新增職業預測

gemini_ai.py

@@ -11,7 +11,7 @@ import target_object
 #
 #
 # 設定圖檔位置 (此處僅為範例，純文字查詢時可忽略)
-image_path = r'G:\Python\tools\input_images\1411135045-張華桀.jpg'
+image_path = r'G:\Python\tools\input_images\拾穗.jpeg'
 
 
 # 要使用的模型種類，免費版一分鐘只能跑最多十筆

gemini_ai_work.py

@@ -0,0 +1,109 @@
+#!pip install -q -U google-generativeai
+import google.generativeai as genai
+import PIL.Image
+import image_converter as img_converter
+import random
+import os
+import ast
+import target_object
+
+#基本設定都放這邊----------------------------------------
+#
+#
+# 設定圖檔位置 (此處僅為範例，純文字查詢時可忽略)
+image_path = r'G:\Python\tools\input_images\拾穗.jpeg'
+
+
+# 要使用的模型種類，免費版一分鐘只能跑最多十筆
+gemini_model = 'gemini-2.5-flash'
+
+
+#--------------------------------------------------------
+## 替換冒號和逗號為換行符號
+def replace_colon_comma_with_newline(input_string):
+  processed_string = input_string.replace(':', '\n').replace('：', '\n').replace('],', ']\n')
+  return processed_string
+
+
+
+def getApiToken():
+    try:
+        my_api_key = os.getenv('my_api_key')
+        my_list = ast.literal_eval(my_api_key) # Convert string to list因為存在環境變數中是字串格式
+
+        return  random.choice(my_list)
+    except Exception as e:
+        return ""
+ 
+    
+# function，輸入是文字或是圖檔的位置
+def analyze_content_with_gemini_work(input_content):
+    """
+    透過 Gemini API 辨識內容，可處理純文字或圖片。
+
+    Args:
+        input_content (str or PIL.Image.Image):
+            如果輸入是字串，則代表要辨識的文字訊息或圖片路徑。
+            如果輸入是 PIL.Image.Image 物件，則直接使用該圖片。
+        user_prompt (str, optional):
+            使用者提供的自訂 prompt。如果為 None，則使用預設的 prompt。
+            Defaults to None.
+
+    Returns:
+        str: 辨識結果的文字描述。
+    """
+    my_api_key = getApiToken()  # 從環境變數中獲取API金鑰
+    genai.configure(api_key=my_api_key)
+    
+    # 根據 user_prompt 決定要使用的 prompt
+    prompt_to_use = str(target_object.work_JSON)
+    
+    # print("-"*50)
+    # print(prompt_to_use)
+    
+    try:
+        # 判斷輸入的類型
+        if isinstance(input_content, str):
+            # 如果輸入是字串，嘗試判斷是否為圖片路徑
+            if input_content.lower().endswith(('.png', '.jpg', '.jpeg', '.gif','.webp')):
+                if input_content.lower().endswith(('.webp')):
+                    input_content = img_converter.convert_webp_to_jpg(input_content)  # 如果是 webp 圖片，先轉換為 jpg
+                
+                model = genai.GenerativeModel(gemini_model)
+                image_obj = PIL.Image.open(input_content)
+                response = model.generate_content([prompt_to_use, image_obj])
+            else:
+                # 純文字輸入
+                model = genai.GenerativeModel(gemini_model)
+                response = model.generate_content(input_content) # 純文字直接使用輸入內容當 prompt
+        elif isinstance(input_content, PIL.Image.Image):
+            model = genai.GenerativeModel(gemini_model)
+            response = model.generate_content([prompt_to_use, input_content])
+        else:
+            return "錯誤：輸入必須是文字、圖片路徑（字串）或 PIL.Image 物件。"
+
+        return replace_colon_comma_with_newline(response.text)
+
+    except Exception as e:
+        return f"發生錯誤：{e}"
+
+
+if __name__ == '__main__':
+    # --- 程式碼使用範例 ---
+
+    # 範例 1：傳送純文字訊息
+    # print("正在處理純文字訊息...")
+    # text_message = "你好，請簡要說明一下Python是什麼？"
+    # response_text = analyze_content_with_gemini(text_message)
+    # print("回應結果：")
+    # print(response_text)
+    # print("-" * 20)
+
+    # 範例 2：傳送圖片路徑
+    # 請確保 image_path 指向有效的圖片檔案
+    print("正在處理圖片訊息...")
