Base44
Mini toolsolmOCR
By Ai2
olmOCR provides both a toolkit and LLM-sized OCR models for high-fidelity document linearization. It focuses on turning messy PDFs or scanned pages into structured text suitable for downstream LLMs, with attention to layout, tables, math, and handwritten content. The project ships several 7B and 8B image-to-text models plus a pipeline that outputs markdown, making it a strong backbone for building RAG systems or datasets from large scientific and business corpora.
New
Image
Gen 4
Overview
olmOCR is AllenAI’s open-source document recognition pipeline and model family that converts PDFs and images into clean text, preserving reading order, tables, equations, and handwriting.
About Ai2
We are a Seattle based non-profit AI research institute founded in 2014 by the late Paul Allen. We develop foundational AI research and innovation to deliver real-world impact through large-scale open models, data, robotics, conservation, and beyond.
Website:
allenai.org
Tools using olmOCR
No tools found for this model yet.
Last updated: February 12, 2026
