Aparavi DTC icon

Aparavi DTC

Complete Aparavi DTC platform with OCR, parsing, transcription, PII censoring, and custom pipelines

Overview

This node integrates with the Aparavi DTC platform to perform various document and data processing operations such as OCR (Optical Character Recognition), document parsing, audio transcription, audio summarization, PII (Personally Identifiable Information) anonymization, and advanced parsing. It supports processing input from local files, binary data from previous nodes, or direct text input. The node is useful for automating data extraction and analysis workflows, such as extracting text from scanned documents, transcribing audio files, or anonymizing sensitive information in text data.

Use Case Examples

  1. Extract text from a scanned PDF document using Simple OCR.
  2. Transcribe an audio recording to text using Audio Transcribe.
  3. Anonymize personal data in a text input to comply with privacy regulations.
  4. Parse structured data from documents using the Advanced Parser operation.

Properties

Name Meaning
Input Type Specifies the type of input data to process: a file path, binary data from a previous node, or text data.
File Path Full path to the file to process (used when Input Type is 'File Path').
Binary Property Name of the binary property containing the file to process (used when Input Type is 'Binary Data').
Text Data Text data to process (used when Input Type is 'Text Data').
Options Additional options for the operation including custom API base URL, timeout in seconds, and number of retry attempts on failure.

Output

JSON

  • json - The JSON output contains the results of the selected operation, such as extracted text, parsed data, transcription results, anonymized text, or pipeline execution status.

Dependencies

  • Requires an Aparavi API key credential for authentication to the Aparavi DTC 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.
  • Text input is only supported for the Anonymize PII operation; using text input for other operations will cause errors.
  • Network connection issues to the Aparavi service may cause retries; check connectivity and API endpoint availability.
  • Invalid pipeline JSON for custom pipeline operation will cause parsing errors; ensure the JSON is well-formed.

Discussion