CHG: check

app.py

@@ -1,64 +1,47 @@
 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]})
+# Initialize the client with the updated model
+client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
+
+# Define the system prompt
+SYSTEM_PROMPT = (
+    "\nYou are an expert programming assistant with deep knowledge of software development, debugging, "
+    "and code optimization. Your responses should be clear, concise, and include code examples when appropriate. "
+    "Always explain your reasoning step by step to help the user understand the solution."
+)
 
+def respond(message, history: list[tuple[str, str]]):
+    messages = [{"role": "system", "content": SYSTEM_PROMPT}]
+    
+    for user_msg, assistant_msg in history:
+        if user_msg:
+            messages.append({"role": "user", "content": user_msg})
+        if assistant_msg:
+            messages.append({"role": "assistant", "content": assistant_msg})
+    
     messages.append({"role": "user", "content": message})
-
+    
     response = ""
+    
+    # Static parameters for generation
+    max_tokens = 512
+    temperature = 0.7
+    top_p = 0.95
 
-    for message in client.chat_completion(
+    for token 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
+        content = token.choices[0].delta.content
+        response += content
         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)",
-        ),
-    ],
-)
-
+# Create the Gradio ChatInterface without additional inputs
+demo = gr.ChatInterface(respond)
 
 if __name__ == "__main__":
     demo.launch()