Update app.py

app.py

@@ -1,64 +1,105 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+import os
+import time
+from cerebras.cloud.sdk import Cerebras
+import markdown
+
+# Set up the Cerebras client
+client = Cerebras(api_key=os.getenv("CEREBRAS_API_KEY"))
+
+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.
+    """
+    # Start compute time measurement
+    start_time = time.time()
+
+    try:
+        # Create a chat stream with Cerebras
+        stream = client.chat.completions.create(
+            messages=[
+                {"role": "system", "content": system_prompt},
+                {"role": "user", "content": user_input}
+            ],
+            model=model,
+            stream=True,
+            max_completion_tokens=max_completion_tokens,
+            temperature=temperature,
+            top_p=top_p
+        )
+
+        # Collect response from the stream
+        response = ""
+        chain_of_thought = ""
+        for chunk in stream:
+            if chunk.choices[0].delta.content:
+                response += chunk.choices[0].delta.content
+            if "Chain of Thought:" in chunk.choices[0].delta.content:
+                chain_of_thought += chunk.choices[0].delta.content.split("Chain of Thought:", 1)[-1]
+
+        # End compute time measurement
+        compute_time = time.time() - start_time
+
+        # Improved formatting for chain of thought
+        formatted_response = response
+        if chain_of_thought:
+           formatted_response += f"\n\n**Chain of Thought:**\n{chain_of_thought}"
+
+        return formatted_response, chain_of_thought, f"Compute Time: {compute_time:.2f} seconds"
+
+    except Exception as e:
+         return f"Error: {str(e)}", "", "An error occurred. Please check your API key or the Cerebras service."
+
+# Gradio interface
+def gradio_ui():
+    with gr.Blocks() as demo:
+        gr.Markdown("""# 🚀 IntellijMind Release 1st \nExperience the most advanced chatbot for deep insights and unmatched clarity!""")
+
+        with gr.Row():
+            with gr.Column(scale=6):
+                chat_history = gr.Chatbot(label="Chat History")
+            with gr.Column(scale=2):
+                compute_time = gr.Textbox(label="Compute Time", interactive=False)
+                chain_of_thought_display = gr.Textbox(label="Chain of Thought", interactive=False, lines=10)
+
+        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")
+
+         # Set default values for system prompt, model, etc.
+        default_system_prompt = """You are IntellijMind, an advanced AI designed to assist users with detailed insights, problem-solving, and chain-of-thought reasoning. Provide your answers in markdown format. If you do not know the answer, mention that you do not know and don't make things up. Also, remember to be concise and get straight to the point without unnecessary fluff."""
+        default_model = "llama-3.3-70b"
+        default_temperature = 0.2
+        default_top_p = 1
+        default_max_tokens = 1024
+
+
+        def handle_chat(chat_history, user_input):
+            chat_history.append((user_input, None))
+            yield chat_history, "", "Thinking..."
+
+            ai_response, chain_of_thought, compute_info = chat_with_cerebras(user_input, default_system_prompt, default_model, default_temperature, default_top_p, default_max_tokens)
+            chat_history[-1] = (user_input, markdown.markdown(ai_response))  # render markdown output to HTML
+            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]
+        )
+        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 Release 1st**: Setting new standards for AI interaction.\n""")
+
+        gr.Markdown("""\n\n## About\nThis project was created by Aniket Kumar as a showcase of AI capabilities with Cerebras. Feel free to explore and share!""")
+
+    return demo
+
+# Run the Gradio app
+demo = gradio_ui()
+demo.launch()