Blame for app.py

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_community.document_loaders import DataFrameLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_huggingface import HuggingFaceEmbeddings
from langchain_community.vectorstores import FAISS
from PIL import Image, ImageFont, ImageDraw
import warnings
import cv2
import numpy as np
from deepface import DeepFace

# 忽略 pandas 的一些警告
warnings.filterwarnings("ignore")

# ==========================================
# 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")

# --- 資料讀取 ---
df = pd.DataFrame()
try:
    df = pd.read_csv('restaurants.csv', engine='python') 
    df.columns = df.columns.str.strip() 

    def classify_mood(row):
        name_str = str(row.get('Name', ''))
        rag_str = str(row.get('RAG_Content', ''))
        text = (name_str + " " + rag_str).lower()
        tags = []
        rules = {
            "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:
                if kw in text:
                    tags.append(mood)
        if not tags: tags.append("隨意/探索")
        return ", ".join(list(set(tags)))
        
    if 'Mood_Tags' not in df.columns:
        df['Mood_Tags'] = df.apply(classify_mood, axis=1)
    print("✅ 成功讀取 restaurants.csv")
except Exception as e:
    print(f"⚠️ 讀取 restaurants.csv 失敗: {e}") 

# --- 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: pass

# --- RAG ---
retriever = None
if not df.empty and 'RAG_Content' in df.columns:
    try:
        loader = DataFrameLoader(df, page_content_column="RAG_Content")
        documents = loader.load()
        text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
        docs = text_splitter.split_documents(documents)
        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: pass

# ==========================================
# 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
    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"],
        "3 (普通)": ["平靜/放鬆", "隨意/探索"],
        "4 (不錯)": ["開心/慶祝", "平靜/放鬆"],
        "5 (超棒)": ["開心/慶祝"]
    }
    target_moods = score_map.get(mood_score_str, [])
    food_keyword = ""
    if food_choice == "吃飯": food_keyword = "飯"
    elif food_choice == "吃麵": food_keyword = "麵"

    candidates = df.copy()
    if target_moods:
        pattern = "|".join(target_moods)
        if 'Mood_Tags' in candidates.columns:
            candidates = candidates[candidates['Mood_Tags'].str.contains(pattern, regex=True, na=False)]
    
    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: return df.sample(1).iloc[0], True
    return candidates.sample(1).iloc[0], False

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"
    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"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", 
            messages=[{"role": "system", "content": system_prompt}, {"role": "user", "content": user_msg}]
        )
        return response.choices[0].message.content
    except Exception as e:
        return f"Groq Error: {str(e)}"

def generate_image_huggingface(prompt):
    if not HF_TOKEN: return None
    try:
        hf_client = InferenceClient(token=HF_TOKEN)
        return hf_client.text_to_image(prompt=prompt, model="stabilityai/stable-diffusion-xl-base-1.0")
    except: return None

def mood_agent_logic(score_input, food_input, diary_input, debug_mode):
    if not score_input:
        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", 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)}'))
    rag_info = str(restaurant.get('RAG_Content', ''))
    if retriever:
        try:
            docs = retriever.invoke(name)
            if docs: rag_info = "\n".join([d.page_content for d in docs])
        except: pass

    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)
    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
    image_output = generate_image_huggingface(img_prompt)
    yield final_response, image_output, map_html

# ==========================================
# 2. 情緒辨識整合模組
# ==========================================

emotion_text_obj = {'angry': '生氣', 'disgust': '噁心', 'fear': '害怕', 'happy': '開心', 'sad': '難過', 'surprise': '驚訝', 'neutral': '正常'}

def putText(img, x, y, text, size=50, color=(255, 255, 255)):
    try:
        fontpath = 'NotoSansTC-VariableFont_wght.ttf'
        if not os.path.exists(fontpath): return img
        font = ImageFont.truetype(fontpath, size)
        imgPil = Image.fromarray(img)
        draw = ImageDraw.Draw(imgPil)
        displayText = emotion_text_obj.get(text, text)
        draw.text((x, y), displayText, fill=color, font=font)
        return np.array(imgPil)
    except: return img

# 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:
        analyze = DeepFace.analyze(frame, actions=['emotion'], enforce_detection=False)
        if isinstance(analyze, list): analyze = analyze[0]
        detected_emotion = analyze['dominant_emotion']
        
        frame = putText(frame, 20, 40, detected_emotion)

        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

# 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
    
    # 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

# ==========================================
# 3. Gradio 介面建構
# ==========================================

with gr.Blocks(title="AI 心情食堂") as demo:
    
    # 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")
        gr.Markdown("請看著鏡頭，讓 AI 幫你判斷今天的心情分數！")

        with gr.Row():
            # 左側：輸入區
            with gr.Column(scale=1):
                gr.Markdown("### 📸 步驟 1：心情偵測")
                
                with gr.Row():
                    # 左邊：即時鏡頭
                    webcam_input = gr.Image(sources=["webcam"], label="即時鏡頭", streaming=True)
                    # 右邊：偵測結果
                    captured_image = gr.Image(label="偵測結果", interactive=False)
                
                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(
                    ["1 (心情差)", "2 (不太好)", "3 (普通)", "4 (不錯)", "5 (超棒)"], 
                    label="1. 心情分數 (AI 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=3, label="3. 心情日記", placeholder="選填...")
                
                debug_mode_btn = gr.Checkbox(label="🔧 除錯資訊", value=False)
                submit_btn = gr.Button("🚀 送出給 Agent", variant="primary")

            # 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")

    # --- 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]
    )

    # 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=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]
    )

    # 4. 送出 Agent
    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()