Update App.py Version 3

app.py

@@ -3,16 +3,20 @@ import os
 import requests
 import json
 from typing import List, Tuple
+import time
 
 # Load GROQ API key from environment (set it in Hugging Face secrets)
 GROQ_API_KEY = os.environ.get("GROQ_API_KEY")
 GROQ_API_URL = "https://api.groq.com/openai/v1/chat/completions"
 
-# Available models
+# ✅ UPDATED: Correct GROQ model names (as of Dec 2024)
 MODELS = {
-    "Llama 3 (8B) - Fast": "llama3-8b-8192",
-    "Llama 3 (70B) - Powerful": "llama3-70b-8192",
-    "Mixtral (8x7B) - Balanced": "mixtral-8x7b-32768"
+    "Llama 3.2 (3B) - Fast": "llama-3.2-3b-preview",
+    "Llama 3.2 (1B) - Light": "llama-3.2-1b-preview",
+    "Llama 3.2 (90B Text) - Powerful": "llama-3.2-90b-text-preview",
+    "Llama 3.2 (11B Text) - Balanced": "llama-3.2-11b-text-preview",
+    "Mixtral (8x7B)": "mixtral-8x7b-32768",
+    "Gemma 2 (9B)": "gemma2-9b-it"
 }
 
 # 🎯 Customize this system prompt based on your bot's role
@@ -53,9 +57,12 @@ def query_groq_api(message: str, chat_history: List[Tuple[str, str]], model: str
     # Add current message
     messages.append({"role": "user", "content": message})
     
+    # ✅ Get the actual model name from the dictionary
+    actual_model = MODELS.get(model, "llama-3.2-3b-preview")
+    
     # Prepare payload
     payload = {
-        "model": model,
+        "model": actual_model,
         "messages": messages,
         "temperature": temperature,
         "max_tokens": max_tokens,
@@ -64,14 +71,19 @@ def query_groq_api(message: str, chat_history: List[Tuple[str, str]], model: str
     }
     
     try:
-        response = requests.post(GROQ_API_URL, headers=headers, json=payload)
+        response = requests.post(GROQ_API_URL, headers=headers, json=payload, timeout=30)
         
         if response.status_code == 200:
             data = response.json()
             return data["choices"][0]["message"]["content"]
+        elif response.status_code == 404:
+            # ✅ Specific error for model not found
+            return f"❌ Error: Model '{actual_model}' not found. Available models are: {', '.join(MODELS.values())}"
         else:
             return f"❌ Error {response.status_code}: {response.text}"
     
+    except requests.exceptions.Timeout:
+        return "⏰ Request timeout. Please try again."
     except requests.exceptions.RequestException as e:
         return f"🚫 Connection error: {str(e)}"
     except Exception as e:
@@ -83,11 +95,15 @@ def respond(message: str, chat_history: List[Tuple[str, str]], model: str, tempe
     if not message.strip():
         return "", chat_history
     
+    # Show typing indicator
+    chat_history.append((message, "🤔 Thinking..."))
+    yield "", chat_history
+    
     # Get bot response
-    bot_reply = query_groq_api(message, chat_history, model, temperature, max_tokens)
+    bot_reply = query_groq_api(message, chat_history[:-1], model, temperature, max_tokens)
     
-    # Add to chat history
-    chat_history.append((message, bot_reply))
+    # Replace typing indicator with actual response
+    chat_history[-1] = (message, bot_reply)
     
     return "", chat_history
 
@@ -143,19 +159,21 @@ with gr.Blocks(theme=gr.themes.Soft(), title="CodeMentor - Programming Tutor") a
     - Best practices and design patterns
     
     Select your preferences below and start asking questions!
+    
+    ⚠️ **Note**: Using GROQ API with free tier (limited requests per minute)
     """)
     
     with gr.Row():
         with gr.Column(scale=1):
-            # UI Improvements (as required in assignment)
+            # UI Improvements
             gr.Markdown("### ⚙️ Settings")
             
             # Model selection dropdown
             model_dropdown = gr.Dropdown(
                 choices=list(MODELS.keys()),
-                value="Llama 3 (8B) - Fast",
+                value="Llama 3.2 (3B) - Fast",
                 label="Select AI Model",
-                info="Choose the model for responses"
+                info="✅ Updated with correct GROQ model names"
             )
             
             # Programming language selection
@@ -186,7 +204,7 @@ with gr.Blocks(theme=gr.themes.Soft(), title="CodeMentor - Programming Tutor") a
                 info="Maximum length of responses"
             )
             
-            # Example questions dropdown (replacing Dataset)
+            # Example questions dropdown
             gr.Markdown("### 💡 Example Questions")
             example_dropdown = gr.Dropdown(
                 choices=[
@@ -223,7 +241,6 @@ with gr.Blocks(theme=gr.themes.Soft(), title="CodeMentor - Programming Tutor") a
             )
             
             with gr.Row():
-                # Send button
                 send_btn = gr.Button("🚀 Send", variant="primary")
                 stop_btn = gr.Button("⏹️ Stop", variant="stop")
     
@@ -264,7 +281,7 @@ with gr.Blocks(theme=gr.themes.Soft(), title="CodeMentor - Programming Tutor") a
     # Handle reset button
     def reset_settings():
         return [
-            "Llama 3 (8B) - Fast",  # model_dropdown
+            "Llama 3.2 (3B) - Fast",  # model_dropdown
             "Python",  # language_dropdown
             0.7,  # temperature_slider
             500,  # max_tokens_slider
@@ -277,25 +294,27 @@ with gr.Blocks(theme=gr.themes.Soft(), title="CodeMentor - Programming Tutor") a
         outputs=[model_dropdown, language_dropdown, temperature_slider, max_tokens_slider, example_dropdown]
     )
     
-    # Handle stop button
-    stop_btn.click(
-        fn=None,
-        inputs=None,
-        outputs=None,
-        cancels=[]
-    )
-    
-    # Footer
+    # Footer with troubleshooting info
     gr.Markdown("""
     ---
-    ### ℹ️ About
-    - **Powered by**: GROQ API with Llama 3
-    - **Theme**: Programming Tutor
-    - **UI Features**: Model selection, language focus, temperature control, response length slider
-    - **Deployed on**: Hugging Face Spaces
+    ### ℹ️ About & Troubleshooting
+    
+    **Powered by**: GROQ API
+    **Current Models Available**:
+    - `llama-3.2-3b-preview` (Fast, 3B parameters)
+    - `llama-3.2-1b-preview` (Lightweight, 1B)
+    - `llama-3.2-90b-text-preview` (Most powerful, 90B)
+    - `llama-3.2-11b-text-preview` (Balanced, 11B)
+    - `mixtral-8x7b-32768` (Mixture of experts)
+    - `gemma2-9b-it` (Google's model)
+    
+    **If you see "model not found" error**:
+    1. Check GROQ Console for available models
+    2. Ensure your API key has access to the selected model
+    3. Try a different model from the dropdown
     
-    ⚠️ Note: This is an educational tool. Always verify critical code before production use.
+    **Note**: Free tier has rate limits. If requests fail, wait 1 minute and try again.
     """)
 
 if __name__ == "__main__":
-    demo.launch(debug=False)
+    demo.launch(debug=False, server_name="0.0.0.0", server_port=7860)