- Introduction
- Getting started
- Build on any canvas
- Build with Case
- Reference
- Defining case keys (system vs. external)
- Establishing task I/O and write-back contracts
- Modeling primary and secondary stages
- Triggering a case from Data Fabric
- Implementing stage-level personas and permissions
- Setting SLAs and automated escalation rules
- Configuring a rework loop (re-entry)
- Configuring and testing the Case Manager Agent (preview)
- Build with Flow
- Summarize document
- Extract
- Build with BPMN
- Operating
- Monitoring
- Optimizing
- Reference information
Extract
Extract structured fields from documents using IXP extraction models.
The Extract node pulls structured fields out of a document (an invoice, receipt, form, or contract) using a UiPath Intelligent Xtraction and Processing (IXP) model, and returns the result for downstream nodes to act on. Use it when a step in your process needs typed data lifted out of an unstructured file.
To build, evaluate, deploy, and use the model behind the Extract node, check the IXP in Flow guide.
Add an Extract node
The Extract node runs an IXP extraction model. You can use a model that already exists, or create a new one in the node.
- Select + on the handle of the node it follows, then select Document > Extract.
- Select one of these options:
- Extract document (Preview): adds a node with a new model, which you build and evaluate in the node.
- In this solution: reuses the model of an Extract node in another workflow of the same solution.
- Published: uses a deployed IXP model, such as one deployed from IXP or from the Extract node of another workflow. Each model appears as its own node. You need access to the place where the model is deployed.
The Extract node requires both the IXP and Document Understanding services, even when you only use IXP models. Enabling or disabling services describes how to turn them on.
When the node runs, Maestro Orchestrate sends the document to the model, the model digitizes and extracts it, and the structured result returns on the node's output. The node waits for the model to finish before continuing, so allow time for large documents.
Build, evaluate, and deploy the model
If you create the model with Extract document, you build and evaluate it in the node. When you deploy the solution, the model deploys with it. A Published model is read-only in the node. The IXP in Flow guide describes each task:
| Task | Page in the IXP in Flow guide |
|---|---|
| Add, configure, and remove the node, and open the definition of its model | Managing Extract nodes |
| Upload sample documents | Uploading sample documents |
| Define the taxonomy: the fields that the model extracts | Defining the taxonomy |
| Review and correct the predictions of the model | Reviewing predictions |
| Measure how well the model performs before you deploy it | Model evaluation |
| Deploy the model with the solution and manage its deployed versions | Model deployment |
| Use a model from IXP, from this workflow, or from another workflow | Consuming models via Flow |
| Learn what happens when a document exceeds the token or page limit of the model | Document processing limits |
Configuration
Configure the Extract node in the properties panel after adding it to the canvas.
| Field | Required | Default | Description |
|---|---|---|---|
| File | Yes | None | The document to extract from. Bind it to a file produced earlier in the workflow, such as the output of a trigger or of an earlier node. |
| Page range | No | Empty | The pages to extract from, for example 1-5. Leave it empty to process the whole document. |
| Definition | Not applicable | None | A summary of the node's model: its version and evaluation results, the annotated documents, and the fields it extracts. Edit opens the full view, where you set up the model and its fields. |
Output
The Extract node returns its result at $vars.<nodeId>.output, with these keys:
versiontyperesulttaxonomymetadata
The fields inside result depend on the fields your model extracts. To see them, debug the workflow, open the node's expanded view, and check the Output column. It shows the output of the last run as Schema, JSON, or Extraction result. Before the node runs, the keys have no values. Output in the IXP in Flow guide describes the panel.
To test later nodes without running an extraction, change the mode of the Output column from Live to Static mock, a value you define, or Generated, a response that an LLM generates. Output mocking describes both.
Error handling
On the Error handling tab, select Enable error handling. The node then has an error output handle. If the extraction fails, the run continues on the error path, and the error is at $vars.<nodeId>.error, with the code, message, detail, category, and status keys. Error handling describes how to route on it.
Notes
- Published lists the models that are deployed when you open the Add node panel. After you deploy a new model, open the panel again to see it.
Next steps
- IXP in Flow guide: build, evaluate, and deploy the model behind the node.
- Document processing: how the document nodes work together.
- Analyze files: extract data from a file step by step.