with reference documents so DocPipe can compare incoming pages against it. Set the Confidence Threshold to control how strict the match must be. Pages with a similarity score at or above the threshold are forwarded to the matching pipe; pages below fall through to theother output so you can handle them separately.
Inputs and outputs
Allowed inputs: Trigger nodes, route, parse, review. Output: Pages routed to the matching output edge, or to theother edge if no classification matched.
Credits
See credits for pricing. Rules mode costs 0.5 credits per page; AI mode costs 0.2 credits per page. Generating embeddings on the forward trigger when you upload reference documents is billed separately at 0.2 credits per page per reference document.Related
Classify best practices
Pick a mode, write criteria, and tune confidence
Conditional routing guide
Patterns for branching pipelines on document type
Forward trigger
Configure reference documents for AI classification
Extract action
Extract data after classifying by document type