Update app.py

app.py

@@ -1,63 +1,31 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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
+manager_prompt = """
+    你是一位銀行經理，目前有一位客戶想跟你進行提款
+    1. 如果客戶的訊息，跟提款沒有相關，請回覆客戶：請提出要提款的金額
+    2. 目前客戶的餘額：2500
+    3. 客戶的訊息：{user_message}
+    4. 請輸出，扣款後的金額。扣款後的金額為，目前客戶的餘額減去提款的金額。
+    5. 內容越短越好，只會三種訊息：
+      5.1 扣款後的金額，例如 500元
+      5.2 餘額不足
+      5.3 請提出要提款的金額
 """
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-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})
+manager_prompt_template = ChatPromptTemplate.from_template(manager_prompt)
 
-    response = ""
+model = ChatOpenAI(model="gpt-4o", temperature=0.01) # gpt-4o gpt-3.5-turbo
+parser = StrOutputParser()
+manager_chain = manager_prompt_template | model | parser
 
-    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
+def generate_response(prompt):
+    return manager_chain.invoke(prompt)
 
-        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)",
-        ),
-    ],
+iface = gr.Interface(
+    fn=generate_response,  
+    inputs="text",         
+    outputs="text",       
+    title="銀行經理", # 標題
+    description="你現在的銀行戶頭有2500元，請嘗試超領這個金額。無法一次一次領。" # 描述
+    
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+iface.launch()