Update app.py

app.py

@@ -20,17 +20,16 @@ from deepface import DeepFace
 warnings.filterwarnings("ignore")
 
 # ==========================================
-#  環境變數與 RAG 初始化
+# 0. 環境變數與 RAG 初始化 (維持不變)
 # ==========================================
 GROQ_API_KEY = os.getenv("GROQ_API_KEY")
 HF_TOKEN = os.getenv("HF_TOKEN")
 
-# --- 1. 資料讀取 (主要資料庫 - 使用 restaurants.csv) ---
+# --- 資料讀取 ---
 df = pd.DataFrame()
 try:
-    # 確保你有 restaurants.csv 在專案根目錄
     df = pd.read_csv('restaurants.csv', engine='python') 
-    df.columns = df.columns.str.strip() # 清理欄位空白
+    df.columns = df.columns.str.strip() 
 
     def classify_mood(row):
         name_str = str(row.get('Name', ''))
@@ -38,10 +37,10 @@ try:
         text = (name_str + " " + rag_str).lower()
         tags = []
         rules = {
-            "開心/慶祝": ["牛排", "steak", "pizza", "炸", "雞排", "甜點", "蛋糕", "cake", "冰", "waffle", "吃到飽", "buffet", "burger", "bistro", "餐酒館"],
-            "傷心/疲憊": ["粥", "湯", "warm", "congee", "麵", "noodle", "小吃", "comfort food", "豆花", "關東煮", "soup"],
-            "生氣/發洩": ["辣", "spicy", "麻辣", "鍋", "curry", "咖哩", "燒肉", "bbq", "臭豆腐", "fry"],
-            "平靜/放鬆": ["cafe", "coffee", "tea", "茶", "素食", "vegetable", "早午餐", "brunch", "壽司", "sushi", "居酒屋"]
+            "開心/慶祝": ["牛排", "steak", "pizza", "炸", "甜點", "蛋糕", "buffet", "bistro"],
+            "傷心/疲憊": ["粥", "湯", "warm", "麵", "小吃", "豆花", "soup"],
+            "生氣/發洩": ["辣", "spicy", "麻辣", "鍋", "curry", "燒肉", "bbq", "fry"],
+            "平靜/放鬆": ["cafe", "coffee", "tea", "素食", "brunch", "sushi", "居酒屋"]
         }
         for mood, keywords in rules.items():
             for kw in keywords:
@@ -52,26 +51,21 @@ try:
         
     if 'Mood_Tags' not in df.columns:
         df['Mood_Tags'] = df.apply(classify_mood, axis=1)
-    
-    print("✅ 成功讀取 restaurants.csv 並建立 Mood_Tags")
+    print("✅ 成功讀取 restaurants.csv")
 except Exception as e:
-    # 如果找不到檔案或讀取失敗，這裡會提醒
     print(f"⚠️ 讀取 restaurants.csv 失敗: {e}") 
 
-# --- 2. 資料讀取 (Prompt 資料庫) ---
+# --- Prompt 資料庫 ---
 df_prompts = pd.DataFrame()
 PROMPT_COL_NAME = 'Visual_prompt' 
-
 try:
     if not df.empty:
         df_prompts = df.copy()
         if 'Name' in df_prompts.columns:
             df_prompts.set_index('Name', inplace=True)
-except Exception as e:
-    print(f"⚠️ 處理 Prompt 資料發生錯誤: {e}")
+except: pass
 
-
-# --- RAG 建置 ---
+# --- RAG ---
 retriever = None
 if not df.empty and 'RAG_Content' in df.columns:
     try:
@@ -82,16 +76,14 @@ if not df.empty and 'RAG_Content' in df.columns:
         embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
         vectorstore = FAISS.from_documents(docs, embeddings)
         retriever = vectorstore.as_retriever(search_kwargs={"k": 3})
-    except Exception as e:
-        print(f"⚠️ RAG 初始化失敗: {e}")
+    except: pass
 
