Feat: Images dataset collection (#4941)

* New pic (#4858)

* 更新数据集相关类型，添加图像文件ID和预览URL支持；优化数据集导入功能，新增图像数据集处理组件；修复部分国际化文本；更新文件上传逻辑以支持新功能。

* 与原先代码的差别

* 新增 V4.9.10 更新说明，支持 PG 设置`systemEnv.hnswMaxScanTuples`参数，优化 LLM stream 调用超时，修复全文检索多知识库排序问题。同时更新数据集索引，移除 datasetId 字段以简化查询。

* 更换成fileId_image逻辑，并增加训练队列匹配的逻辑

* 新增图片集合判断逻辑，优化预览URL生成流程，确保仅在数据集为图片集合时生成预览URL，并添加相关日志输出以便调试。

* Refactor Docker Compose configuration to comment out exposed ports for production environments, update image versions for pgvector, fastgpt, and mcp_server, and enhance Redis service with a health check. Additionally, standardize dataset collection labels in constants and improve internationalization strings across multiple languages.

* Enhance TrainingStates component by adding internationalization support for the imageParse training mode and update defaultCounts to include imageParse mode in trainingDetail API.

* Enhance dataset import context by adding additional steps for image dataset import process and improve internationalization strings for modal buttons in the useEditTitle hook.

* Update DatasetImportContext to conditionally render MyStep component based on data source type, improving the import process for non-image datasets.

* Refactor image dataset handling by improving internationalization strings, enhancing error messages, and streamlining the preview URL generation process.

* 图片上传到新建的 dataset_collection_images 表，逻辑跟随更改

* 修改了除了controller的其他部分问题

* 把图片数据集的逻辑整合到controller里面

* 补充i18n

* 补充i18n

* resolve评论：主要是上传逻辑的更改和组件复用

* 图片名称的图标显示

* 修改编译报错的命名问题

* 删除不需要的collectionid部分

* 多余文件的处理和改动一个删除按钮

* 除了loading和统一的imageId,其他都resolve掉的

* 处理图标报错

* 复用了MyPhotoView并采用全部替换的方式将imageFileId变成imageId

* 去除不必要文件修改

* 报错和字段修改

* 增加上传成功后删除临时文件的逻辑以及回退一些修改

* 删除path字段，将图片保存到gridfs内，并修改增删等操作的代码

* 修正编译错误

---------

Co-authored-by: archer <545436317@qq.com>

* perf: image dataset

* feat: insert image

* perf: image icon

* fix: training state

---------

Co-authored-by: Zhuangzai fa <143257420+ctrlz526@users.noreply.github.com>

packages/web/i18n/zh-Hant/chat.json

@@ -71,13 +71,13 @@
   "response_embedding_model_tokens": "向量模型 Tokens",
   "response_hybrid_weight": "語義檢索 : 全文檢索 = {{emb}} : {{text}}",
   "response_rerank_tokens": "重排模型 Tokens",
+  "search_results": "搜索結果",
   "select": "選取",
   "select_file": "上傳檔案",
   "select_file_img": "上傳檔案 / 圖片",
   "select_img": "上傳圖片",
   "source_cronJob": "定時執行",
   "stream_output": "串流輸出",
-  "to_dataset": "前往知識庫",
   "unsupported_file_type": "不支援的檔案類型",
   "upload": "上傳",
   "variable_invisable_in_share": "自定義變數在免登入連結中不可見",

