Aparavi DTC
Complete Aparavi DTC platform with OCR, parsing, transcription, PII censoring, and custom pipelines
Actions10
Overview
This node integrates with the Aparavi DTC platform to perform various document and data processing operations such as OCR, parsing, audio transcription, PII anonymization, and executing custom pipelines. It supports processing input from file paths, binary data, or text data, making it versatile for workflows involving document analysis, audio processing, and data privacy compliance. For example, it can extract text from PDFs, transcribe audio files, anonymize personal data in text, or run user-defined processing pipelines.
Use Case Examples
- Extract text from a scanned PDF using Simple OCR.
- Transcribe an audio recording to text with Audio Transcribe.
- Anonymize sensitive personal information in text data for GDPR compliance.
- Run a custom JSON-defined processing pipeline on a document.
Properties
| Name | Meaning |
|---|---|
| File Path | Full path to the file to process when input type is 'file'. |
| Binary Property | Name of the binary property containing the file to process when input type is 'binary'. |
| Text Data | Text data to process when input type is 'text'. |
| Pipeline JSON | Custom pipeline configuration in JSON format for the Custom Pipeline operation. |
| Options | Additional options including custom base URL for the API, timeout in seconds, and retry attempts on failure. |
Output
JSON
json- The JSON output contains the results of the processing operation, such as extracted text, parsed data, transcription results, anonymized text, or pipeline execution status and results.
Dependencies
- Requires an Aparavi API key credential for authentication.
- Uses the AparaviClient from the 'aparavi-client' library to communicate with the Aparavi platform.
Troubleshooting
- Ensure that the Aparavi API credentials are correctly configured; missing or invalid API keys will cause authentication errors.
- For file inputs, verify that the file path is correct and accessible by the node.
- When using binary input, ensure the binary property name matches the property containing the file data.
- Invalid JSON format in the Pipeline JSON property will cause parsing errors; validate JSON before use.
- Connection errors to the Aparavi service may occur; the node retries on connection failures but persistent issues may require checking network connectivity or API endpoint availability.
- Operations that do not support text input will throw errors if text data is provided instead of file or binary data.