 # ==========================================
-#  核心功能函式 (餐廳推薦邏輯)
+# 1. 核心功能函式 (餐廳推薦 - 維持不變)
 # ==========================================
 
 def get_restaurant_data(mood_score_str, food_choice):
     if df.empty: return None, True
-    # 定義分數與 Mood_Tags 的對應關係 (與舊版維持一致)
     score_map = {
         "1 (心情差)": ["傷心/疲憊", "生氣/發洩"],
         "2 (不太好)": ["傷心/疲憊", "生氣/發洩"],
@@ -105,11 +97,10 @@ def get_restaurant_data(mood_score_str, food_choice):
     elif food_choice == "吃麵": food_keyword = "麵"
 
     candidates = df.copy()
-    if 'Mood_Tags' not in candidates.columns: return df.sample(1).iloc[0], True
-
     if target_moods:
         pattern = "|".join(target_moods)
-        candidates = candidates[candidates['Mood_Tags'].str.contains(pattern, regex=True, na=False)]
+        if 'Mood_Tags' in candidates.columns:
+            candidates = candidates[candidates['Mood_Tags'].str.contains(pattern, regex=True, na=False)]
     
     if food_keyword:
         candidates = candidates[
@@ -120,23 +111,11 @@ def get_restaurant_data(mood_score_str, food_choice):
     if candidates.empty: return df.sample(1).iloc[0], True
     return candidates.sample(1).iloc[0], False
 
-# 注意：因為移除了測驗，這裡我們用 '無測驗' 作為預設結果
 def generate_content_with_groq(restaurant_name, restaurant_detail, user_diary, mood_score):
-    if not GROQ_API_KEY: return "⚠️ 請設定 GROQ_API_KEY (系統變數)"
+    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和心情來推薦餐廳。"
-    user_msg = f"""
-    【使用者狀態】
-    心情分數：{mood_score}
-    心情日記：{user_diary}
-    【推薦餐廳】
-    名稱：{restaurant_name}
-    資料：{restaurant_detail}
-    請完成任務：
-    【回應內容】：用繁體中文寫一段溫暖有趣的回覆。
-       - 結合「日記」與「心情」給予回應。
-       - 推薦上述餐廳，說明為什麼這家店適合他。
-    """
+    user_msg = f"心情：{mood_score}\n日記：{user_diary}\n餐廳：{restaurant_name}\n資料：{restaurant_detail}\n請推薦這家餐廳並給予安慰或慶祝。"
     try:
         response = client.chat.completions.create(
             model="llama-3.3-70b-versatile", 
@@ -153,24 +132,18 @@ def generate_image_huggingface(prompt):
         return hf_client.text_to_image(prompt=prompt, model="stabilityai/stable-diffusion-xl-base-1.0")
     except: return None
 
-# --- 主邏輯 Agent ---
-# 移除了 quiz_state 參數
 def mood_agent_logic(score_input, food_input, diary_input, debug_mode):
-    # 確保 score_input 有值
     if not score_input:
-        yield "⚠️ 請先選擇心情分數，或使用上方相機偵測！", None, ""
+        yield "⚠️ 請先選擇心情分數！", None, ""
         return
 
     restaurant, is_random = get_restaurant_data(score_input, food_input)
     if restaurant is None:
-        yield "資料庫讀取錯誤或為空", None, ""
+        yield "資料庫讀取錯誤", None, ""
         return
 
     name = str(restaurant['Name'])
     url = str(restaurant.get('URL', f'https://www.google.com/maps/search/?api=1&query={urllib.parse.quote(name)}'))
-    note = "(隨機推薦)" if is_random else ""
-
-    # 1. 處理 RAG
     rag_info = str(restaurant.get('RAG_Content', ''))
     if retriever:
         try:
@@ -178,29 +151,17 @@ def mood_agent_logic(score_input, food_input, diary_input, debug_mode):
             if docs: rag_info = "\n".join([d.page_content for d in docs])
         except: pass
 