+    
+    response_image = analyze_content_with_gemini_work(image_path)
+    print("回應結果：")
+    print(response_image)
+    print("-" * 20)

main.py

@@ -1,298 +1,339 @@
-# -*- coding: utf-8 -*-
-"""
-系統需求:
-- gradio: 用於建立 Web UI
-- opencv-python: 用於圖片處理
-- ultralytics: YOLOv8 官方函式庫
-- Pillow: 圖片處理基礎庫
-- transformers: (可選，若YOLO模型需要)
-"""
-
-import gradio as gr
-import os
-import cv2
-from ultralytics import YOLO
-import shutil
-import zipfile
-import uuid  # 匯入 uuid 以生成唯一的執行 ID
-from pathlib import Path # 匯入 Path 以更方便地操作路徑
-import gemini_ai as genai
-from datetime import datetime
-import mongo_lib as mongo
-
-
-
-
-def create_zip_archive(files, zip_filename):
-    """
-    將一系列檔案壓縮成一個 zip 檔案。
-
-    Args:
-        files (list): 要壓縮的檔案路徑列表。
-        zip_filename (str): 產生的 zip 檔案路徑。
-
-    Returns:
-        str: 產生的 zip 檔案路徑。
-    """
-    with zipfile.ZipFile(zip_filename, 'w', zipfile.ZIP_DEFLATED) as zipf:
-        for file in files:
-            if os.path.exists(file):
-                # 使用 os.path.basename 確保只寫入檔案名稱，而非完整路徑
-                zipf.write(file, os.path.basename(file))
-            else:
-                print(f"警告: 檔案 '{file}' 不存在，無法加入壓縮檔。")
-    return zip_filename
-
-def gradio_multi_model_detection(
-    image_files,
-    model_files,
-    conf_threshold,
-    enable_mllm,
-    mllm_prompt,
-    progress=gr.Progress(track_tqdm=True)
-):
-    """
-    Gradio 的主要處理函式，使用生成器 (yield) 實現流式輸出。
-
-    Args:
-        image_files (list): Gradio File 元件回傳的圖片檔案列表。
-        model_files (list): Gradio File 元件回傳的模型檔案列表。
-        conf_threshold (float): 置信度閾值。
-        enable_mllm (bool): 是否啟用 MLLM 分析。
-        mllm_prompt (str): 使用者自訂的 MLLM prompt。
-        progress (gr.Progress): Gradio 的進度條元件。
-
-    Yields:
-        dict: 用於更新 Gradio 介面元件的字典。
-    """
-    global_datetime = datetime.now()
-    
-    #寫主表log
-    document = {"log_style":"master",
-                "create_datetime": str(global_datetime), 
-                "image_files": image_files, 
-                "model_files": model_files,
-                "conf_threshold":conf_threshold,
-                "enable_mllm":enable_mllm,
-                "mllm_prompt":mllm_prompt
-                }
-        
-    mongo.insert_mongodb_log("multi_model_detection",document)  #寫入log方便日後查驗            
-    
-    if not image_files:
-        yield {
-            output_status: gr.update(value="錯誤：請至少上傳一張圖片。"),
-            output_gallery: None,
-            output_text: None,
-            download_button: None
-        }
-        return
-
-    # --- 1. 初始化設定 ---
-    # 為本次執行創建一個唯一的子目錄
-    run_id = str(uuid.uuid4())
-    base_output_dir = Path('gradio_detection_results')
-    run_output_dir = base_output_dir / f"run_{run_id[:8]}"
-    run_output_dir.mkdir(parents=True, exist_ok=True)
-
-    image_paths = [file.name for file in image_files]
-    model_paths = [file.name for file in model_files] if model_files else []
-
-    # --- 2. 載入模型 ---
-    yield {output_status: gr.update(value="正在載入模型...")}
-    loaded_models = []
-    if not model_paths:
-        # 如果沒有上傳模型，使用預設模型
-        default_model_path = 'yolov8n.pt'
-        try:
-            model = YOLO(default_model_path)
-            loaded_models.append((default_model_path, model))
-        except Exception as e:
-            yield {output_status: gr.update(value=f"錯誤: 無法載入預設模型 '{default_model_path}' - {e}")}
-            return
-    else:
-        for model_path in model_paths:
-            try:
-                model = YOLO(model_path)
-                loaded_models.append((model_path, model))
-            except Exception as e:
-                print(f"警告: 無法載入模型 '{model_path}' - {e}，將跳過此模型。")
-                continue
-
-    if not loaded_models:
-        yield {output_status: gr.update(value="錯誤: 沒有任何模型成功載入。")}
-        return
-
-    # --- 3. 逐一處理圖片 ---
-    total_images = len(image_paths)
-    annotated_image_paths = []
-    all_result_files = []
-    # results_map 儲存圖片路徑與其對應的文字檔路徑，用於後續點擊查詢
-    results_map = {}
-    # all_texts 用於收集所有圖片的辨識結果文字
-    all_texts = []
-
-    for i, image_path_str in enumerate(image_paths):
-        image_path = Path(image_path_str)
-        progress(i / total_images, desc=f"處理中: {image_path.name}")
-        yield {
-            output_status: gr.update(value=f"處理中... ({i+1}/{total_images}) - {image_path.name}"),
