Indra OCR

by datalab-toco.huggingface.datalab-to/indra-ocr

  • Remote endpoint
  • 2 tools

Tools

  • indra_ocr_convert_file Read a PDF or image document: markdown / plain text / JSON, with layout. Indra OCR detects every text line and every layout block (headings, lists, tables, captions, footnotes...), orders them for reading, and writes the page as markdown. Digital PDFs are read through their own text layer where it passes Indra's checks; scans and images go through the OCR models. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool
  • indra_ocr_convert_file_1 Read a PDF or image document: markdown / plain text / JSON, with layout. Indra OCR detects every text line and every layout block (headings, lists, tables, captions, footnotes...), orders them for reading, and writes the page as markdown. Digital PDFs are read through their own text layer where it passes Indra's checks; scans and images go through the OCR models. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool

As the server's own listing gives them. We never call a tool.