import gradio as gr from openai import OpenAI from huggingface_hub import InferenceClient import os import sys import subprocess 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 # ========================================== # Step 0: 環境安裝檢查 (僅保留 Playwright) # ========================================== def install_playwright(): """確保 Playwright 瀏覽器核心有安裝""" try: import playwright except ImportError: print("⚠️ 偵測到缺少 playwright，正在強制安裝...") subprocess.check_call([sys.executable, "-m", "pip", "install", "playwright"]) # 設定瀏覽器路徑 os.environ["PLAYWRIGHT_BROWSERS_PATH"] = os.path.join(os.getcwd(), "playwright_browsers") print("🔄 檢查 Chromium 瀏覽器...") try: # 檢查是否已安裝，若無則安裝 if not os.path.exists(os.environ["PLAYWRIGHT_BROWSERS_PATH"]): subprocess.run([sys.executable, "-m", "playwright", "install", "chromium"], check=True) except Exception as e: print(f"⚠️ 瀏覽器安裝警告: {e}") # 執行安裝 install_playwright() # 延遲匯入 from playwright.sync_api import sync_playwright load_dotenv() # ========================================== # 模組載入 (emotion 模組) # ========================================== import emotion # ========================================== # 0. 環境變數 & 1. 資料初始化 # ========================================== GROQ_API_KEY = os.getenv("GROQ_API_KEY") HF_TOKEN = os.getenv("HF_TOKEN") global_df = None global_mood_df = None global_retriever = None rag_initialized = False def init_static_data(): """初始化靜態的心情資料：讀取外部 CSV""" global global_mood_df if global_mood_df is None: csv_path = 'mood_food_guide.csv' if os.path.exists(csv_path): try: # 讀取 CSV，確保欄位正確 global_mood_df = pd.read_csv(csv_path) print(f"✅ 成功載入心情指南：{csv_path}") except Exception as e: print(f"❌ 讀取 CSV 失敗: {e}") global_mood_df = pd.DataFrame() # 建立空表防止後續報錯 else: print(f"⚠️ 警告：找不到 {csv_path}，請確認檔案已上傳至 Space。") global_mood_df = pd.DataFrame() # ========================================== # API 金鑰檢查工具函式 # ========================================== def check_api_key_status(name, key): """檢查 API Key 是否存在，並回傳部分內容以供辨識""" if not key: return "❌ 未設定 (Not Set)" # 遮罩處理，只顯示前後幾碼 if len(key) > 8: masked = f"{key[:4]}...{key[-4:]}" else: masked = "******" return f"✅ 已設定 ({masked})" # ========================================== # 2. Google Maps 爬蟲功能 # ========================================== def sync_google_maps(url): global global_df, global_retriever, rag_initialized clean_url = url.strip() if url else "" if not clean_url or "http" not in clean_url.lower(): yield "❌ 請輸入有效的 Google Maps 分享連結。" return try: yield "🚀 [1/4] 啟動瀏覽器..." with sync_playwright() as p: browser = p.chromium.launch(headless=True) page = browser.new_page() yield "🌐 [2/4] 連線中..." page.goto(clean_url, wait_until="domcontentloaded", timeout=60000) yield "⏳ [3/4] 等待列表加載 (約 10 秒)..." time.sleep(10) yield "📄 [4/4] 解析餐廳資訊..." titles = page.locator('div.fontHeadlineSmall').all_inner_texts() details = page.locator('div.fontBodyMedium').all_inner_texts() restaurant_list = [] for i, name in enumerate(titles): name = name.strip() if name: addr = details[i].strip() if i < len(details) else "" search_query = f"{name} {addr}" restaurant_list.append({ "Name": name, "Address": addr, "Category": "未分類", "RAG_Content": f"餐廳：{name}，資訊：{addr}", "URL": f"https://www.google.com/maps/search/?api=1&query={urllib.parse.quote(search_query)}" }) browser.close() if not restaurant_list: yield "⚠️ 找不到餐廳。請確認連結格式正確且已公開。" return global_df = pd.DataFrame(restaurant_list) try: embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2") vectorstore = FAISS.from_texts(global_df['RAG_Content'].tolist(), embeddings, metadatas=global_df.to_dict('records')) global_retriever = vectorstore.as_retriever(search_kwargs={"k": 3}) except Exception as e: print(f"RAG 初始化警告: {e}") rag_initialized = True yield f"✅ 同步成功！已載入 {len(restaurant_list)} 間餐廳。" except Exception as e: yield f"❌ 系統錯誤：{str(e)}" # ========================================== # 3. 