-            output_gallery: gr.update(value=annotated_image_paths)
-        }
-
-        original_image = cv2.imread(str(image_path))
-        if original_image is None:
-            print(f"警告: 無法讀取圖片 '{image_path}'，跳過。")
-            continue
-        
-        annotated_image = original_image.copy()
-        image_base_name = image_path.stem
-
-        # --- 3a. YOLO 物件偵測 ---
-        yolo_output_content = [f"--- 檔案: {image_path.name} ---"]
-        all_detections_for_image = []
-        
-        for model_path_str, model_obj in loaded_models:
-            model_name = Path(model_path_str).name
-            yolo_output_content.append(f"--- 模型: {model_name} ---")
-            results = model_obj(str(image_path), verbose=False, device="cpu")[0]
-
-            if results.boxes:
-                for box in results.boxes:
-                    conf = float(box.conf[0])
-                    if conf >= conf_threshold:
-                        x1, y1, x2, y2 = map(int, box.xyxy[0])
-                        cls_id = int(box.cls[0])
-                        cls_name = model_obj.names[cls_id]
-                        
-                        detection_info = {'model_name': model_name, 'class_name': cls_name, 'confidence': conf, 'bbox': (x1, y1, x2, y2)}
-                        all_detections_for_image.append(detection_info)
-                        yolo_output_content.append(f"  - {cls_name} (信賴度: {conf:.2f}) [座標: {x1},{y1},{x2},{y2}]")
-            else:
-                yolo_output_content.append("  未偵測到任何物件。")
-
-        # 繪製偵測框
-        colors = [(255, 0, 0), (0, 255, 0), (0, 0, 255), (255, 255, 0), (255, 0, 255), (0, 255, 255)]
-        color_map = {Path(p).name: colors[idx % len(colors)] for idx, (p, _) in enumerate(loaded_models)}
-        for det in all_detections_for_image:
-            x1, y1, x2, y2 = det['bbox']
-            color = color_map.get(det['model_name'], (200, 200, 200))
-            label = f"{det['class_name']} {det['confidence']:.2f}"
-            cv2.rectangle(annotated_image, (x1, y1), (x2, y2), color, 2)
-            cv2.putText(annotated_image, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)
-
-        # 儲存 YOLO 標註圖
-        output_image_path = run_output_dir / f"{image_base_name}_yolo_detected.jpg"
-        cv2.imwrite(str(output_image_path), annotated_image)
-        annotated_image_paths.append(str(output_image_path))
-        all_result_files.append(str(output_image_path))
-
-        # 儲存 YOLO 辨識資訊
-        output_yolo_txt_path = run_output_dir / f"{image_base_name}_yolo_objects.txt"
-        output_yolo_txt_path.write_text("\n".join(yolo_output_content), encoding='utf-8')
-        all_result_files.append(str(output_yolo_txt_path))
-
-        # --- 3b. MLLM 分析 (如果啟用) ---
-        output_mllm_txt_path = None
-        mllm_result_content = ""
-        if enable_mllm:
-            try:
-                prompt_to_use = mllm_prompt if mllm_prompt and mllm_prompt.strip() else None
-                mllm_str = genai.analyze_content_with_gemini(str(image_path), prompt_to_use)
-                mllm_result_content = f"--- MLLM 分析結果 ---\n{mllm_str}"
-            except Exception as e:
-                mllm_result_content = f"--- MLLM 分析失敗 ---\n原因: {e}"
-            
-            output_mllm_txt_path = run_output_dir / f"{image_base_name}_mllm_result.txt"
-            output_mllm_txt_path.write_text(mllm_result_content, encoding='utf-8')
-            all_result_files.append(str(output_mllm_txt_path))
-        
-        #寫明細表log
-        document = {"log_style":"detail",
-                    "create_datetime": str(global_datetime), 
-                    "image_path": str(image_path), 
-                    "yolo_result": yolo_output_content, 
-                    "enable_mllm": enable_mllm,
-                    "mllm_prompt": mllm_prompt,                    
-                    "mllm_result": mllm_result_content}
-        
-        mongo.insert_mongodb_log("multi_model_detection",document)  #寫入log方便日後查驗
-
-        # 將本次圖片的結果加入到總列表中
-        all_texts.append("\n".join(yolo_output_content))
-        if output_mllm_txt_path:
-            all_texts.append(output_mllm_txt_path.read_text(encoding='utf-8'))
-
-
-    # --- 4. 完成處理，打包並更新最終結果 ---
-    progress(1, desc="打包結果中...")