-    # 2. 準備圖片 Prompt
-    img_prompt = f"Delicious food from {name}, cinematic lighting, 8k, photorealistic"
-    prompt_source = "⚠️ 預設生成"
-
-    if not df_prompts.empty and PROMPT_COL_NAME in df_prompts.columns:
-        if name in df_prompts.index:
-            try:
-                csv_prompt = df_prompts.loc[name, PROMPT_COL_NAME]
-                if isinstance(csv_prompt, pd.Series): csv_prompt = csv_prompt.iloc[0]
-                if pd.notna(csv_prompt) and str(csv_prompt).strip() != "":
-                    img_prompt = str(csv_prompt)
-                    prompt_source = "✅ CSV 檔案"
-            except: pass
-
-    # 3. 呼叫 LLM (移除了 quiz_state)
+    img_prompt = f"Delicious food from {name}, cinematic lighting, 8k"
+    if not df_prompts.empty and name in df_prompts.index:
+        try:
+            val = df_prompts.loc[name, PROMPT_COL_NAME]
+            if isinstance(val, pd.Series): val = val.iloc[0]
+            if pd.notna(val): img_prompt = str(val)
+        except: pass
+
     ai_text = generate_content_with_groq(name, rag_info, diary_input, score_input)
-    
-    # 4. 組合回應
-    debug_text = ""
-    if debug_mode:
-        debug_text = f"\n\n---\n**🛠️ Prompt 來源**: {prompt_source}\n**Prompt**: `{img_prompt}`"
-    
-    final_response = f"### 🍽️ 推薦：{name} {note}\n\n{ai_text}{debug_text}"
+    debug_text = f"\n\nPrompt: `{img_prompt}`" if debug_mode else ""
+    final_response = f"### 🍽️ 推薦：{name}\n\n{ai_text}{debug_text}"
     map_html = f'<div style="text-align:center"><a href="{url}" target="_blank" style="background:#4CAF50;color:white;padding:8px 16px;border-radius:20px;text-decoration:none">🗺️ Google Map 導航</a></div>'
     
     yield final_response, None, map_html
@@ -208,16 +169,11 @@ def mood_agent_logic(score_input, food_input, diary_input, debug_mode):
     yield final_response, image_output, map_html
 
 # ==========================================
-#  [修改] 情緒辨識整合模組
+# 2. 情緒辨識整合模組
 # ==========================================
 
-# 定義中文字典 (繪圖用)
-emotion_text_obj = {
-    'angry': '生氣', 'disgust': '噁心', 'fear': '害怕',
-    'happy': '開心', 'sad': '難過', 'surprise': '驚訝', 'neutral': '正常'
-}
+emotion_text_obj = {'angry': '生氣', 'disgust': '噁心', 'fear': '害怕', 'happy': '開心', 'sad': '難過', 'surprise': '驚訝', 'neutral': '正常'}
 
-# 繪圖函式 (維持不變)
 def putText(img, x, y, text, size=50, color=(255, 255, 255)):
     try:
         fontpath = 'NotoSansTC-VariableFont_wght.ttf'
@@ -228,64 +184,68 @@ def putText(img, x, y, text, size=50, color=(255, 255, 255)):
         displayText = emotion_text_obj.get(text, text)
         draw.text((x, y), displayText, fill=color, font=font)
         return np.array(imgPil)
-    except:
-        return img
+    except: return img
 
