Update app.py

app.py

@@ -1,64 +1,63 @@
 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
+
+# Set up the Cerebras client
+client = Cerebras(api_key=os.getenv("CEREBRAS_API_KEY"))
+
+def chat_with_cerebras(user_input):
+    """
+    Handles interaction with the Cerebras model.
+    Sends user input and returns the model's response along with compute time.
+    """
+    # Start compute time measurement
+    start_time = time.time()
+
+    try:
+        # Create a chat stream with Cerebras
+        stream = client.chat.completions.create(
+            messages=[
+                {"role": "system", "content": "You are a helpful assistant."},
+                {"role": "user", "content": user_input}
+            ],
+            model="llama-3.3-70b",
+            stream=True,
+            max_completion_tokens=1024,
+            temperature=0.2,
+            top_p=1
+        )
+
+        # Collect response from the stream
+        response = ""
+        for chunk in stream:
+            response += chunk.choices[0].delta.content or ""
+
+        # End compute time measurement
+        compute_time = time.time() - start_time
+
+        return response, f"Compute Time: {compute_time:.2f} seconds"
+
+    except Exception as e:
+        return "Error: Unable to process your request.", str(e)
+
+# Gradio interface
+def gradio_ui():
+    with gr.Blocks() as demo:
+        gr.Markdown("""# Cerebras AI Chatbot\nChat with a state-of-the-art AI model.""")
+
+        with gr.Row():
+            user_input = gr.Textbox(label="Your Message", placeholder="Type your message here...")
+            response = gr.Textbox(label="AI Response", interactive=False)
+            compute_time = gr.Textbox(label="Compute Time", interactive=False)
+
+        submit_button = gr.Button("Submit")
+
+        # Define interaction logic
+        submit_button.click(chat_with_cerebras, inputs=user_input, outputs=[response, compute_time])
+
+    return demo
+
+# Run the Gradio app
+demo = gradio_ui()
+demo.launch()