-    zip_filename = run_output_dir / f"run_{run_id[:8]}_results.zip"
-    created_zip_path = create_zip_archive(all_result_files, str(zip_filename))
-
-    final_status = f"處理完成！共 {total_images} 張圖片。結果儲存於: {run_output_dir.absolute()}"
-    combined_text_output = "\n\n".join(all_texts)
-    
-    
-
-
-    yield {
-        output_status: gr.update(value=final_status),
-        download_button: gr.update(value=created_zip_path, visible=True),
-        output_text: gr.update(value=combined_text_output),
-        output_gallery: gr.update(value=annotated_image_paths) # 確保最終 gallery 也被更新
-    }
-
-def toggle_mllm_prompt(is_enabled):
-    """
-    根據 Checkbox 狀態，顯示或隱藏 MLLM prompt 輸入框。
-    """
-    return gr.update(visible=is_enabled)
-
-# --- Gradio Interface ---
-with gr.Blocks(theme=gr.themes.Soft()) as demo:
-    gr.Markdown("# 智慧影像分析工具 (YOLO + MLLM)")
-    gr.Markdown("上傳圖片與YOLO模型進行物件偵測，並可選用MLLM進行進階圖像理解。   ver.250830.1")
-    mongo_uri = os.getenv('mongo_uri')
-    #gr.Markdown(mongo_uri)
-
-    with gr.Row():
-        with gr.Column(scale=1):
-            # 輸入元件
-            image_input = gr.File(label="上傳圖片", file_count="multiple", file_types=["image"])
-            #model_input = gr.File(label="上傳YOLO模型 (.pt)", file_count="multiple", file_types=[".pt"], info="若不提供，將使用預設的 yolov8n.pt 模型。")
-            model_input = gr.File(label="上傳YOLO模型 (.pt)", file_count="multiple", file_types=[".pt"])
-            
-            with gr.Accordion("進階設定", open=False):
-                conf_slider = gr.Slider(minimum=0.1, maximum=1, value=0.40, step=0.05, label="信賴度閾值")
-                mllm_enabled_checkbox = gr.Checkbox(label="開啟MLLM辨識", value=False)
-                mllm_prompt_input = gr.Textbox(label="自訂 MLLM Prompt (選填)", placeholder="例如：請描述圖中人物的穿著與場景。", visible=False)
-
-            run_button = gr.Button("開始辨識", variant="primary")
-
-        with gr.Column(scale=2):
-            # 輸出元件
-            output_gallery = gr.Gallery(label="辨識結果預覽", height=500, object_fit="contain", allow_preview=True)
-            output_text = gr.Textbox(label="詳細辨識資訊", lines=15, placeholder="辨識完成後，所有結果將顯示於此。")
-            output_status = gr.Textbox(label="執行狀態", interactive=False)
-            download_button = gr.File(label="下載所有結果 (.zip)", file_count="single", visible=False)
-
-    # --- 事件綁定 ---
-    
-    # 點擊 "開始辨識" 按鈕
-    run_button.click(
-        fn=gradio_multi_model_detection,
-        inputs=[image_input, model_input, conf_slider, mllm_enabled_checkbox, mllm_prompt_input],
-        outputs=[output_gallery, output_status, download_button, output_text]
-    )
-
-    # 勾選/取消 "開啟MLLM辨識"
-    mllm_enabled_checkbox.change(
-        fn=toggle_mllm_prompt,
-        inputs=mllm_enabled_checkbox,
-        outputs=mllm_prompt_input
-    )
-
-# 啟動 Gradio 應用
-if __name__ == "__main__":
-    demo.launch(debug=True)
-    #demo.launch(share=True)
+# -*- coding: utf-8 -*-
+"""
+系統需求:
+- gradio: 用於建立 Web UI
+- opencv-python: 用於圖片處理
+- ultralytics: YOLOv8 官方函式庫
+- Pillow: 圖片處理基礎庫
+- transformers: (可選，若YOLO模型需要)
+huggingface上面是用main.py當主畫面
+
+"""
+
+import gradio as gr
+import os
+import cv2
+from ultralytics import YOLO
+import shutil
+import zipfile
+import uuid  # 匯入 uuid 以生成唯一的執行 ID
+from pathlib import Path # 匯入 Path 以更方便地操作路徑
+import gemini_ai as genai
+import gemini_ai_work as genai_work
+from datetime import datetime
+import mongo_lib as mongo
+
+
+
+
+def create_zip_archive(files, zip_filename):
+    """
+    將一系列檔案壓縮成一個 zip 檔案。
+
+    Args:
+        files (list): 要壓縮的檔案路徑列表。
+        zip_filename (str): 產生的 zip 檔案路徑。
+
+    Returns:
+        str: 產生的 zip 檔案路徑。
