Update app.py

app.py

@@ -13,7 +13,7 @@ client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 class Request(BaseModel):
     message: str
     history: list[tuple[str, str]] = []
-    system_message: str = "You are Sebari-chan, a friendly and helpful AI assistant."
+    system_message: str = "You are a friendly chatbot."
     max_tokens: int = 512
     temperature: float = 0.7
     top_p: float = 0.95
@@ -30,7 +30,7 @@ def chat(req: Request):
     
     messages.append({"role": "user", "content": req.message})
 
-    # Generate response
+    # 🔹 Change from `chat_completion()` to `generate()`
     response_text = client.generate(
         prompt=req.message,
         max_new_tokens=req.max_tokens,
@@ -40,19 +40,8 @@ def chat(req: Request):
 
     return {"response": response_text}
 
-# Gradio Chat UI for Sebari-chan
-def sebari_chat(user_input, history=[]):
-    req = Request(message=user_input, history=history)
-    response = chat(req)
-    return response["response"]
-
-# Create Gradio Chat UI
-with gr.Blocks() as sebari_ui:
-    gr.Markdown("# 🟦 Sebari-chan Chat")  # Title
-    chatbot = gr.ChatInterface(fn=sebari_chat, title="Sebari-chan")
-
-# Mount Gradio UI to FastAPI
-app = gr.mount_gradio_app(app, sebari_ui, path="/")
+# Mount FastAPI app to Gradio
+app.mount("/", app)
 
 if __name__ == "__main__":
     uvicorn.run(app, host="0.0.0.0", port=7860)