---
name: "hf-space-prithivmlmods-multimodal-ocr"
description: "Use the Hugging Face Space prithivMLmods/Multimodal-OCR."
metadata:
  source: huggingface-space
  spaceId: "prithivMLmods/Multimodal-OCR"
  hubUrl: https://huggingface.co/spaces/prithivMLmods/Multimodal-OCR
  agentsMdUrl: https://huggingface.co/spaces/prithivMLmods/Multimodal-OCR/agents.md
  appUrl: https://prithivmlmods-multimodal-ocr.hf.space
---

# Hugging Face Space: prithivMLmods/Multimodal-OCR

Use this skill when the user wants to use the Hugging Face Space `prithivMLmods/Multimodal-OCR`.

- Space page: https://huggingface.co/spaces/prithivMLmods/Multimodal-OCR
- App URL: https://prithivmlmods-multimodal-ocr.hf.space
- Source instructions: https://huggingface.co/spaces/prithivMLmods/Multimodal-OCR/agents.md

## Space agent instructions

To use this application (prithivMLmods/Multimodal-OCR: Extract text from images with multiple OCR models):
API schema: GET https://prithivmlmods-multimodal-ocr.hf.space/gradio_api/info
Call endpoint: POST https://prithivmlmods-multimodal-ocr.hf.space/gradio_api/call/v2/{endpoint} {"param_name": value, ...}
Poll result: GET https://prithivmlmods-multimodal-ocr.hf.space/gradio_api/call/{endpoint}/{event_id}
File inputs: POST https://prithivmlmods-multimodal-ocr.hf.space/gradio_api/upload -F "files=@file.ext", use as: {"path": "<returned-path>", "meta": {"_type": "gradio.FileData"}, "orig_name": "file.ext"}
Auth: Bearer $HF_TOKEN (https://huggingface.co/settings/tokens)
