Hacker News new | past | comments | ask | show | jobs | submit | from login

Replace OCR with Vision Language Models (github.com/vlm-run) 292 points by EarlyOom 49 days ago | past | 125 comments Show HN: Visually parse an entire YouTube video frame by frame (github.com/vlm-run) 5 points by EarlyOom 54 days ago | past A Node.js SDK for calling Vision Language Models (github.com/vlm-run) 6 points by EarlyOom 55 days ago | past Run structured extraction on documents/images locally with Ollama and Pydantic (github.com/vlm-run) 170 points by EarlyOom 56 days ago | past | 29 comments

Join us for AI Startup School this June 16-17 in San Francisco! Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search: