Update app.py

app.py

@@ -1,64 +1,38 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
-"""
-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")
+# 模型設定
+model_name = "ckiplab/gpt2-base-chinese"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
-
-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,
-    ):
-        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
-"""
-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)",
-        ),
-    ],
+system_prompt = (
+    "你是一位台灣公立高中總務處工作人員，使用繁體中文。你非常重視校園的職業安全衛生與防災安全議題，"
+    "並且遵守台北市教育局的相關法令。無論學生問你什麼問題，你都會將話題引導到這些議題上。\n"
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+def reply_fn(chat_history, user_msg):
+    full_prompt = system_prompt + ''.join([f"學生：{msg[0]}\n你：{msg[1]}\n" for msg in chat_history]) + f"學生：{user_msg}\n你："
+    inputs = tokenizer.encode(full_prompt, return_tensors="pt")
+    outputs = model.generate(inputs, max_new_tokens=100, do_sample=True, temperature=0.7)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    answer = response.split("你：")[-1].strip()
+    chat_history.append((user_msg, answer))
+    return chat_history, ""
+
+with gr.Blocks(theme=gr.themes.Soft(primary_hue="blue")) as demo:
+    gr.Markdown("""
+    # 🏫 總務處職安防災 AI 小幫手
+    歡迎使用！我是總務處的 AI 助理，任何問題我都會從 **職業安全衛生** 和 **校園防災** 的角度給你正確的建議 👷‍♂️🚒
+    """)
+    
+    chatbot = gr.Chatbot(show_copy_button=True)
+    msg = gr.Textbox(placeholder="請輸入你的問題...", label="學生提問")
+    clear = gr.Button("清除對話")
+
+    state = gr.State([])
+
+    msg.submit(reply_fn, [state, msg], [chatbot, msg])
+    clear.click(lambda: ([], ""), None, [chatbot, msg, state])
+
+demo.launch()