import gradio as gr from openai import OpenAI from huggingface_hub import InferenceClient import os import time import requests import urllib.parse import pandas as pd from langchain_huggingface import HuggingFaceEmbeddings from langchain_community.vectorstores import FAISS from PIL import Image from dotenv import load_dotenv # --- [新增] 匯入組員的模組 --- import teammate_logic # --------------------------- load_dotenv() # 自動尋找並載入 .env 檔案中的變數 # ========================================== # 0. 環境變數 # ========================================== GROQ_API_KEY = os.getenv("GROQ_API_KEY") HF_TOKEN = os.getenv("HF_TOKEN") # 全域變數 global_df = None global_mood_df = None global_retriever = None rag_initialized = False # ========================================== # 1. 系統初始化 (讀取 CSV + 讀取 FAISS) # ========================================== def init_rag_system(): global global_df, global_mood_df, global_retriever, rag_initialized if rag_initialized: return print("⏳ 正在初始化系統...") # --- A. 讀取 CSV (用於篩選與對照) --- try: global_df = pd.read_csv('restaurants.csv') global_df['RAG_Content'] = global_df['RAG_Content'].fillna("") global_df['Category'] = global_df['Category'].fillna("其他") global_mood_df = pd.read_csv('mood_food_guide.csv') print(f"✅ CSV 資料讀取成功 (餐廳: {len(global_df)} 筆)") except Exception as e: print(f"❌ CSV 讀取失敗: {e}") return # --- B. 讀取預先建立好的 FAISS 索引 --- if os.path.exists("faiss_index"): try: print("⏳ 正在載入 FAISS 向量資料庫...") embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2") vectorstore = FAISS.load_local( "faiss_index", embeddings, allow_dangerous_deserialization=True ) global_retriever = vectorstore.as_retriever(search_kwargs={"k": 3}) print("✅ FAISS 資料庫載入完成！") except Exception as e: print(f"❌ FAISS 載入失敗: {e}") else: print("⚠️ 警告：找不到 'faiss_index' 資料夾，RAG 功能將無法使用。") print("請先執行 build_index.py 並上傳資料夾。") rag_initialized = True # ========================================== # 2. 核心功能 # ========================================== def get_restaurant_data(mood_score_str, food_choice): init_rag_system() if global_df is None or global_df.empty: return None, True, "資料庫未載入", "無建議" try: score = int(str(mood_score_str).split(' ')[0]) except: score = 3 mood_info = global_mood_df[global_mood_df['分數'] == score] if not mood_info.empty: rec_categories = mood_info.iloc[0]['推薦料理類別'] mood_reason = mood_info.iloc[0]['原因'] else: rec_categories = "" mood_reason = "隨意探索" candidates = global_df.copy() if rec_categories: candidates = candidates[candidates['Category'].apply(lambda x: str(x) in str(rec_categories) or str(rec_categories) in str(x))] food_keyword = "飯" if food_choice == "吃飯" else "麵" if food_choice == "吃麵" else "" if food_keyword: candidates = candidates[ candidates['Name'].str.contains(food_keyword, case=False, na=False) | candidates['RAG_Content'].str.contains(food_keyword, case=False, na=False) ] if candidates.empty: result = global_df.sample(1).iloc[0] is_random = True else: result = candidates.sample(1).iloc[0] is_random = False return result, is_random, rec_categories, mood_reason def generate_content_with_groq(restaurant_name, restaurant_detail, user_diary, mood_score, mood_guide_reason, debug_mode=False): if not GROQ_API_KEY: return "⚠️ 請設定 GROQ_API_KEY" client = OpenAI(api_key=GROQ_API_KEY, base_url="https://api.groq.com/openai/v1") system_prompt = "你是一個幽默、懂吃且善解人意的 AI 朋友。請根據使用者的日記、心情以及「心情美食指南」來推薦餐廳。" # 移除了測驗相關的 user_msg 內容 user_msg = f""" 【狀態】心情分數：{mood_score} 【日記】{user_diary} 【心情美食指南建議】 因為分數是 {mood_score}，建議吃這類食物的原因是：「{mood_guide_reason}」。 