Update app.py

app.py

@@ -1,9 +1,13 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 from typing import List, Tuple
+import os
 
-# Create inference client
-client = InferenceClient(model="HuggingFaceH4/zephyr-7b-beta")
+# Initialize client with token (add HF_TOKEN in your Space secrets)
+client = InferenceClient(
+    model="HuggingFaceH4/zephyr-7b-beta",
+    token=os.getenv("HF_TOKEN")
+)
 
 def respond(
     message: str,
@@ -13,31 +17,24 @@ def respond(
     temperature: float,
     top_p: float,
 ):
+    # Build conversation history
     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]})
-
+    for user_msg, bot_reply in history:
+        if user_msg:
+            messages.append({"role": "user", "content": user_msg})
+        if bot_reply:
+            messages.append({"role": "assistant", "content": bot_reply})
     messages.append({"role": "user", "content": message})
 
-    response = ""
-
-    # Streaming inference
-    for msg in client.chat_completion(
+    # Call Hugging Face Inference API
+    msg = client.chat_completion(
         model="HuggingFaceH4/zephyr-7b-beta",
         messages=messages,
         max_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
-        stream=True,
-    ):
-        delta = msg.choices[0].delta.content
-        if delta:
-            response += delta
-            yield response
+    )
+    return msg.choices[0].message.content
 
 # Gradio Chat UI
 demo = gr.ChatInterface(
@@ -46,13 +43,7 @@ demo = gr.ChatInterface(
         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)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
 )