packages/web/i18n/zh-Hant/common.json

@@ -403,7 +403,6 @@
   "core.chat.response.module model": "模型",
   "core.chat.response.module name": "模型名稱",
   "core.chat.response.module query": "問題/搜尋詞",
-  "core.chat.response.module quoteList": "引用內容",
   "core.chat.response.module similarity": "相似度",
   "core.chat.response.module temperature": "溫度",
   "core.chat.response.module time": "執行時長",
@@ -434,7 +433,6 @@
   "core.dataset.Text collection": "文字資料集",
   "core.dataset.apiFile": "API 檔案",
   "core.dataset.collection.Click top config website": "點選設定網站",
-  "core.dataset.collection.Collection name": "資料集名稱",
   "core.dataset.collection.Collection raw text": "資料集內容",
   "core.dataset.collection.Empty Tip": "資料集是空的",
   "core.dataset.collection.QA Prompt": "問答拆分提示詞",
@@ -451,7 +449,6 @@
   "core.dataset.collection.metadata.metadata": "中繼資料",
   "core.dataset.collection.metadata.read source": "檢視原始內容",
   "core.dataset.collection.metadata.source": "資料來源",
-  "core.dataset.collection.metadata.source name": "來源名稱",
   "core.dataset.collection.metadata.source size": "來源大小",
   "core.dataset.collection.status.active": "已就緒",
   "core.dataset.collection.status.error": "訓練異常",
@@ -555,7 +552,7 @@
   "core.dataset.training.Agent queue": "問答訓練排隊中",
   "core.dataset.training.Auto mode": "補充索引",
   "core.dataset.training.Auto mode Tip": "透過子索引以及呼叫模型產生相關問題與摘要，來增加資料區塊的語意豐富度，更有利於檢索。需要消耗更多的儲存空間並增加 AI 呼叫次數。",
-  "core.dataset.training.Chunk mode": "分塊存儲",
+  "core.dataset.training.Chunk mode": "分塊儲存",
   "core.dataset.training.Full": "預計 20 分鐘以上",
   "core.dataset.training.Leisure": "閒置",
   "core.dataset.training.QA mode": "問答對提取",
@@ -788,7 +785,6 @@
   "dataset.dataset_name": "知識庫名稱",
   "dataset.deleteFolderTips": "確認刪除此資料夾及其包含的所有知識庫？刪除後資料無法復原，請確認！",
   "dataset.test.noResult": "搜尋結果為空",
-  "dataset_data_import_q_placeholder": "最多 {{maxToken}} 字。",
   "dataset_data_input_a": "答案",
   "dataset_data_input_chunk": "常規模式",
   "dataset_data_input_chunk_content": "內容",
@@ -802,7 +798,6 @@
   "delete_success": "刪除成功",
   "delete_warning": "刪除警告",
   "embedding_model_not_config": "偵測到沒有可用的索引模型",
-  "error.Create failed": "建立失敗",
   "error.code_error": "驗證碼錯誤",
   "error.fileNotFound": "找不到檔案",
   "error.inheritPermissionError": "繼承權限錯誤",
@@ -1208,6 +1203,7 @@
   "templateTags.Writing": "文字創作",
   "template_market": "模板市場",
   "textarea_variable_picker_tip": "輸入「/」以選擇變數",
+  "to_dataset": "前往知識庫",
   "ui.textarea.Magnifying": "放大",
   "un_used": "未使用",
   "unauth_token": "憑證已過期，請重新登入",

packages/web/i18n/zh-Hant/dataset.json

@@ -26,16 +26,21 @@
   "collection.training_type": "處理模式",
   "collection_data_count": "資料量",
   "collection_metadata_custom_pdf_parse": "PDF 增強解析",
+  "collection_name": "數據集名稱",
   "collection_not_support_retraining": "此集合類型不支援重新調整參數",
   "collection_not_support_sync": "該集合不支援同步",
   "collection_sync": "立即同步",
   "collection_sync_confirm_tip": "確認開始同步資料？\n系統將會拉取最新資料進行比較，如果內容不相同，則會建立一個新的集合並刪除舊的集合，請確認！",
   "collection_tags": "集合標籤",
+  "common.dataset.data.Input Error Tip": "[圖片數據集] 處理過程錯誤:",
+  "common.error.unKnow": "未知錯誤",
   "common_dataset": "通用資料集",
   "common_dataset_desc": "通過導入文件、網頁鏈接或手動錄入形式構建知識庫",
   "condition": "條件",
   "config_sync_schedule": "設定定時同步",
+  "confirm_import_images": "共 {{num}} 張圖片 | 確認創建",
   "confirm_to_rebuild_embedding_tip": "確定要為資料集切換索引嗎？\n切換索引是一個重要的操作，需要對您資料集內所有資料重新建立索引，可能需要較長時間，請確保帳號內剩餘點數充足。\n\n此外，您還需要注意修改使用此資料集的應用程式，避免與其他索引模型資料集混用。",
+  "core.dataset.Image collection": "圖片數據集",
   "core.dataset.import.Adjust parameters": "調整參數",
   "custom_data_process_params": "自訂",
   "custom_data_process_params_desc": "自訂資料處理規則",
@@ -88,6 +93,7 @@
   "image_auto_parse": "圖片自動索引",
   "image_auto_parse_tips": "呼叫 VLM 自動標註文件裡的圖片，並生成額外的檢索索引",
   "image_training_queue": "圖片處理排隊",
+  "images_creating": "正在創建",
   "immediate_sync": "立即同步",
   "import.Auto mode Estimated Price Tips": "需呼叫文字理解模型，將消耗較多 AI 點數：{{price}} 點數 / 1K tokens",
   "import.Embedding Estimated Price Tips": "僅使用索引模型，消耗少量 AI 點數：{{price}} 點數 / 1K tokens",
@@ -102,6 +108,8 @@
   "index_size": "索引大小",
   "index_size_tips": "向量化時內容的長度，系統會自動按該大小對分塊進行進一步的分割。",
   "input_required_field_to_select_baseurl": "請先輸入必填信息",
+  "insert_images": "新增圖片",
+  "insert_images_success": "新增圖片成功，需等待訓練完成才會展示",
   "is_open_schedule": "啟用定時同步",
   "keep_image": "保留圖片",
   "loading": "加載中...",
@@ -133,6 +141,7 @@
   "process.Image_Index": "圖片索引生成",
   "process.Is_Ready": "已就緒",
   "process.Is_Ready_Count": "{{count}} 組已就緒",
+  "process.Parse_Image": "圖片解析中",
   "process.Parsing": "內容解析中",
   "process.Vectorizing": "索引向量化",
   "process.Waiting": "排隊中",
@@ -174,11 +183,13 @@
   "the_knowledge_base_has_indexes_that_are_being_trained_or_being_rebuilt": "資料集有索引正在訓練或重建中",
   "total_num_files": "共 {{total}} 個文件",
   "training.Error": "{{count}} 組異常",
+  "training.Image mode": "圖片處理",
   "training.Normal": "正常",
   "training_mode": "分段模式",
   "training_ready": "{{count}} 組",
   "vector_model_max_tokens_tip": "每個分塊資料，最大長度為 3000 tokens",
   "vllm_model": "圖片理解模型",
+  "vlm_model_required_warning": "需要圖片理解模型",
   "website_dataset": "網站同步",
   "website_dataset_desc": "通過爬蟲，批量爬取網頁數據構建知識庫",
   "website_info": "網站資訊",