+    """
+    with zipfile.ZipFile(zip_filename, 'w', zipfile.ZIP_DEFLATED) as zipf:
+        for file in files:
+            if os.path.exists(file):
+                # 使用 os.path.basename 確保只寫入檔案名稱，而非完整路徑
+                zipf.write(file, os.path.basename(file))
+            else:
+                print(f"警告: 檔案 '{file}' 不存在，無法加入壓縮檔。")
+    return zip_filename
+
+def gradio_multi_model_detection(
+    image_files,
+    model_files,
+    conf_threshold,
+    enable_mllm,
+    mllm_prompt,
+    enable_career_prediction, # 新增職業預測參數
+    progress=gr.Progress(track_tqdm=True)
+):
+    """
+    Gradio 的主要處理函式，使用生成器 (yield) 實現流式輸出。
+
+    Args:
+        image_files (list): Gradio File 元件回傳的圖片檔案列表。
+        model_files (list): Gradio File 元件回傳的模型檔案列表。
+        conf_threshold (float): 置信度閾值。
+        enable_mllm (bool): 是否啟用 MLLM 分析。
+        mllm_prompt (str): 使用者自訂的 MLLM prompt。
+        enable_career_prediction (bool): 是否啟用職業預測分析。
+        progress (gr.Progress): Gradio 的進度條元件。
+
+    Yields:
+        dict: 用於更新 Gradio 介面元件的字典。
+    """
+    global_datetime = datetime.now()
+    
+    #寫主表log
+    document = {"log_style":"master",
+                "create_datetime": str(global_datetime), 
+                "image_files": image_files, 
+                "model_files": model_files,
+                "conf_threshold":conf_threshold,
+                "enable_mllm":enable_mllm,
+                "mllm_prompt":mllm_prompt,
+                "enable_career_prediction":enable_career_prediction # 新增職業預測狀態到 log
+                }
+        
+    mongo.insert_mongodb_log("multi_model_detection",document)  #寫入log方便日後查驗            
+    
+    if not image_files:
+        yield {
+            output_status: gr.update(value="錯誤：請至少上傳一張圖片。"),
+            output_gallery: None,
+            output_text: None,
+            download_button: None
+        }
+        return
+
+    # --- 1. 初始化設定 ---
+    # 為本次執行創建一個唯一的子目錄
+    run_id = str(uuid.uuid4())
+    base_output_dir = Path('gradio_detection_results')
+    run_output_dir = base_output_dir / f"run_{run_id[:8]}"
+    run_output_dir.mkdir(parents=True, exist_ok=True)
+
+    image_paths = [file.name for file in image_files]
+    model_paths = [file.name for file in model_files] if model_files else []
+
+    # --- 2. 載入模型 ---
+    yield {output_status: gr.update(value="正在載入模型...")}
+    loaded_models = []
+    if not model_paths:
+        # 如果沒有上傳模型，使用預設模型
+        default_model_path = 'yolov8n.pt'
+        try:
+            model = YOLO(default_model_path)
+            loaded_models.append((default_model_path, model))
+        except Exception as e:
+            yield {output_status: gr.update(value=f"錯誤: 無法載入預設模型 '{default_model_path}' - {e}")}
+            return
+    else:
+        for model_path in model_paths:
+            try:
+                model = YOLO(model_path)
+                loaded_models.append((model_path, model))
+            except Exception as e:
+                print(f"警告: 無法載入模型 '{model_path}' - {e}，將跳過此模型。")
+                continue
+
+    if not loaded_models:
+        yield {output_status: gr.update(value="錯誤: 沒有任何模型成功載入。")}
+        return
+
+    # --- 3. 逐一處理圖片 ---
+    total_images = len(image_paths)
+    annotated_image_paths = []
+    all_result_files = []
+    # results_map 儲存圖片路徑與其對應的文字檔路徑，用於後續點擊查詢
+    results_map = {}
+    # all_texts 用於收集所有圖片的辨識結果文字
+    all_texts = []
+
+    for i, image_path_str in enumerate(image_paths):
+        image_path = Path(image_path_str)
+        progress(i / total_images, desc=f"處理中: {image_path.name}")
+        yield {