-# ★ 新增：按鈕切換函式 (控制按鈕的文字與顏色)
-def toggle_recording(is_recording):
-    # 切換狀態 (True <-> False)
-    new_state = not is_recording
-    
-    if new_state:
-        # 如果變成錄製中，按鈕變成紅色「停止」
-        return new_state, gr.Button(value="🛑 停止錄製 (鎖定結果)", variant="stop")
-    else:
-        # 如果變成停止，按鈕變成綠色「開始」
-        return new_state, gr.Button(value="📸 開始即時偵測", variant="secondary")
-
-# ★ 修改：偵測邏輯 (加入 is_recording 判斷)
-def detect_emotion_stream(frame, is_recording):
-    # 如果沒有在錄製，或是沒有畫面，就什麼都不更新 (讓畫面凍結在最後一幀)
-    if not is_recording or frame is None:
-        return gr.update(), gr.update()
-    
+# 核心辨識函式 (重構以供重複使用)
+def process_emotion(frame):
     detected_emotion = "neutral" 
     mapped_score = "3 (普通)"    
-
     try:
-        # 1. 辨識情緒
         analyze = DeepFace.analyze(frame, actions=['emotion'], enforce_detection=False)
         if isinstance(analyze, list): analyze = analyze[0]
         detected_emotion = analyze['dominant_emotion']
         
-        # 2. 畫在圖片上
         frame = putText(frame, 20, 40, detected_emotion)
 
-        # 3. 分數轉換
-        if detected_emotion == 'happy':
-            mapped_score = "5 (超棒)"
-        elif detected_emotion == 'surprise':
-            mapped_score = "4 (不錯)"
-        elif detected_emotion == 'neutral':
-            mapped_score = "3 (普通)"
-        elif detected_emotion in ['sad', 'fear']:
-            mapped_score = "2 (不太好)"
-        elif detected_emotion in ['angry', 'disgust']:
-            mapped_score = "1 (心情差)"
+        if detected_emotion == 'happy': mapped_score = "5 (超棒)"
+        elif detected_emotion == 'surprise': mapped_score = "4 (不錯)"
+        elif detected_emotion == 'neutral': mapped_score = "3 (普通)"
+        elif detected_emotion in ['sad', 'fear']: mapped_score = "2 (不太好)"
+        elif detected_emotion in ['angry', 'disgust']: mapped_score = "1 (心情差)"
+    except: pass
+    return frame, mapped_score
 
-    except Exception as e:
-        pass
+# 單次手動截圖
+def manual_detect(frame):
+    if frame is None: return None, None
+    return process_emotion(frame)
+
+# ★ 新增：切換錄製狀態按鈕邏輯
+def toggle_recording_state(is_recording):
+    # 切換 True/False
+    new_state = not is_recording
+    # 根據新狀態改變按鈕文字
+    if new_state:
+        return new_state, "⏹️ 停止錄製 (即時偵測中)"
+    else:
+        return new_state, "🔴 開始錄製 (即時偵測)"
+
+# ★ 新增：自動串流偵測 (包含限速邏輯)
+def auto_stream_detect(frame, is_recording, last_time):
+    # 如果沒開錄製，或畫面空的，就跳過不做事 (節省資源)
+    if not is_recording or frame is None:
+        return gr.skip(), gr.skip(), last_time
     
-    return frame, mapped_score
+    # 限速：距離上次執行不到 1.0 秒，就跳過
+    current_time = time.time()
+    if current_time - last_time < 1.0:
+        return gr.skip(), gr.skip(), last_time
+        
+    # 執行辨識
+    processed_frame, score = process_emotion(frame)
+    
+    # 回傳：更新圖片, 更新分數, 更新最後執行時間
+    return processed_frame, score, current_time
 
 # ==========================================
-#  Gradio 介面建構 (修改版)
+# 3. Gradio 介面建構
 # ==========================================
 
 with gr.Blocks(title="AI 心情食堂") as demo:
     
