Update app.py

app.py

@@ -1,47 +1,65 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-from fastapi import FastAPI
-from fastapi.middleware.cors import CORSMiddleware
 
+"""
+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")
 
-def respond(message, history, system_message, max_tokens, temperature, top_p):
+
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
     messages = [{"role": "system", "content": system_message}]
+
     for val in history:
         if val[0]:
             messages.append({"role": "user", "content": val[0]})
         if val[1]:
             messages.append({"role": "assistant", "content": val[1]})
+
     messages.append({"role": "user", "content": message})
+
     response = ""
+
     for message in client.chat_completion(
-        messages, max_tokens=max_tokens, stream=True, temperature=temperature, top_p=top_p
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
     ):
         token = message.choices[0].delta.content
+
         response += token
         yield response
 
-# Create Gradio app
-app = gr.ChatInterface(
+
+"""
+For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+"""
+demo = gr.ChatInterface(
     respond,
     additional_inputs=[
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p"),
+        gr.Slider(
+            minimum=0.1,
+            maximum=1.0,
+            value=0.95,
+            step=0.05,
+            label="Top-p (nucleus sampling)",
+        ),
     ],
 )
 
-# Mount FastAPI app with CORS
-fastapi_app = FastAPI()
-fastapi_app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"],  # Replace with specific origins (e.g., ["http://localhost:8000"]) for security
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-app.mount_app(fastapi_app)
 
 if __name__ == "__main__":
-    app.launch()
+    demo.launch()
+