+            output_status: gr.update(value=f"處理中... ({i+1}/{total_images}) - {image_path.name}"),
+            output_gallery: gr.update(value=annotated_image_paths)
+        }
+
+        original_image = cv2.imread(str(image_path))
+        if original_image is None:
+            print(f"警告: 無法讀取圖片 '{image_path}'，跳過。")
+            continue
+        
+        annotated_image = original_image.copy()
+        image_base_name = image_path.stem
+
+        # --- 3a. YOLO 物件偵測 ---
+        yolo_output_content = [f"--- 檔案: {image_path.name} ---"]
+        all_detections_for_image = []
+        
+        for model_path_str, model_obj in loaded_models:
+            model_name = Path(model_path_str).name
+            yolo_output_content.append(f"--- 模型: {model_name} ---")
+            results = model_obj(str(image_path), verbose=False, device="cpu")[0]
+
+            if results.boxes:
+                for box in results.boxes:
+                    conf = float(box.conf[0])
+                    if conf >= conf_threshold:
+                        x1, y1, x2, y2 = map(int, box.xyxy[0])
+                        cls_id = int(box.cls[0])
+                        cls_name = model_obj.names[cls_id]
+                        
+                        detection_info = {'model_name': model_name, 'class_name': cls_name, 'confidence': conf, 'bbox': (x1, y1, x2, y2)}
+                        all_detections_for_image.append(detection_info)
+                        yolo_output_content.append(f"  - {cls_name} (信賴度: {conf:.2f}) [座標: {x1},{y1},{x2},{y2}]")
+            else:
+                yolo_output_content.append("  未偵測到任何物件。")
+
+        # 繪製偵測框
+        colors = [(255, 0, 0), (0, 255, 0), (0, 0, 255), (255, 255, 0), (255, 0, 255), (0, 255, 255)]
+        color_map = {Path(p).name: colors[idx % len(colors)] for idx, (p, _) in enumerate(loaded_models)}
+        for det in all_detections_for_image:
+            x1, y1, x2, y2 = det['bbox']
+            color = color_map.get(det['model_name'], (200, 200, 200))
+            label = f"{det['class_name']} {det['confidence']:.2f}"
+            cv2.rectangle(annotated_image, (x1, y1), (x2, y2), color, 2)
+            cv2.putText(annotated_image, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)
+
+        # 儲存 YOLO 標註圖
+        output_image_path = run_output_dir / f"{image_base_name}_yolo_detected.jpg"
+        cv2.imwrite(str(output_image_path), annotated_image)
+        annotated_image_paths.append(str(output_image_path))
+        all_result_files.append(str(output_image_path))
+
+        # 儲存 YOLO 辨識資訊
+        output_yolo_txt_path = run_output_dir / f"{image_base_name}_yolo_objects.txt"
+        output_yolo_txt_path.write_text("\n".join(yolo_output_content), encoding='utf-8')
+        all_result_files.append(str(output_yolo_txt_path))
+
+        # --- 3b. MLLM 分析 (如果啟用) ---
+        output_mllm_txt_path = None
+        mllm_result_content = ""
+        if enable_mllm:
+            try:
+                prompt_to_use = mllm_prompt if mllm_prompt and mllm_prompt.strip() else None
+                mllm_str = genai.analyze_content_with_gemini(str(image_path), prompt_to_use)
+                mllm_result_content = f"--- MLLM 分析結果 ---\n{mllm_str}"
+            except Exception as e:
+                mllm_result_content = f"--- MLLM 分析失敗 ---\n原因: {e}"
+            
+            output_mllm_txt_path = run_output_dir / f"{image_base_name}_mllm_result.txt"
+            output_mllm_txt_path.write_text(mllm_result_content, encoding='utf-8')
+            all_result_files.append(str(output_mllm_txt_path))
+
+        # --- 3c. 職業預測分析 (如果啟用) ---
