Vision Parse: Parse PDF Documents into Markdown Using Vision LLMs Posted by doctorbryan on Thursday December 19, 2024 @12:58PM from the github.com dept. https://github.com/iamarunbrahma/vision-parse ( 3 comments | 3 points | on HN )
- Smart Content Extraction: Intelligently identifies and extracts text and tables with high precision
- Content Formatting: Preserves document hierarchy, styling, and indentation for markdown formatted content
- Multi-LLM Support: Supports multiple Vision LLM providers i.e. OpenAI, LLama, Gemini etc. for accuracy and speed
- PDF Document Support: Handle multi-page PDF documents effortlessly by converting each page into byte64 encoded images
- Local Model Hosting: Supports local model hosting using Ollama for secure document processing and for offline use