Update app.py

app.py

@@ -1,9 +1,12 @@
+
+
 import gradio as gr
 from huggingface_hub import InferenceClient
 from typing import List, Tuple
 import logging
 from collections import deque
 import re
+import os
 
 # Configure logging
 logging.basicConfig(
@@ -12,9 +15,12 @@ logging.basicConfig(
 )
 logger = logging.getLogger(__name__)
 
-# Initialize the InferenceClient
+# Initialize the InferenceClient with API token
 try:
-    client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+    client = InferenceClient(
+        model="HuggingFaceH4/zephyr-7b-beta",
+        token=os.getenv("HUGGINGFACEHUB_API_TOKEN")
+    )
     logger.info("Successfully initialized InferenceClient")
 except Exception as e:
     logger.error(f"Failed to initialize InferenceClient: {str(e)}")
@@ -97,21 +103,23 @@ def respond(
 
     response = ""
     try:
-        for message in client.chat_completion(
+        stream = client.chat_completion(
             messages,
             max_tokens=max_tokens,
             stream=True,
             temperature=temperature,
             top_p=top_p,
-        ):
+        )
+        for message in stream:
             token = message.choices[0].delta.content or ""
             response += token
             yield response
         # Store the query and final response in memory
         add_to_memory(message, response)
     except Exception as e:
-        logger.error(f"Error during chat completion: {str(e)}")
-        raise RuntimeError("Failed to generate response from the model")
+        error_msg = f"Error during chat completion: {str(e)}"
+        logger.error(error_msg)
+        yield error_msg  # Yield the error message to display in Gradio
 
 def main():
     """