核心功能 (AI Agent) # ========================================== def get_restaurant_data(mood_score_str, food_choice): init_static_data() # 確保心情指南已載入 if global_df is None or global_df.empty: return None, True, "", "資料庫未載入，無建議" # 解析分數 (例如 "3 (普通)" -> 3) try: score = int(str(mood_score_str).split(' ')[0]) except: score = 3 # 從 CSV 資料中查找對應的推薦類別與原因 rec_categories = "" mood_reason = "隨意探索" if global_mood_df is not None and not global_mood_df.empty: 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'] candidates = global_df.copy() food_keyword = "飯" if food_choice == "吃飯" else "麵" if food_choice == "吃麵" else "" is_random = False if food_keyword: filtered = candidates[candidates['Name'].str.contains(food_keyword, case=False, na=False) | candidates['RAG_Content'].str.contains(food_keyword, case=False, na=False)] if not filtered.empty: candidates = filtered else: is_random = True if candidates.empty: result = global_df.sample(1).iloc[0]; is_random = True else: result = candidates.sample(1).iloc[0] 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。" 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. 先回應他的日記與測驗人設。 2. 引用「心情美食指南」的原因，告訴他為什麼現在適合吃這家餐廳。 3. 介紹這家餐廳的特色。 """ debug_log = "" if debug_mode: debug_log = f"### 🔧 Groq Prompt Debug\n**System:** {system_prompt}\n**User:** {user_msg}" try: response = client.chat.completions.create(model="llama-3.3-70b-versatile", messages=[{"role": "system", "content": system_prompt}, {"role": "user", "content": user_msg}]) return response.choices[0].message.content, debug_log except Exception as e: return f"Groq Error: {str(e)}", debug_log def generate_image_huggingface(prompt): if not HF_TOKEN: return None, "HF_TOKEN 未設定" try: hf_client = InferenceClient(token=HF_TOKEN) image = hf_client.text_to_image( prompt=prompt, negative_prompt="blurry, low quality, distortion, text, watermark", model="stabilityai/stable-diffusion-xl-base-1.0" ) return image, None # 成功時，錯誤訊息為 None except Exception as e: # 回傳具體錯誤訊息 return None, str(e) def mood_agent_logic(score_input, food_input, diary_input, debug_mode): if not rag_initialized: yield "⚠️ 請先同步地圖清單！", None, "", gr.update() return 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, "", gr.update() return name = restaurant['Name']; url = restaurant['URL'] info = restaurant.get('RAG_Content', '') rag_info = str(restaurant.get('RAG_Content', '')) img_prompt = f"Delicious food photography of {name}, {info}. high quality, photorealistic, 8k, cinematic lighting, appetizing, restaurant atmosphere, 50mm lens" ai_text, groq_debug_log = generate_content_with_groq(name, rag_info, diary_input, score_input, mood_reason, debug_mode) prefix = "" if is_random and food_input != "隨便": prefix = f"> 💡 **溫馨提示**：清單中暫無『{food_input}』，已從現有名單挑選最適合的店！\n\n" # 組合完整的除錯資訊，包含 API Key 狀態與錯誤訊息 full_debug_log = "" if debug_mode: # 1. 檢查 Key 狀態 groq_status = check_api_key_status("GROQ_API_KEY", GROQ_API_KEY) hf_status = check_api_key_status("HF_TOKEN", HF_TOKEN) api_debug_block = f""" ### 🔑 API 金鑰與系統狀態 - **GROQ_API_KEY**: {groq_status} - **HF_TOKEN**: {hf_status} - **RAG 狀態**: {"✅ 已初始化" if rag_initialized else "❌ 未初始化"} """ full_debug_log = api_debug_block + "\n" + groq_debug_log + f"\n\n### 🎨 Image Prompt Debug\n{img_prompt}" debug_output_update = gr.update(value=full_debug_log, visible=debug_mode) final_response = f"{prefix}### 🍽️ 推薦：{name}\n\n{ai_text}" map_html = f'
🗺️ Google Map 導航
' # 先回傳文字 yield final_response, None, map_html, debug_output_update # 呼叫圖片生成並捕捉錯誤 image_output, img_error = generate_image_huggingface(img_prompt) # 如果有圖片錯誤且在除錯模式，追加錯誤訊息到 log if img_error and debug_mode: full_debug_log += f"\n\n⚠️ **Hugging Face 圖片生成失敗:**\n{img_error}" debug_output_update = gr.update(value=full_debug_log) yield final_response, image_output, map_html, debug_output_update # ========================================== # 4. 