from dotenv import load_dotenv from openai import OpenAI import json import os import requests from pypdf import PdfReader import gradio as gr # 確保載入 .env 檔案中的環境變數 load_dotenv(override=True) # --- 您的工具函式 (PushOver) --- def push(text): """ 使用 Pushover 服務發送通知。 需要 PUSHOVER_TOKEN 和 PUSHOVER_USER 環境變數。 """ requests.post( "https://api.pushover.net/1/messages.json", data={ "token": os.getenv("PUSHOVER_TOKEN"), "user": os.getenv("PUSHOVER_USER"), "message": text, } ) def record_user_details(email, name="Name not provided", notes="not provided"): """ 記錄有興趣保持聯繫的使用者資訊。 """ push(f"Recording user: {name} with email {email} and notes {notes}") return {"recorded": "ok", "message": f"Successfully recorded details for {name}."} def record_unknown_question(question): """ 記錄模型無法回答的問題，以便後續審查。 """ push(f"Recording unknown question: {question}") return {"recorded": "ok", "message": "Question noted for future reference."} # --- 您的工具定義 (JSON Schema) --- record_user_details_json = { "name": "record_user_details", "description": "Use this tool to record that a user is interested in being in touch and provided an email address", "parameters": { "type": "object", "properties": { "email": { "type": "string", "description": "The email address of this user" }, "name": { "type": "string", "description": "The user's name, if they provided it" } , "notes": { "type": "string", "description": "Any additional information about the conversation that's worth recording to give context" } }, "required": ["email"], "additionalProperties": False } } record_unknown_question_json = { "name": "record_unknown_question", "description": "Always use this tool to record any question that couldn't be answered as you didn't know the answer", "parameters": { "type": "object", "properties": { "question": { "type": "string", "description": "The question that couldn't be answered" }, }, "required": ["question"], "additionalProperties": False } } tools = [{"type": "function", "function": record_user_details_json}, {"type": "function", "function": record_unknown_question_json}] class Me: def __init__(self): # 設定 base_url 以使用 OpenAI 函式庫呼叫 Gemini API self.openai = OpenAI( base_url="https://generativelanguage.googleapis.com/v1beta/openai/" ) self.name = "Rika Choi" # 確保 'me' 資料夾和必要的檔案存在 try: reader = PdfReader("me/linkedin.pdf") self.linkedin = "" for page in reader.pages: text = page.extract_text() if text: self.linkedin += text with open("me/summary.txt", "r", encoding="utf-8") as f: self.summary = f.read() except FileNotFoundError as e: print(f"Error: Required file not found. Please ensure the 'me' folder contains 'linkedin.pdf' and 'summary.txt'. Error: {e}") self.linkedin = "LinkedIn profile data missing." self.summary = "Summary data missing." def handle_tool_call(self, tool_calls): """ 處理模型發出的工具呼叫，執行對應的函式並返回結果。 """ results = [] for tool_call in tool_calls: tool_name = tool_call.function.name arguments = json.loads(tool_call.function.arguments) print(f"Tool called: {tool_name}", flush=True) tool = globals().get(tool_name) result = tool(**arguments) if tool else {"error": f"Tool {tool_name} not found"} # 準備工具調用的結果格式 results.append({ "role": "tool", "content": json.dumps(result), "tool_call_id": tool_call.id }) return results def system_prompt(self): """ 根據個人資料生成系統提示詞。 """ system_prompt = f"You are acting as {self.name}. You are answering questions on {self.name}'s website, \ particularly questions related to {self.name}'s career, background, skills and experience. \ Your responsibility is to represent {self.name} for interactions on the website as faithfully as possible. \ You are given a summary of {self.name}'s background and LinkedIn profile which you can use to answer questions. \ Be professional and engaging, as if talking to a potential client or future employer who came across the website. \ If you don't know the answer to any question, use your record_unknown_question tool to record the question that you couldn't answer, even if it's about something trivial or unrelated to career. \ If the user is engaging in discussion, try to steer them towards getting in touch via email; ask for their email and record it using your record_user_details tool. " system_prompt += f"\n\n## Summary:\n{self.summary}\n\n## LinkedIn Profile:\n{self.linkedin}\n\n" system_prompt += f"With this context, please chat with the user, always staying in character as {self.name}." return system_prompt def chat(self, message, history): """ 與模型進行對話，處理對話歷史和工具呼叫。 修正了 Gradio 歷史記錄到 API 訊息格式的轉換。 """ # 🌟 關鍵修正: 轉換 Gradio 的歷史記錄格式 # Gradio 的 history 是 [(user_msg, assistant_msg), ...] 的元組列表 converted_history = [] for human, ai in history: # 1. 加入使用者訊息 converted_history.append({"role": "user", "content": human}) # 2. 加入 AI 訊息 (如果存在) if ai is not None: converted_history.append({"role": "assistant", "content": ai}) # 建立完整的 messages 列表 messages = ( [{"role": "system", "content": self.system_prompt()}] + converted_history + [{"role": "user", "content": message}] ) done = False while not done: # 呼叫 Gemini API response = self.openai.chat.completions.create( model="gemini-2.5-flash", messages=messages, tools=tools ) # 處理工具調用 (Tool Calling) if response.choices[0].finish_reason=="tool_calls": message = response.choices[0].message tool_calls = message.tool_calls results = self.handle_tool_call(tool_calls) messages.append(message) messages.extend(results) else: done = True return response.choices[0].message.content if __name__ == "__main__": me = Me() # 🌟 Gradio 介面美化和介紹資訊 intro_markdown = f"""

💼 與 {me.name} (徐可瑜) 的 AI 助手對話

嗨！我是Rika，專門協助企業把創新支出變成可節稅的費用，也讓智慧財產有法律的後盾。

## ✨ 擅長領域 * **稅務投抵輔導:** 研發、智機、資安、AI及節能減碳支出之稅務抵減輔導服務。 * **TIPS智財管理:** 智財管理制度建置之輔導及諮詢服務。 * **專利商標申請:** 國內外專利申請服務、國內外商標申請服務。 * **資格:** 中華民國專利師、TIPS智財管理制度自評員、ISO27001:2022資訊安全管理系統主導稽核員。 --- """ # 使用 gr.Blocks 來組織 Markdown 和 ChatInterface with gr.Blocks(title=f"{me.name} AI Chatbot") as demo: # 使用 Markdown 顯示介紹資訊 gr.Markdown(intro_markdown) # 創建 ChatInterface gr.ChatInterface( me.chat, title="請開始提問！", theme="soft", ) demo.launch()