+        output_career_prediction_txt_path = None
+        career_prediction_result_content = ""
+        if enable_career_prediction:
+            try:
+                # 呼叫 genai.analyze_content_with_gemini_work 進行職業預測
+                career_prediction_str = genai_work.analyze_content_with_gemini_work(str(image_path))
+                
+                career_prediction_result_content = f"--- 職業預測分析結果 ---\n{career_prediction_str}"
+            except Exception as e:
+                career_prediction_result_content = f"--- 職業預測分析失敗 ---\n原因: {e}"
+            
+            output_career_prediction_txt_path = run_output_dir / f"{image_base_name}_career_prediction.txt"
+            output_career_prediction_txt_path.write_text(career_prediction_result_content, encoding='utf-8')
+            all_result_files.append(str(output_career_prediction_txt_path))
+        
+        #寫明細表log
+        document = {"log_style":"detail",
+                    "create_datetime": str(global_datetime), 
+                    "image_path": str(image_path), 
+                    "yolo_result": yolo_output_content, 
+                    "enable_mllm": enable_mllm,
+                    "mllm_prompt": mllm_prompt,                    
+                    "mllm_result": mllm_result_content,
+                    "enable_career_prediction": enable_career_prediction, # 新增職業預測狀態到 log
+                    "career_prediction_result": career_prediction_result_content # 新增職業預測結果到 log
+                    }
+        
+        mongo.insert_mongodb_log("multi_model_detection",document)  #寫入log方便日後查驗
+
+        # 將本次圖片的結果加入到總列表中
+        all_texts.append("\n".join(yolo_output_content))
+        if output_mllm_txt_path:
+            all_texts.append(output_mllm_txt_path.read_text(encoding='utf-8'))
+        if output_career_prediction_txt_path: # 如果有職業預測結果，也加入到總列表中
+            all_texts.append(output_career_prediction_txt_path.read_text(encoding='utf-8'))
+
+
+    # --- 4. 完成處理，打包並更新最終結果 ---
+    progress(1, desc="打包結果中...")
+    zip_filename = run_output_dir / f"run_{run_id[:8]}_results.zip"
+    created_zip_path = create_zip_archive(all_result_files, str(zip_filename))
+
+    final_status = f"處理完成！共 {total_images} 張圖片。結果儲存於: {run_output_dir.absolute()}"
+    combined_text_output = "\n\n".join(all_texts)
+    
+    
+
+
+    yield {
+        output_status: gr.update(value=final_status),
+        download_button: gr.update(value=created_zip_path, visible=True),
+        output_text: gr.update(value=combined_text_output),
+        output_gallery: gr.update(value=annotated_image_paths) # 確保最終 gallery 也被更新
+    }
+
+def toggle_mllm_prompt(is_enabled):
+    """
+    根據 Checkbox 狀態，顯示或隱藏 MLLM prompt 輸入框。
+    """
+    return gr.update(visible=is_enabled)
+
+def toggle_career_prediction_checkbox(is_enabled):
+    """
+    根據 Checkbox 狀態，處理職業預測相關邏輯 (目前無需顯示額外輸入框)。
+    """
+    return None # 職業預測目前不需要額外的輸入框，所以直接返回 None
+
+# --- Gradio Interface ---
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("# ㊙️智慧影像與職業潛能分析 (YOLO + MLLM)")
+    gr.Markdown("上傳圖片與YOLO模型進行物件偵測，並可選用MLLM進行進階圖像理解。   ver.250830.1")
+    # mongo_uri = os.getenv('mongo_uri')
+    # gr.Markdown(mongo_uri)
+
+    with gr.Row():
+        with gr.Column(scale=1):
+            # 輸入元件
+            image_input = gr.File(label="上傳圖片", file_count="multiple", file_types=["image"])
+            #model_input = gr.File(label="上傳YOLO模型 (.pt)", file_count="multiple", file_types=[".pt"], info="若不提供，將使用預設的 yolov8n.pt 模型。")
+            model_input = gr.File(label="上傳YOLO模型 (.pt)", file_count="multiple", file_types=[".pt"])