橋接邏輯 # ========================================== def _score_to_radio_value(score): mapping = {1: "1 (心情差)", 2: "2 (不太好)", 3: "3 (普通)", 4: "4 (不錯)", 5: "5 (超棒)"} try: score = int(score) except: score = 3 return mapping.get(score, "3 (普通)") def bridge_start_click(st): try: res = emotion.on_restart(st) return res[1], res[0], gr.update(visible=True), res[5], res[4], gr.update(visible=False) except: return gr.update(), gr.update(), gr.update(), gr.update(), st, gr.update() def bridge_stop_click(st): try: res = emotion.on_stop(st) return res[1], res[0], gr.update(visible=False), res[5], res[4] except: return gr.update(), gr.update(), gr.update(), gr.update(), st def bridge_predict_frame(frame, st): try: res = emotion.on_stream(frame, st) out_cam = res[0]; out_result = res[1]; out_st = res[4]; out_btn_start = res[5] score_update = gr.update(); btn_go_visible = gr.update(visible=False) out_btn_stop = gr.update() if hasattr(out_st, 'finished') and out_st.finished and hasattr(out_st, 'final_score'): new_val = _score_to_radio_value(out_st.final_score) score_update = gr.update(value=new_val) out_btn_stop = gr.update(visible=False) btn_go_visible = gr.update(visible=True) return out_cam, out_result, out_st, out_btn_stop, out_btn_start, score_update, btn_go_visible except Exception as e: return frame, gr.update(), st, gr.update(), gr.update(), gr.update(), gr.update() def bridge_predict_upload(img, st): try: res = emotion.on_upload(img, st) out_result, out_st = res[0], res[2] score_update = gr.update() if hasattr(out_st, 'finished') and out_st.finished and hasattr(out_st, 'final_score'): new_val = _score_to_radio_value(out_st.final_score) score_update = gr.update(value=new_val) return out_result, score_update, gr.Tabs(selected=1), out_st except: return gr.update(), gr.update(), gr.Tabs(), st # ========================================== # 5. Gradio 介面 # ========================================== css_ = "#app_container { max-width: 960px; margin: 0 auto; }" if hasattr(emotion, 'css'): css_ += "\n" + emotion.css with gr.Blocks(title="AI 心情食堂", css=css_) as demo: st_state = gr.State(emotion.AppState()) with gr.Tabs() as tabs: # Tab 1 with gr.TabItem("😊 情緒辨識 (Step 1)", id=0): with gr.Column(elem_id="app_container"): gr.Markdown("### 第一步：測測你的心情能量\n讓 AI 看看你的表情，自動幫你決定心情分數！") with gr.Row(): btn_start = gr.Button("📸 開啟攝影機辨識", variant="primary") btn_stop = gr.Button("⏹️ 停止", variant="secondary", visible=False) cam = gr.Image(sources=["webcam"], streaming=True, type="numpy", label="攝影機畫面", visible=False) result_markdown = gr.Markdown(emotion._hint_html("請按「開啟攝影機辨識」並允許瀏覽器使用相機。")) btn_go_dining = gr.Button("🚀 確定心情，來找餐廳！", variant="primary", visible=False, size="lg") # Tab 2 with gr.TabItem("🍽️ AI 心情食堂 (Step 2)", id=1): with gr.Column(): gr.Markdown(f"## 🔗 載入你的口袋名單") with gr.Row(): map_url = gr.Textbox(label="Google Maps Saved Lists 連結", placeholder="請貼上清單的分享連結...", scale=3) sync_btn = gr.Button("🔄 同步清單", variant="secondary", scale=1) sync_msg = gr.Markdown("ℹ️ 尚未同步資料庫") gr.Markdown("---") gr.Markdown(f"## 🍱 今天想吃點什麼？") 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 (由 Tab 1 自動填入)", 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", value=False) submit_btn = gr.Button("🍱 送出給 Agent", variant="primary") debug_output = gr.Markdown(label="除錯資訊 (Debug Log)", visible=False) 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") # 事件 sync_btn.click(fn=sync_google_maps, inputs=[map_url], outputs=[sync_msg]) btn_start.click(fn=bridge_start_click, inputs=[st_state], outputs=[result_markdown, cam, btn_stop, btn_start, st_state, btn_go_dining]) btn_stop.click(fn=bridge_stop_click, inputs=[st_state], outputs=[result_markdown, cam, btn_stop, btn_start, st_state]) cam.stream(fn=bridge_predict_frame, inputs=[cam, st_state], outputs=[cam, result_markdown, st_state, btn_stop, btn_start, score_input, btn_go_dining]) btn_go_dining.click(fn=lambda: gr.Tabs(selected=1), inputs=None, outputs=tabs) # debug_mode submit_btn.click( fn=mood_agent_logic, inputs=[score_input, food_input, diary_input, debug_mode_btn], outputs=[agent_output, image_output, map_output, debug_output] ) if __name__ == "__main__": demo.launch(ssr_mode=False)