【推薦餐廳】 名稱：{restaurant_name} 資料：{restaurant_detail} 任務： 請用繁體中文寫一段溫暖有趣的回覆： 1. 綜合回應他的日記與心情。 2. 引用「心情美食指南」的原因。 3. 介紹這家餐廳的特色。 (只需要回覆文字內容) """ try: response = client.chat.completions.create( model="llama-3.3-70b-versatile", messages=[{"role": "system", "content": system_prompt}, {"role": "user", "content": user_msg}] ) content = response.choices[0].message.content # 如果開啟除錯模式，附加 Prompt 資訊 if debug_mode: debug_info = f""" \n\n--- 🛠️ [DEBUG] LLM Prompt 檢查 --- \n**System Prompt:**\n{system_prompt} \n**User Message:**\n{user_msg} \n----------------------------------- """ return content + debug_info return content except Exception as e: return f"Groq Error: {str(e)}" def generate_image_huggingface(prompt): if not HF_TOKEN: return None if not prompt or pd.isna(prompt): prompt = "Delicious gourmet food, photorealistic, 8k" try: hf_client = InferenceClient(token=HF_TOKEN) return hf_client.text_to_image(prompt=prompt, model="stabilityai/stable-diffusion-xl-base-1.0") except Exception as e: print(f"❌ 生圖失敗: {e}") return None def mood_agent_logic(score_input, food_input, diary_input, debug_mode): restaurant, is_random, rec_categories, mood_reason = get_restaurant_data(score_input, food_input) if restaurant is None: yield "資料庫讀取錯誤", None, "" return name = restaurant['Name'] address = restaurant['Address'] url = restaurant['URL'] img_prompt = restaurant.get('Visual_prompt') note = "(隨機推薦)" if is_random else "" # RAG 檢索 rag_info = str(restaurant.get('RAG_Content', '')) if global_retriever: docs = global_retriever.invoke(name) if docs: rag_info = "\n".join([d.page_content for d in docs]) # 呼叫生成函式 (已移除 quiz_state 參數) ai_text = generate_content_with_groq(name, rag_info, diary_input, score_input, mood_reason, debug_mode) # 如果開啟除錯模式，附加圖片 Prompt 資訊 if debug_mode: img_debug_info = f""" \n\n--- 🛠️ [DEBUG] 圖片生成檢查 --- \n**使用的 Visual Prompt:**\n{img_prompt} \n(如果上方圖片為空白，可能是 HF API 忙碌或 Prompt 無效) \n----------------------------------- """ ai_text += img_debug_info final_response = f"### 🍽️ 推薦：{name} {note}\n\n{ai_text}" map_html = f'
🗺️ Google Map 導航
' yield final_response, None, map_html image_output = generate_image_huggingface(img_prompt) yield final_response, image_output, map_html # ========================================== # 3. Gradio 介面建構 # ========================================== # 結合組員的 CSS combined_css = teammate_logic.css with gr.Blocks(title="AI 心情食堂", css=combined_css) as demo: with gr.Tabs(): # Tab 1: 主功能區 (已移除 Q1-Q5，直接顯示點餐介面) with gr.TabItem("🍽️ AI 心情食堂 (點餐推薦)", id=0): with gr.Column(): gr.Markdown(f"## 🍱 呷飽沒？？！") with gr.Row(): with gr.Column(scale=1): score_input = gr.Radio(["1 (心情差)", "2 (不太好)", "3 (普通)", "4 (不錯)", "5 (超棒)"], label="1. 心情分數", value="3 (普通)") food_input = gr.Radio(["吃飯", "吃麵", "隨便"], label="2. 想吃什麼", value="隨便") diary_input = gr.Textbox(lines=4, label="3. 心情日記", placeholder="寫下今天發生的事...") debug_mode_btn = gr.Checkbox(label="🔧 開啟除錯模式 (顯示 Prompt 與圖片資訊)", value=False) submit_btn = gr.Button("送出給 Agent", variant="primary") with gr.Column(scale=1): agent_output = gr.Markdown(label="AI 回應") image_output = gr.Image(label="AI 推薦美食圖", type="pil", width=400) map_output = gr.HTML(label="地圖導航") # Tab 2: 組員功能 with gr.TabItem("情緒辨識 (組員功能)", id=1): teammate_logic.render_ui() # 呼叫組員的介面渲染函式 # 事件綁定 (只保留主功能) submit_btn.click( fn=mood_agent_logic, inputs=[score_input, food_input, diary_input, debug_mode_btn], outputs=[agent_output, image_output, map_output] ) if __name__ == "__main__": demo.launch(ssr_mode=False)