Update app.py

app.py

@@ -1,5 +1,6 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from typing import List, Tuple
 
 """
 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
@@ -8,12 +9,12 @@ client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
 
 def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
+    message: str,
+    history: List[Tuple[str, str]],
+    system_message: str,
+    max_tokens=1024,
+    temperature=0.7,
+    top_p=0.95,
 ):
     messages = [{"role": "system", "content": system_message}]
 
@@ -27,17 +28,21 @@ def respond(
 
     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
+    try:
+        for message in client.chat_completion(
+            messages,
+            max_tokens=max_tokens,
+            stream=True,
+            temperature=temperature,
+            top_p=top_p,
+        ):
+            if message.choices and "delta" in message.choices[0]:
+                token = message.choices[0].delta.get("content", "")
+                response += token
+                yield response
+    except Exception as e:
+        print(f"Error during API call: {e}")
+        yield "An error occurred while processing the request."
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
@@ -60,4 +65,4 @@ demo = gr.ChatInterface(
 
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()