| title: AI Tutor Document Processor | |
| emoji: 📚 | |
| colorFrom: blue | |
| colorTo: purple | |
| sdk: gradio | |
| sdk_version: 6.26.0 | |
| python_version: "3.12" | |
| app_file: app.py | |
| pinned: false | |
| license: apache-2.0 | |
| short_description: AI Tutor document processing and normalization | |
| # AI Tutor Document Processor | |
| Document processing service for the AI Tutor platform. | |
| ## Pipeline | |
| Document | |
| → Docling | |
| → Structured Document | |
| → AI Tutor Normalization | |
| → JSON | |
| ## Features | |
| - PDF processing | |
| - DOCX processing | |
| - PPTX processing | |
| - HTML processing | |
| - Markdown processing | |
| - Text processing | |
| - Heading detection | |
| - Section detection | |
| - Table extraction | |
| - Figure detection | |
| - Activity detection | |
| - Question detection | |
| - Source references | |
| - AI-Tutor document schema | |
| ## Output | |
| The processor produces: | |
| - Raw Docling JSON | |
| - Markdown | |
| - AI-Tutor normalized JSON | |
| - Processing statistics |