dragon-okinawa / docling-ocr-pdf

docling-ocr-pdf model leverages Docling's document parsing to perform OCR on various document formats, streamlining text extraction for AI tasks

  • Public
  • 71 runs
  • L40S
  • GitHub
  • License
Iterate in playground

Input

Set the REPLICATE_API_TOKEN environment variable:
export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run dragon-okinawa/docling-ocr-pdf using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "dragon-okinawa/docling-ocr-pdf:26632288fc0a29e51b1ca75b6ad9fd00d1fe6f14bd1add083eb4d0ec96ceec3d",
    "input": {
      "timeout": 120,
      "to_format": "md",
      "from_format": "any"
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

No output yet! Press "Submit" to start a prediction.

Run time and cost

This model runs on Nvidia L40S GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

The docling-ocr-pdf model utilizes the document processing capabilities from the Docling project to perform Optical Character Recognition (OCR) on a variety of document formats, including but not limited to PDFs.

It enables efficient document preprocessing, making textual data ready for generative AI tasks.