Update README.md

README.md

@@ -1,98 +1,111 @@
-# Math Question Validator with OpenAI o3
-
-A Python tool for validating mathematical questions and answers using OpenAI's o3 model, with automatic reconciliation and quality assessment.
+---
+title: Math Question Validator
+emoji: 🧮
+colorFrom: blue
+colorTo: green
+sdk: gradio
+sdk_version: 4.44.0
+app_file: app.py
+pinned: false
+license: mit
+---
+
+# Math Question Validator
+
+A powerful web-based tool for validating mathematical questions and answers using state-of-the-art AI models.
 
 ## Features
 
-- **Automated Answer Validation**: Uses OpenAI o3 model to solve math problems
-- **Quality Assessment**: Evaluates question clarity, difficulty, and pedagogical value
-- **Smart Reconciliation**: Generates detailed LaTeX documents comparing different solutions
-- **Batch Processing**: Handles large datasets with progress tracking
-- **File-based Output**: Avoids truncation issues with cloud storage by saving outputs as separate files
-
-## Setup
-
-### Prerequisites
-- Python 3.8+
-- OpenAI API key with o3 access
-- MiKTeX (optional, for PDF compilation)
-
-### Installation
-
-1. Clone the repository:
-```bash
-git clone https://github.com/YOUR_USERNAME/validator.git
-cd validator
-```
-
-2. Install dependencies:
-```bash
-pip install pandas openpyxl python-dotenv openai tqdm
-```
-
-3. Create `.env` file with your OpenAI API key:
-```
-OPENAI_API_KEY=your_key_here
-```
-
-## Usage
-
-### Basic Validation
-```bash
-python math_validator.py
-```
-
-This will:
-1. Load questions from the Excel file
-2. Filter for math/statistics questions
-3. Assess each question's quality
-4. Generate o3 model answers
-5. Compare with reference answers
-6. Create LaTeX reconciliation documents for mismatches
-
-### Compile LaTeX to PDF
-```bash
-python compile_latex.py
-```
-
-## Output Structure
-
-```
-validation_results/
-└── run_YYYYMMDD_HHMMSS/
-    ├── manifest.json           # Index of all results
-    ├── model_answers/          # Full model responses
-    │   └── q_XXXX_answer.txt
-    ├── latex_documents/        # Reconciliation documents
-    │   └── q_XXXX_reconciliation.tex
-    └── compiled_pdfs/          # Compiled PDFs (if generated)
-        └── q_XXXX_reconciliation.pdf
-```
-
-## File Naming Convention
-
-Files are named using Excel row numbers for easy cross-reference:
-- `q_0116_reconciliation.tex` → Excel row 116
-- `q_0117_answer.txt` → Excel row 117
-
-## Models Used
-
-- **o3**: Primary model for solving mathematical problems
-- **gpt-4o**: Quality assessment and question evaluation
-
-## Excel Output Columns
-
-- `model_answer_file`: Path to model's answer
-- `answer_match`: MATCH/DIFFERENT/ERROR
-- `latex_file`: Path to reconciliation document
-- `quality_rating`: excellent/good/fair/poor
-- `difficulty_level`: too_easy/appropriate/too_hard/unclear
-- `quality_comment`: Detailed assessment
+- 🚀 **Multiple AI Models**: Support for o3-mini, GPT-5, Claude 4, Grok 4, DeepSeek, and more
+- 🔄 **Parallel Processing**: Process hundreds of questions simultaneously
+- 📊 **Detailed Analytics**: Track accuracy, timeouts, and errors in real-time
+- 📝 **LaTeX Reconciliation**: Generate detailed comparison documents for mismatched answers
+- 🖼️ **Image Support**: Handle questions with diagrams and figures
+- 📈 **Progress Tracking**: Real-time statistics and progress monitoring
+
+## Quick Start
+
+1. **Upload your Excel file** containing math questions
+2. **Select models** for solving and reconciliation
+3. **Configure processing** options (parallel processes, batch size)
+4. **Start validation** and monitor progress
+5. **Download results** with detailed analysis
+
+## Setting Up API Keys
+
+This app requires API keys to function. Add them in the Spaces Settings:
+
+1. Go to Settings → Variables and secrets
+2. Add your API keys:
+   - `OPENAI_API_KEY` - For OpenAI models (o3-mini, GPT-5, GPT-4o)
+   - `OPENROUTER_API_KEY` - For Claude, Grok, Gemini, and other models
+
+## Input Format
+
+Your Excel file should have a "Data" sheet with these columns:
+- `question` - The math question text
+- `correct_answer` or `answer` - The reference answer
+- `raw_subject` - Subject classification (optional, for filtering)
+- `file_url` - Image URL if question has a diagram (optional)
+
+## Output
+
+The validator generates:
+- **Validated Excel file** with model answers and match results
+- **LaTeX reconciliation documents** for mismatched answers
+- **Model answer files** with complete solutions
+- **Statistics summary** with accuracy metrics
+
+## Model Recommendations
+
+### For Best Accuracy
+- Solver: o3-mini
+- Reconciliation: gpt-4o
+
+### For Speed
+- Solver: gpt-4o
+- Reconciliation: gpt-4o
+- Use 4-6 parallel processes
+
+### For Cost-Effectiveness
+- Solver: Claude 3.5 Sonnet
+- Reconciliation: Claude 3.5 Sonnet
+
+## Advanced Features
+
+### Parallel Processing
+- Automatically splits large datasets across multiple processes
+- Merges results seamlessly
+- Optimal for 100+ questions
+
+### Custom Ranges
+- Process specific question ranges
+- Useful for testing or resuming interrupted runs
+
+### LaTeX Compilation
+- Optional PDF generation from LaTeX reconciliation documents
+- Requires pdflatex (not available in HF Spaces)
+
+## Limitations
+
+- Maximum file size: 200MB
+- Image support requires URLs (local images not supported in HF Spaces)
+- LaTeX PDF compilation not available (use .tex files locally)
+
+## Support
+
+For issues or questions:
+- Check the Configuration tab in the app
+- Review error messages in the output log
+- Ensure API keys are correctly set
 
 ## License
 
-[Your chosen license]
+MIT License - Free to use and modify
 
-## Author
+## Credits
 
-[Your name]
+Built with:
+- Gradio for the web interface
+- OpenAI, Anthropic, and other AI providers for models
+- pandas for data processing