Document → Process
AI-generatedOverview
This node processes documents using the Unstract API. It uploads a document's binary data to the API, waits for the processing to complete, and returns the processed document data including optional metadata and metrics. This node is useful for automating document analysis, extraction, or transformation workflows where documents need to be processed by Unstract's service.
Use Case Examples
- Automate invoice processing by uploading invoice PDFs and extracting structured data.
- Process contracts or legal documents to extract key information and metadata.
- Analyze scanned documents or images to convert them into structured data formats.
Properties
| Name | Meaning |
|---|---|
| File Contents | Name of the binary property that contains the file data to be processed. |
| Unstract Host | Host URL for the Unstract API. |
| API Deployment Name | Name of the API deployment to use. |
| Timeout | Maximum time in seconds to wait for processing. |
| Additional Options | Additional optional parameters for processing such as including metadata, metrics, tags, and using cached results. |
Output
JSON
json- The processed document data returned from the Unstract API, including execution status, metadata, metrics, and any other response details.
Dependencies
- Requires an API key credential for the Unstract API to authenticate requests.
Troubleshooting
- Common issues include missing or incorrect binary data property specified in 'File Contents'. Ensure the binary property exists on the input data.
- Timeout errors if the processing takes longer than the specified timeout parameter. Increase the timeout if needed.
- API errors returned from Unstract such as invalid deployment name or authentication failures. Verify credentials and deployment configuration.
- Unexpected API response structure errors indicate the API response did not contain expected fields. Check API version and deployment status.