Add ChatGPT-style Gradio interface for question generation

Dockerfile

@@ -32,6 +32,7 @@ RUN pip install -r requirements.txt
 
 # Copy application files
 COPY app.py .
+COPY gradio_app.py .
 COPY README.md .
 
 # Create HF cache directory with proper permissions
@@ -43,5 +44,5 @@ ENV OMP_NUM_THREADS=4
 # Expose port
 EXPOSE 7860
 
-# Run the application
-CMD ["python", "app.py"]
+# Run the Gradio application
+CMD ["python", "gradio_app.py"]

README.md

@@ -1,6 +1,6 @@
 ---
-title: Question Generation API
-emoji: 🤔
+title: Question Generation AI
+emoji: 🤖
 colorFrom: blue
 colorTo: purple
 sdk: docker
@@ -9,24 +9,30 @@ license: apache-2.0
 app_port: 7860
 ---
 
-# Question Generation API
+# Question Generation AI
 
-This Hugging Face Space provides an API for generating thoughtful questions from input statements using the **DavidAU/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-GGUF** model.
+This Hugging Face Space provides a ChatGPT-style interface for generating thoughtful questions from input statements using the **Google FLAN-T5-Large** model.
 
 ## Features
 
-- 🧠 **Deep Reasoning**: Uses enhanced reasoning capabilities for better question quality
-- 📚 **1M Context**: Supports very long input statements (up to 1 million tokens)
-- 🎯 **Customizable**: Adjust number of questions, difficulty level, and generation parameters
-- 🚀 **Fast API**: RESTful API with automatic documentation
-- 🔧 **GPU Optimized**: Optimized for NVIDIA A10G hardware
+- 🤖 **ChatGPT-Style Interface**: Intuitive chat interface for generating questions
+- 🎯 **Customizable**: Adjust number of questions, difficulty level, and creativity
+- 📚 **FLAN-T5 Powered**: Uses Google's instruction-tuned T5 model for high-quality questions
+- 🚀 **Fast & Reliable**: Optimized for quick response times
+- 🔧 **GPU Optimized**: Runs efficiently on NVIDIA A10G hardware
+- 💡 **Educational Focus**: Perfect for creating study materials and assessments
 
-## API Endpoints
+## How to Use
 
-### Generate Questions
-**POST** `/generate-questions`
+### Chat Interface
+Simply enter any statement or topic in the chat box, and the AI will generate thoughtful questions about it. You can:
 
-Generate questions from a given statement.
+- **Adjust Settings**: Control the number of questions (1-10), difficulty level, and creativity
+- **Try Different Topics**: Works great with educational content, research topics, or any text
+- **Interactive Experience**: Chat-like interface similar to ChatGPT
+
+### API Access (Still Available)
+The original API endpoints are still accessible at `/generate-questions` for programmatic access.
 
 **Request Body:**
 ```json

requirements.txt

@@ -10,4 +10,5 @@ huggingface-hub>=0.19.0
 python-multipart==0.0.6
 numpy>=1.24.0
 sentencepiece>=0.1.99
-protobuf>=3.20.0
+protobuf>=3.20.0
+gradio>=4.0.0