Update app.py

app.py

@@ -1,11 +1,15 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import os
 
-"""
-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("abhillubillu/ai_gameapp")
+# Retrieve your token from the environment variable
+hf_token = os.getenv("HF_TOKEN_NEW")
 
+# Initialize InferenceClient with the token
+client = InferenceClient(
+    model="abhillubillu/ai_gameapp",
+    token=hf_token  # Use your token stored in HF_TOKEN_NEW
+)
 
 def respond(
     message,
@@ -27,21 +31,19 @@ def respond(
 
     response = ""
 
+    # Stream the response from the model
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
-        stream=True,
+        stream=True,  # Ensure your model supports streaming
         temperature=temperature,
         top_p=top_p,
     ):
         token = message.choices[0].delta.content
-
         response += token
         yield response
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Setting up Gradio Chat Interface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -58,6 +60,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch(show_error=True)
+    demo.launch(show_error=True)