README.md

metadata

pipeline_tag: image-to-text
library_name: mistralai
license: apache-2.0
language: ar

OCR Arabic Model

موديل OCR قادر على استخراج النصوص من الصور باللغة العربية.

Usage

from mistralai import Mistral, ImageURLChunk
client = Mistral(api_key="HF_TOKEN")
result = client.ocr.process(
    document=ImageURLChunk(image_url="data:image/jpeg;base64,..."),
    model="ocr"
)
print(result)