+            
+            with gr.Accordion("進階設定(開啟越多功能速度越慢呦)", open=False):
+                conf_slider = gr.Slider(minimum=0.1, maximum=1, value=0.40, step=0.05, label="yolo信賴度閾值")
+                mllm_enabled_checkbox = gr.Checkbox(label="開啟MLLM辨識", value=False)
+                mllm_prompt_input = gr.Textbox(label="自訂 MLLM Prompt (選填)", placeholder="例如：請描述圖中人物的穿著與場景。", visible=False)
+                career_prediction_checkbox = gr.Checkbox(label="開啟職業預測", value=False) # 新增職業預測 checkbox
+
+            run_button = gr.Button("開始辨識", variant="primary")
+
+        with gr.Column(scale=2):
+            # 輸出元件
+            output_gallery = gr.Gallery(label="辨識結果預覽", height=500, object_fit="contain", allow_preview=True)
+            output_text = gr.Textbox(label="詳細辨識資訊", lines=15, placeholder="辨識完成後，所有結果將顯示於此。")
+            output_status = gr.Textbox(label="執行狀態", interactive=False)
+            download_button = gr.File(label="下載所有結果 (.zip)", file_count="single", visible=False)
+
+    # --- 事件綁定 ---
+    
+    # 點擊 "開始辨識" 按鈕
+    run_button.click(
+        fn=gradio_multi_model_detection,
+        inputs=[image_input, model_input, conf_slider, mllm_enabled_checkbox, mllm_prompt_input, career_prediction_checkbox], # 新增 career_prediction_checkbox
+        outputs=[output_gallery, output_status, download_button, output_text]
+    )
+
+    # 勾選/取消 "開啟MLLM辨識"
+    mllm_enabled_checkbox.change(
+        fn=toggle_mllm_prompt,
+        inputs=mllm_enabled_checkbox,
+        outputs=mllm_prompt_input
+    )
+
+    # 勾選/取消 "開啟職業預測"
+    career_prediction_checkbox.change(
+        fn=toggle_career_prediction_checkbox,
+        inputs=career_prediction_checkbox,
+        outputs=[] # 職業預測目前不需要更新任何輸出元件
+    )
+
+# 啟動 Gradio 應用
+if __name__ == "__main__":
+    demo.launch(debug=True)
+    #demo.launch(share=True)

target_object.py

@@ -56,4 +56,33 @@ target_JSON ={
 		"角色_動物",
 		"角色_工作人員"
 	]
-}
+}
+
+work_JSON ={
+  "role": "您是一位藝術職涯分析師，擅長從畫作作品中推薦適合的未來職業。您不僅分析作品的意象或外在形象，更深入剖析其技法、氛圍、光影、配色、構圖、透視和隱喻等特質，並將這些特質與MBTI人格類型相結合。",
+  "tone": "以第一人稱如朋友般的說話語氣，以積極正面的方向推薦職業，務必讓聽者有沉浸式的感覺。並且會遵守weighting設定的權重來評分，並照著output_format中的規範輸出格式。",
+  "occupations": [
+    "軟體工程師",    "'系統管理員",   "網路工程師",    "資料科學家",    "人工智慧工程師",  "雲端工程師",
+    "資安專家",     "UI/UX設計師", "遊戲開發工程師",  "硬體工程師",    "電子工程師",    "機械工程師",
+    "土木工程師",    "結構工程師",    "建築師",      "室內設計師",    "工業設計師",    "產品經理",
+    "專案經理",     "品管工程師",    "測試工程師",    "教師",       "醫師",       "牙醫師",
+    "藥師",       "護理師",      "放射師",      "醫檢師",      "物理治療師",    "職能治療師",
+    "心理師",      "營養師",      "獸醫師",      "律師",       "法官",       "檢察官",
+    "會計師",      "審計師",      "財務分析師",    "金融交易員",    "投資顧問",     "理財專員",
+    "銀行行員",     "保險業務員",    "不動產經紀人",   "採購專員",     "物流專員",     "倉儲管理員",
+    "運輸司機",     "航空駕駛員",    "空服員",      "船舶駕駛員",    "消防員",      "警察",
+    "軍人",       "保全人員",     "社工師",      "公務員",      "政治人物",     "記者",
+    "編輯",       "作家",       "翻譯員",      "攝影師",      "導演",       "演員",
+    "歌手",       "音樂製作人",    "舞者",       "畫家",       "設計師",      "插畫師",
+    "動畫師",      "攝影棚工作人員",  "廣告創意人員",   "行銷專員",     "數位行銷專員",   "公關專員",
+    "品牌經理",     "客戶經理",     "業務員",      "客服人員",     "餐飲廚師",     "餐飲服務員",
+    "飯店櫃檯人員",   "旅遊導遊",     "旅行社專員",    "美容師",      "美髮師",      "美甲師",
+    "健身教練",     "運動員",      "裁判",       "農夫",       "漁夫",       "牧場管理員",
+    "工廠技術員",    "焊接工",      "水電工",      "清潔人員",     "網紅",       "自創業"
+  ],
+  "weighting": {"外在意象": "5%", "藝術技法与特質": "45%", "MBTI特質關聯": "50%"},
+  "output_format": {
+    "推薦的工作 : ": "<工作A> %，<工作B> %，<工作C> %",
+    "推薦的原因 : ": "解釋作品特質如何對應到MBTI並適合推薦的職業"
+  }
+}