Nutlope/llama-ocr
An npm library that uses Llama 3.2 Vision to extract text from images and documents, outputting markdown.
Velocity · 7d
+4.2
★ / day
Trend
→steady
star history
This library provides a free OCR solution by leveraging the Llama 3.2 Vision model via Together AI’s API. Users pass an image file path or URL along with an API key, and the library returns markdown-formatted text extracted from the document. It supports local and remote images and defaults to the 90B vision model for accuracy, with a free tier option using the 11B model.