Update app.py

app.py

@@ -5,43 +5,29 @@ from huggingface_hub import InferenceClient
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
 # Define how the chatbot responds
-shop_floor_data = {
-    "Machine A": {"Status": "Running", "Efficiency": "92%", "Output": "200 units/day"},
-    "Machine B": {"Status": "Idle", "Efficiency": "N/A", "Output": "0 units/day"},
-    "Assembly Line 1": {"Status": "Running", "Output": "450 units/day"},
-    "Welding Robot": {"Status": "Under maintenance", "Next Check": "April 10, 2025"},
-}
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    message_lower = message.lower()
-    
-    if "status" in message_lower or "machine" in message_lower or "output" in message_lower:
-        response = "📊 **Shop Floor Status**:\n\n"
-        for name, info in shop_floor_data.items():
-            response += f"**{name}**\n"
-            for key, value in info.items():
-                response += f"  - {key}: {value}\n"
-            response += "\n"
-        yield response
-        return
-
-    # Fallback to the LLM response
+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
 
-    response
 
 
 # Build the UI using Gradio Blocks