PyVisionAI v0.2.7

Features

Extract text and images from documents
Vision Language Models support (OpenAI and Ollama)
Support for PDF, DOCX, PPTX, and HTML files
Interactive HTML page capture

Recent Changes

Added file extractor API diagram
Enhanced documentation with mermaid diagrams
Added retry mechanism for API calls
Improved model factory implementation

Installation

Via PyPI: pip install pyvisionai
Via Homebrew: brew install pyvisionai

Requirements

Python 3.11+
1GB disk space (more for Llama model)