Update app.py Version 6

app.py

@@ -7,11 +7,28 @@ import time
 GROQ_API_KEY = os.environ.get("GROQ_API_KEY")
 GROQ_API_URL = "https://api.groq.com/openai/v1/chat/completions"
 
-def query_groq_api(message, chat_history):
-    """Actually call GROQ API"""
+# ✅ YOUR AVAILABLE MODELS (from your account)
+AVAILABLE_MODELS = {
+    "Llama 3.1 (8B) - Fast": "llama-3.1-8b-instant",
+    "Llama 3.3 (70B) - Powerful": "llama-3.3-70b-versatile", 
+    "Qwen 3 (32B)": "qwen/qwen3-32b",
+    "Llama 4 Maverick (17B)": "meta-llama/llama-4-maverick-17b-128e-instruct",
+    "Llama 4 Scout (17B)": "meta-llama/llama-4-scout-17b-16e-instruct",
+    "GPT OSS (20B)": "openai/gpt-oss-20b",
+    "GPT OSS (120B)": "openai/gpt-oss-120b"
+}
+
+# Default model that should definitely work
+DEFAULT_MODEL = "llama-3.1-8b-instant"
+
+def query_groq_api(message, chat_history, model_name):
+    """Call GROQ API with your available models"""
     
     if not GROQ_API_KEY:
-        return "❌ **ERROR**: GROQ_API_KEY not set. Add it in Hugging Face Secrets."
+        return "❌ **ERROR**: GROQ_API_KEY not found. Add it in Hugging Face Secrets."
+    
+    # Get actual model ID from friendly name
+    actual_model = AVAILABLE_MODELS.get(model_name, DEFAULT_MODEL)
     
     headers = {
         "Authorization": f"Bearer {GROQ_API_KEY}",
@@ -20,11 +37,14 @@ def query_groq_api(message, chat_history):
     
     # Build messages array
     messages = [
-        {"role": "system", "content": "You are a helpful programming tutor. Answer in 2-3 sentences."}
+        {
+            "role": "system", 
+            "content": "You are CodeMentor, a helpful programming tutor. Keep answers clear and concise (2-3 sentences). Always format code examples in markdown code blocks."
+        }
     ]
     
-    # Add conversation history
-    for user_msg, bot_msg in chat_history:
+    # Add conversation history (last 3 exchanges for context)
+    for user_msg, bot_msg in chat_history[-3:]:
         messages.append({"role": "user", "content": user_msg})
         messages.append({"role": "assistant", "content": bot_msg})
     
@@ -33,7 +53,7 @@ def query_groq_api(message, chat_history):
     
     # Request data
     data = {
-        "model": "llama-3.2-3b-preview",  # Working model
+        "model": actual_model,
         "messages": messages,
         "temperature": 0.7,
         "max_tokens": 300,
@@ -51,24 +71,25 @@ def query_groq_api(message, chat_history):
         
         if response.status_code == 200:
             result = response.json()
-            return result["choices"][0]["message"]["content"]
+            reply = result["choices"][0]["message"]["content"]
+            return f"{reply}\n\n**🤖 Model**: {model_name}"
         elif response.status_code == 429:
             return "⏰ **RATE LIMITED**: Please wait 60 seconds before trying again."
         else:
-            return f"❌ API Error {response.status_code}: {response.text[:100]}"
+            return f"❌ **API Error {response.status_code}**: Try a different model from the dropdown."
     
     except requests.exceptions.Timeout:
-        return "⏱️ **TIMEOUT**: Request took too long. Try a shorter question."
+        return "⏱️ **TIMEOUT**: Request took too long. Try the 'Llama 3.1 (8B)' model."
     except Exception as e:
-        return f"⚠️ Error: {str(e)}"
+        return f"⚠️ **Error**: {str(e)[:100]}"
 
-def chat_response(message, history):
+def chat_response(message, history, model):
     """Main chat function"""
     if not message.strip():
         return "", history
     
     # Get response from GROQ
-    bot_message = query_groq_api(message, history)
+    bot_message = query_groq_api(message, history, model)
     
     # Add to history
     history.append((message, bot_message))
@@ -78,72 +99,98 @@ def chat_response(message, history):
 def clear_chat():
     return []
 
+def reset_settings():
+    return ["Llama 3.1 (8B) - Fast", "What is Python?"]
+
 # Create Gradio interface
 with gr.Blocks(title="Programming Tutor - GROQ", theme=gr.themes.Soft()) as demo:
     
     gr.Markdown("""
     # 👨‍💻 Programming Tutor Chatbot
-    **Powered by GROQ LLM API**
+    **Using YOUR Available GROQ Models**
     """)
     
