Update app.py

app.py

@@ -1,47 +1,64 @@
 import gradio as gr
-import json
 from huggingface_hub import InferenceClient
-from fastapi import FastAPI
-from gradio.routes import mount_gradio_app
 
-# Load Hugging Face model
+"""
+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")
 
-# Create FastAPI app
-app = FastAPI()
 
-def respond(message: str, history):
-    if history is None:
-        history = []
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    messages = [{"role": "system", "content": system_message}]
 
-    messages = [{"role": "system", "content": "You are Sebari-chan, an AI assistant."}]
-
-    for user_msg, bot_reply in history:
-        if user_msg:
-            messages.append({"role": "user", "content": user_msg})
-        if bot_reply:
-            messages.append({"role": "assistant", "content": bot_reply})
+    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_text = ""
-    for message in client.chat_completion(messages, stream=True):
+    response = ""
+
+    for message in client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
+    ):
         token = message.choices[0].delta.content
-        response_text += token
 
-    # Update history
-    history.append((message, response_text))
+        response += token
+        yield response
 
-    return response_text, history
 
-# Gradio API
-gradio_app = gr.Interface(
-    fn=respond,
-    inputs=["text", gr.State()],  # Fix: Use gr.State() for history
-    outputs=["text", gr.State()]  # Fix: Match output structure
+"""
+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 (nucleus sampling)",
+        ),
+    ],
 )
 
-app = mount_gradio_app(app, gradio_app, path="/")
 
 if __name__ == "__main__":
-    app.run()
+    demo.launch()