Learn to build a private OCR system using the Llama 3.2 visual model in this 17-minute technical demonstration video. Explore how to convert images and scanned documents into structured Markdown while maintaining formatting integrity for tables, lists, and spreadsheets. Follow along with hands-on demonstrations using both the web interface and Colab environment, with practical code examples in JavaScript and Python. Discover pricing details, documentation from Together.AI, and explore a specialized implementation for Thai OCR. Master the process of setting up and utilizing LlamaOCR through step-by-step tutorials, complete with working code snippets and real-world applications.
Overview
Syllabus
LlamaOCR Project
Demo Using their Site
Colab Demo
Together.AI Docs
Pricing
Python OCR Version
Thai OCR Project
Patreon
Taught by
Sam Witteveen
Related Courses
-
Optical Character Recognition (OCR) with Document AI (Python)
-
Extracting Structured Data from Images with OCR and LLM
-
Computer Vision: OCR Tesseract for Different Formats and File Types
-
Computer Vision OCR Space: Using OCR Space for PDF and Image Text Extraction
-
Azure AI Computer Vision OCR: Image and Document Intelligence Services
-
Building Local LLMs for OCR, Object Detection and Image Parsing Using Mono-InternVL