     # Chatbot display
     chatbot = gr.Chatbot(height=400, label="Conversation")
     
-    # Message input
-    msg = gr.Textbox(
-        placeholder="Ask a programming question...",
-        label="Your Question",
-        lines=2
-    )
-    
     # Store chat history
     chat_state = gr.State([])
     
-    # Buttons
     with gr.Row():
-        submit_btn = gr.Button("🚀 Send", variant="primary")
-        clear_btn = gr.Button("🗑️ Clear", variant="secondary")
-    
-    # Example questions
-    gr.Markdown("### 💡 Try these questions:")
-    
-    examples = [
-        "Hello, who are you?",
-        "Explain Python variables",
-        "How to write a for loop?",
-        "What is a function?"
-    ]
-    
-    with gr.Row():
-        for example in examples:
-            example_btn = gr.Button(example, size="sm")
-            # When clicked, set the message box to example text
-            example_btn.click(
-                lambda x=example: x,
-                inputs=None,
-                outputs=msg
+        with gr.Column(scale=1):
+            # Model selection dropdown
+            gr.Markdown("### ⚙️ Settings")
+            
+            model_dropdown = gr.Dropdown(
+                choices=list(AVAILABLE_MODELS.keys()),
+                value="Llama 3.1 (8B) - Fast",
+                label="Select Model",
+                info="Choose from your available models"
             )
+            
+            # Quick actions
+            gr.Markdown("### ⚡ Quick Actions")
+            with gr.Row():
+                clear_btn = gr.Button("🗑️ Clear Chat", variant="secondary")
+                reset_btn = gr.Button("🔄 Reset", variant="secondary")
+            
+            # Example questions
+            gr.Markdown("### 💡 Example Questions")
+            
+            examples = [
+                "Hello! Who are you?",
+                "Explain variables in programming",
+                "Write a Python function to add two numbers",
+                "What are data types?"
+            ]
+            
+            example_output = gr.Textbox(label="Selected Question", interactive=False, visible=False)
+            
+            for example in examples:
+                btn = gr.Button(example, size="sm")
+                btn.click(
+                    lambda x=example: x,
+                    inputs=None,
+                    outputs=example_output
+                )
+        
+        with gr.Column(scale=2):
+            # Message input
+            msg = gr.Textbox(
+                placeholder="Type your programming question here...",
+                label="Your Question",
+                lines=3
+            )
+            
+            # Send button
+            send_btn = gr.Button("🚀 Send Message", variant="primary", size="lg")
+    
+    # Update message box when example is clicked
+    example_output.change(
+        lambda x: x,
+        inputs=example_output,
+        outputs=msg
+    )
     
-    # Set up event handlers
-    def respond(message, history):
+    # Function to handle message submission
+    def respond(message, history, model):
         if not message.strip():
             return "", history
         
-        # Call GROQ API
-        bot_reply = query_groq_api(message, history)
+        bot_reply = query_groq_api(message, history, model)
         history.append((message, bot_reply))
         return "", history
     
-    # Connect inputs and outputs
+    # Set up event handlers
     msg.submit(
         respond,
-        inputs=[msg, chat_state],
+        inputs=[msg, chat_state, model_dropdown],
         outputs=[msg, chatbot]
     )
     
-    submit_btn.click(
+    send_btn.click(
         respond,
-        inputs=[msg, chat_state],
+        inputs=[msg, chat_state, model_dropdown],
         outputs=[msg, chatbot]
     )
     
@@ -153,14 +200,29 @@ with gr.Blocks(title="Programming Tutor - GROQ", theme=gr.themes.Soft()) as demo
         outputs=[chatbot, chat_state]
     )
     
+    reset_btn.click(
+        reset_settings,
+        inputs=None,
+        outputs=[model_dropdown, msg]
+    )
+    
     # Footer
-    gr.Markdown("""
+    gr.Markdown(f"""
     ---
-    ### ℹ️ About
-    - **Model**: llama-3.2-3b-preview
-    - **API**: GROQ
-    - **Note**: Free tier has rate limits. Wait 1 minute if you get errors.
+    ### ℹ️ About Your Available Models
+    
+    **Fast Models (Try These First):**
+    1. **Llama 3.1 (8B)** - Fastest, good for simple questions
+    2. **Qwen 3 (32B)** - Balanced speed and quality
+    3. **Llama 4 Maverick (17B)** - Good for code examples
+    
+    **Powerful Models (Slower):**
+    1. **Llama 3.3 (70B)** - Most powerful but slower
+    2. **GPT OSS (120B)** - Very powerful, may be slow
+    
+    **Rate Limits:** 30 requests/minute for most models
+    **Tip:** Start with "Llama 3.1 (8B)" for fastest responses
     """)
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(debug=False, server_name="0.0.0.0", server_port=7860)