# Hugging Face Spaces Configuration # MarkItDown Testing Platform Metadata title: "MarkItDown Testing Platform" emoji: "🚀" colorFrom: "blue" colorTo: "purple" sdk: "gradio" sdk_version: "4.44.1" app_file: "app.py" python_version: "3.11" # Space configuration models: - google/gemini-pro - microsoft/markitdown datasets: [] # Space settings pinned: false license: "mit" duplicated_from: null # Hardware requirements (for paid tiers) # hardware: "t4-medium" # Uncomment for GPU acceleration # Environment variables (public - no secrets here) variables: GRADIO_THEME: "soft" MAX_FILE_SIZE_MB: "50" PROCESSING_TIMEOUT: "300" APP_VERSION: "1.0.0" # App metadata short_description: "Enterprise-grade document conversion testing with AI-powered analysis using Microsoft MarkItDown and Google Gemini" # Tags for discoverability tags: - document-processing - ai-analysis - markdown-conversion - enterprise-tools - quality-assessment - microsoft-markitdown - google-gemini - document-conversion - pdf-processing - office-documents # Custom configuration for the space custom: features: - "Multi-format document conversion (PDF, DOCX, PPTX, XLSX, HTML, TXT, CSV, JSON, XML)" - "AI-powered quality analysis with Google Gemini" - "Interactive visualization dashboards" - "Real-time processing metrics" - "Export capabilities (Markdown, HTML, JSON, PDF)" - "Enterprise-grade error handling and recovery" - "Performance optimization and monitoring" supported_formats: documents: ["PDF", "DOCX", "PPTX", "XLSX"] web: ["HTML", "HTM"] text: ["TXT", "CSV", "JSON", "XML", "RTF"] analysis_types: - "Quality Analysis: Comprehensive conversion assessment" - "Structure Review: Document hierarchy evaluation" - "Content Summary: Thematic analysis and insights" - "Extraction Quality: Data preservation assessment" technical_specs: max_file_size: "50MB (HF Spaces free tier)" processing_timeout: "5 minutes" memory_optimization: "Stateless architecture with automatic cleanup" concurrent_processing: "Async pipeline with resource management"