packages/web/i18n/zh-Hant/file.json

@@ -1,9 +1,31 @@
 {
+  "Action": "請選擇要上傳的圖片",
+  "All images import failed": "所有圖片導入失敗",
+  "Dataset_ID_not_found": "數據集ID不存在",
+  "Failed_to_get_token": "獲取令牌失敗",
+  "Image_ID_copied": "已復制ID",
+  "Image_Preview": "圖片預覽",
+  "Image_dataset_requires_VLM_model_to_be_configured": "圖片數據集需要配置圖片理解模型(VLM)才能使用，請先在模型配置中添加支持圖片理解的模型",
+  "Image_does_not_belong_to_current_team": "圖片不屬於當前團隊",
+  "Image_file_does_not_exist": "圖片不存在",
+  "Loading_image": "加載圖片中...",
+  "Loading_image_failed": "預覽加載失敗",
+  "Only_support_uploading_one_image": "僅支持上傳一張圖片",
+  "image_description_tip": "請輸入圖片的描述內容",
+  "Please select the image to upload": "請選擇要上傳的圖片",
+  "Please select the image to upload select the image to upload": "",
+  "Please wait for all files to upload": "請等待所有文件上傳完成",
   "bucket_chat": "對話檔案",
   "bucket_file": "知識庫檔案",
   "click_to_view_raw_source": "點選檢視原始來源",
+  "dataset_data_input_image_support_format": "支持 .jpg, .jpeg, .png, .gif, .webp 格式",
+  "delete_image": "刪除圖片",
   "file_name": "檔案名稱",
   "file_size": "檔案大小",
+  "image": "圖片",
+  "image_collection": "圖片集合",
+  "please_upload_image_first": "請先上傳圖片",
+  "reached_max_file_count": "已達檔案數量上限",
   "release_the_mouse_to_upload_the_file": "放開滑鼠以上傳檔案",
   "select_and_drag_file_tip": "點選或拖曳檔案至此處上傳",
   "select_file_amount_limit": "最多可選擇 {{max}} 個檔案",
@@ -12,7 +34,9 @@
   "support_file_type": "支援 {{fileType}} 格式的檔案",
   "support_max_count": "最多可支援 {{maxCount}} 個檔案",
   "support_max_size": "單一檔案大小上限為 {{maxSize}}",
+  "total_files": "共{{selectFiles.length}}個文件",
+  "upload_error_description": "單次僅支援上傳多個檔案或一個資料夾",
   "upload_failed": "上傳失敗",
-  "reached_max_file_count": "已達檔案數量上限",
-  "upload_error_description": "單次僅支援上傳多個檔案或一個資料夾"
-}
+  "upload_file_error": "請上傳圖片",
+  "uploading": "正在上傳..."
+}