Update app.py

app.py

@@ -1,35 +1,35 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-# Use a pipeline as a high-level helper
 from transformers import pipeline
+from typing import List, Tuple  # Importing for type annotations
 
-pipe = pipeline("fill-mask", model="google-bert/bert-base-uncased")
-"""
-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
-"""
+# Initialize InferenceClient with the correct model
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
-
+# Function to handle the response generation using chat completion
 def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
+    message: str,
+    history: List[Tuple[str, str]],  # Using List and Tuple for type annotation
+    system_message: str,
+    max_tokens: int,
+    temperature: float,
+    top_p: float,
 ):
     messages = [{"role": "system", "content": system_message}]
-
+    
+    # Append history to the messages list
     for val in history:
         if val[0]:
             messages.append({"role": "user", "content": val[0]})
         if val[1]:
             messages.append({"role": "assistant", "content": val[1]})
 
+    # Append the current user message
     messages.append({"role": "user", "content": message})
 
     response = ""
 
+    # Use the client to get chat completion and stream the response
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -38,14 +38,11 @@ def respond(
         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 Interface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -62,6 +59,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()