mopdernised code

app.py

@@ -1,3 +1,4 @@
+import os
 import gradio as gr
 from huggingface_hub import InferenceClient
 
@@ -5,7 +6,10 @@ 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")
-client = InferenceClient("meta-llama/Meta-Llama-3-8B-Instruct")
+client = InferenceClient(
+    "meta-llama/Meta-Llama-3-8B-Instruct",
+    token=os.environ.get("HF_TOKEN")
+)
 
 
 def respond(
@@ -33,20 +37,20 @@ def respond(
 
     response = ""
 
-    for message in client.chat_completion(
+    # Stream the model output safely
+    for msg in client.chat_completion(
         messages,
         max_tokens=max_tokens,
-        stream=True,
         temperature=temperature,
         top_p=top_p,
+        stream=True,
     ):
-        if message.choices:
-            token = message.choices[0].delta.content
-            if token:
-                response += token
+        if hasattr(msg, "choices") and msg.choices:
+            delta = msg.choices[0].delta
+            if hasattr(delta, "content") and delta.content:
+                response += delta.content
                 yield response
-        else:
-            yield "Please clear the history and try again."
+        # Ignore any events that do not contain content
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface

requirements.txt

@@ -1 +1,2 @@
-huggingface_hub==0.22.2
+gradio>=4.44.0
+huggingface_hub>=0.23.0