Update app.py

app.py

@@ -6,7 +6,7 @@ from cerebras.cloud.sdk import Cerebras
 # Set up the Cerebras client
 client = Cerebras(api_key=os.getenv("CEREBRAS_API_KEY"))
 
-def chat_with_cerebras(user_input):
+def chat_with_cerebras(user_input, system_prompt, model, temperature, top_p, max_completion_tokens):
     """
     Handles interaction with the Cerebras model.
     Sends user input and returns the model's response along with compute time and chain-of-thought reasoning.
@@ -18,14 +18,14 @@ def chat_with_cerebras(user_input):
         # Create a chat stream with Cerebras
         stream = client.chat.completions.create(
             messages=[
-                {"role": "system", "content": "You are IntellijMind, an advanced AI designed to assist users with detailed insights, problem-solving, and chain-of-thought reasoning."},
+                {"role": "system", "content": system_prompt},
                 {"role": "user", "content": user_input}
             ],
-            model="llama-3.3-70b",
+            model=model,
             stream=True,
-            max_completion_tokens=1024,
-            temperature=0.2,
-            top_p=1
+            max_completion_tokens=max_completion_tokens,
+            temperature=temperature,
+            top_p=top_p
         )
 
         # Collect response from the stream
@@ -43,7 +43,7 @@ def chat_with_cerebras(user_input):
         return response, chain_of_thought, f"Compute Time: {compute_time:.2f} seconds"
 
     except Exception as e:
-        return "Error: Unable to process your request.", "", str(e)
+        return f"Error: {str(e)}", "", "An error occurred. Please check your API key or the Cerebras service."
 
 # Gradio interface
 def gradio_ui():
@@ -57,19 +57,34 @@ def gradio_ui():
                 compute_time = gr.Textbox(label="Compute Time", interactive=False)
                 chain_of_thought_display = gr.Textbox(label="Chain of Thought", interactive=False, lines=10)
 
+        with gr.Accordion("Advanced Settings", open=False):
+            system_prompt_input = gr.Textbox(label="System Prompt", value="You are IntellijMind, an advanced AI designed to assist users with detailed insights, problem-solving, and chain-of-thought reasoning.", lines=3)
+            model_select = gr.Dropdown(label="Model", choices=["llama-3.3-70b", "llama-2-70b"], value="llama-3.3-70b")  # Add other model names as required
+            temperature_slider = gr.Slider(label="Temperature", minimum=0, maximum=2, step=0.1, value=0.2)
+            top_p_slider = gr.Slider(label="Top P", minimum=0, maximum=1, step=0.01, value=1)
+            max_tokens_slider = gr.Slider(label="Max Tokens", minimum=50, maximum=2048, step=50, value=1024)
+
+
         user_input = gr.Textbox(label="Type your message", placeholder="Ask me anything...", lines=2)
         send_button = gr.Button("Send", variant="primary")
         clear_button = gr.Button("Clear Chat")
 
-        def handle_chat(chat_history, user_input):
-            ai_response, chain_of_thought, compute_info = chat_with_cerebras(user_input)
-            chat_history.append((user_input, ai_response))
-            return chat_history, chain_of_thought, compute_info
+        def handle_chat(chat_history, user_input, system_prompt, model, temperature, top_p, max_tokens):
+            chat_history.append((user_input, None))
+            yield chat_history, "", "Thinking..."
+
+            ai_response, chain_of_thought, compute_info = chat_with_cerebras(user_input, system_prompt, model, temperature, top_p, max_tokens)
+            chat_history[-1] = (user_input, ai_response)
+            yield chat_history, chain_of_thought, compute_info
 
         def clear_chat():
             return [], "", ""
 
-        send_button.click(handle_chat, inputs=[chat_history, user_input], outputs=[chat_history, chain_of_thought_display, compute_time])
+        send_button.click(
+            handle_chat,
+            inputs=[chat_history, user_input, system_prompt_input, model_select, temperature_slider, top_p_slider, max_tokens_slider],
+            outputs=[chat_history, chain_of_thought_display, compute_time]
+        )
         clear_button.click(clear_chat, outputs=[chat_history, chain_of_thought_display, compute_time])
 
         gr.Markdown("""---\n### 🌟 Features:\n- **Advanced Reasoning**: Chain-of-thought explanations for complex queries.\n- **Real-Time Performance Metrics**: Measure response compute time instantly.\n- **Insightful Chain of Thought**: See the reasoning process behind AI decisions.\n- **User-Friendly Design**: Intuitive chatbot interface with powerful features.\n- **Powered by IntellijMind**: Setting new standards for AI interaction.\n""")
@@ -78,4 +93,4 @@ def gradio_ui():
 
 # Run the Gradio app
 demo = gradio_ui()
-demo.launch()
+demo.launch()