Gemini Document Processor is a powerful document processing tool that uses Google's Gemini AI to generate high-quality Thai language summaries from PDF and EPUB files, with image extraction and Obsidian integration.
Features
AI-Powered Summarization
Uses Google's latest Gemini models to generate comprehensive Thai language summaries from PDF and EPUB files.
Multiple Document Formats
Processes both PDF and EPUB files to accommodate different user needs.
Smart Chunking
Improves AI performance by processing documents in manageable chunks.
Image Extraction
Extracts and filters images from documents based on size thresholds.
Obsidian Integration
Directly exports markdown files into your Obsidian vault with metadata support, including YAML frontmatter.
Web Interface
Provides a clean, tabbed web application for managing the document processing workflow.
Real-time Progress Tracking
Offers live updates and job status monitoring during document processing.