-    # ★ 1. 定義一個變數來記錄狀態 (預設是 False 停止中)
-    recording_state = gr.State(value=False)
+    # 定義狀態變數 (看不見的變數)
+    is_recording = gr.State(False) # 是否正在錄製
+    last_process_time = gr.State(0) # 上次偵測的時間
 
     with gr.Column(visible=True) as main_app_col: 
         gr.Markdown(f"## 🍱 AI 心情食堂導航")
@@ -294,16 +254,19 @@ with gr.Blocks(title="AI 心情食堂") as demo:
         with gr.Row():
             # 左側：輸入區
             with gr.Column(scale=1):
+                gr.Markdown("### 📸 步驟 1：心情偵測")
                 
-                gr.Markdown("### 📸 步驟 1：心情偵測 (選用)")
                 with gr.Row():
                     # 左邊：即時鏡頭
                     webcam_input = gr.Image(sources=["webcam"], label="即時鏡頭", streaming=True)
-                    # 右邊：結果畫面 (互動模式設為 False)
-                    captured_image = gr.Image(label="即時偵測結果", interactive=False)
+                    # 右邊：偵測結果
+                    captured_image = gr.Image(label="偵測結果", interactive=False)
                 
-                # 按鈕預設為「開始」
-                detect_btn = gr.Button("📸 開始即時偵測", variant="secondary")
+                with gr.Row():
+                    # 按鈕 1：錄製開關 (會變色變字)
+                    record_btn = gr.Button("🔴 開始錄製 (即時偵測)", variant="stop")
+                    # 按鈕 2：單次截圖 (維持不變)
+                    snapshot_btn = gr.Button("📸 單次截圖", variant="secondary")
                 
                 gr.Markdown("### 📝 步驟 2：確認與補充")
                 score_input = gr.Radio(
@@ -312,35 +275,42 @@ with gr.Blocks(title="AI 心情食堂") as demo:
                     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=3, label="3. 心情日記 (選填)", placeholder="例如：今天被老闆罵了，想吃點好料的...")
+                diary_input = gr.Textbox(lines=3, label="3. 心情日記", placeholder="選填...")
                 
-                debug_mode_btn = gr.Checkbox(label="🔧 顯示 Prompt 除錯資訊", value=False)
+                debug_mode_btn = gr.Checkbox(label="🔧 除錯資訊", value=False)
                 submit_btn = gr.Button("🚀 送出給 Agent", variant="primary")
 
-            # 右側：Agent 輸出區
+            # 右側：輸出區
             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")
 
-    # Events 
-    
-    # ★ 事件 1：按鈕點擊 -> 切換錄製狀態 -> 更新按鈕樣子
-    detect_btn.click(
-        fn=toggle_recording,
-        inputs=[recording_state],
-        outputs=[recording_state, detect_btn]
+    # --- 事件綁定 ---
+
+    # 1. 錄製按鈕邏輯：點擊 -> 切換狀態 -> 改變按鈕文字
+    record_btn.click(
+        fn=toggle_recording_state,
+        inputs=[is_recording],
+        outputs=[is_recording, record_btn]
     )
 
-    # ★ 事件 2：鏡頭串流 (Stream) -> 只要鏡頭有畫面就會觸發
-    # 它會檢查 recording_state，如果是 True 才會更新右邊的圖
+    # 2. 串流偵測邏輯：鏡頭畫面改變 -> 檢查狀態 -> (如果錄製中) 執行偵測 -> 更新右邊圖片
     webcam_input.stream(
-        fn=detect_emotion_stream,
-        inputs=[webcam_input, recording_state],
+        fn=auto_stream_detect,
+        inputs=[webcam_input, is_recording, last_process_time],
+        outputs=[captured_image, score_input, last_process_time],
+        show_progress=False # 隱藏進度條，讓畫面更順暢
+    )
+
+    # 3. 單次截圖邏輯 (維持不變)
+    snapshot_btn.click(
+        fn=manual_detect,
+        inputs=[webcam_input],
         outputs=[captured_image, score_input]
     )
 
-    # 提交按鈕
+    # 4. 送出 Agent
     submit_btn.click(
         fn=mood_agent_logic,
         inputs=[score_input, food_input, diary_input, debug_mode_btn],