Document Understanding API- Extract data from Documents

The Document Understanding API automatically extracts, converts, and interprets content from multiple document formats.
It supports Markdown (default) and JSON outputs and accepts Base64-encoded input files.

Method

POST

Endpoint

{{base_url}}/docUnderstand

Authentication

This API requires the following authentication parameters:

Required Params

• client_id — Your API authentication ID.

Required Headers

• client-secret — Your API authentication secret.
• Content-Type: application/json

Input Formats

The API accepts Base64-encoded file data with an optional output format parameter.

1. Markdown Output (Default)

{
  "file_data": "{%base64data%}"
}

2. Markdown Output (Explicit Format)

{
  "file_data": "{%base64data%}",
  "format": "markdown"
}

3. JSON Output

{
  "file_data": "{%base64data%}",
  "format": "json"
}

Supported File Types

• PDF
• PowerPoint
• Word
• Excel
• Audio files
• HTML
• Text formats (CSV, JSON, XML)
• ZIP archives
• EPUB files

Authentication Instructions