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 data processing operations including OCR, document parsing, audio transcription, audio summarization, PII anonymization, advanced parsing, and PII censoring for USA, international, and HIPAA healthcare data. It supports processing input from file paths, binary data, or text data and can handle custom pipelines as well. The node is useful for automating data extraction, transcription, and sensitive data redaction in workflows, such as censoring personal information in documents or audio files before further processing or storage.
Use Case Examples
- Censor international personally identifiable information (PII) in text data fields extracted from documents.
- Perform OCR on a PDF file to extract text for further analysis.
- Transcribe audio files to text and then anonymize PII in the transcription.
Properties
| Name | Meaning |
|---|---|
| Input Type | Specifies the type of input data to process: file path, binary data, or text data. |
| File Path | Full path to the file to process (shown when Input Type is 'File Path'). |
| Binary Property | Name of the binary property containing the file to process (shown when Input Type is 'Binary Data'). |
| Text Data | Text data to process (shown when Input Type is 'Text Data'). |
| Input Data Mode | Determines whether to process all fields or only specific fields in the input data (used for PII censor operations). |
| Fields to Process | Comma-separated list of field names to process when Input Data Mode is 'Specific Fields'. |
| Censor Character | Character used to censor detected PII in the output. |
| Options | Additional options including custom API base URL, timeout in seconds, and retry attempts on failure. |
Output
JSON
json- The main output containing the processed results such as censored text, parsed data, transcriptions, or pipeline execution status.
Dependencies
- Requires an Aparavi API key credential for authentication to the Aparavi DTC platform.
Troubleshooting
- Ensure the Aparavi API credentials are correctly configured; missing or invalid API keys will cause authentication errors.
- File input operations require valid file paths or binary data; invalid paths or missing binary properties will cause errors.
- Text input is only supported for certain operations like Anonymize PII; using text input for unsupported operations will throw errors.
- Custom pipeline JSON must be valid JSON format; invalid JSON will cause parsing errors.
- Network connection issues to the Aparavi API WebSocket endpoint may cause retries or failures; check network connectivity and API base URL settings.