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-CN/chat.json

@@ -71,13 +71,13 @@
   "response_embedding_model_tokens": "向量模型 Tokens",
   "response_hybrid_weight": "语义检索 : 全文检索 = {{emb}} : {{text}}",
   "response_rerank_tokens": "重排模型 Tokens",
+  "search_results": "搜索结果",
   "select": "选择",
   "select_file": "上传文件",
   "select_file_img": "上传文件/图片",
   "select_img": "上传图片",
   "source_cronJob": "定时执行",
   "stream_output": "流输出",
-  "to_dataset": "前往知识库",
   "unsupported_file_type": "不支持的文件类型",
   "upload": "上传",
   "variable_invisable_in_share": "自定义变量在免登录链接中不可见",

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

@@ -403,7 +403,6 @@
   "core.chat.response.module model": "模型",
   "core.chat.response.module name": "模型名",
   "core.chat.response.module query": "问题/检索词",
-  "core.chat.response.module quoteList": "引用内容",
   "core.chat.response.module similarity": "相似度",
   "core.chat.response.module temperature": "温度",
   "core.chat.response.module time": "运行时长",
@@ -434,7 +433,6 @@
   "core.dataset.Text collection": "文本数据集",
   "core.dataset.apiFile": "API 文件",
   "core.dataset.collection.Click top config website": "点击配置网站",
-  "core.dataset.collection.Collection name": "数据集名称",
   "core.dataset.collection.Collection raw text": "数据集内容",
   "core.dataset.collection.Empty Tip": "数据集空空如也",
   "core.dataset.collection.QA Prompt": "QA 拆分引导词",
@@ -451,7 +449,6 @@
   "core.dataset.collection.metadata.metadata": "元数据",
   "core.dataset.collection.metadata.read source": "查看原始内容",
   "core.dataset.collection.metadata.source": "数据来源",
-  "core.dataset.collection.metadata.source name": "来源名",
   "core.dataset.collection.metadata.source size": "来源大小",
   "core.dataset.collection.status.active": "已就绪",
   "core.dataset.collection.status.error": "训练异常",
@@ -743,7 +740,7 @@
   "core.workflow.value": "值",
   "core.workflow.variable": "变量",
   "create": "去创建",
-  "create_failed": "创建异常",
+  "create_failed": "创建失败",
   "create_success": "创建成功",
   "create_time": "创建时间",
   "cron_job_run_app": "定时任务",
@@ -788,7 +785,6 @@
   "dataset.dataset_name": "知识库名称",
   "dataset.deleteFolderTips": "确认删除该文件夹及其包含的所有知识库？删除后数据无法恢复，请确认！",
   "dataset.test.noResult": "搜索结果为空",
-  "dataset_data_import_q_placeholder": "最多 {{maxToken}} 字。",
   "dataset_data_input_a": "答案",
   "dataset_data_input_chunk": "常规模式",
   "dataset_data_input_chunk_content": "内容",
@@ -802,7 +798,6 @@
   "delete_success": "删除成功",
   "delete_warning": "删除警告",
   "embedding_model_not_config": "检测到没有可用的索引模型",
-  "error.Create failed": "创建失败",
   "error.code_error": "验证码错误",
   "error.fileNotFound": "文件找不到了~",
   "error.inheritPermissionError": "权限继承错误",
@@ -1208,6 +1203,7 @@
   "templateTags.Writing": "文本创作",
   "template_market": "模板市场",
   "textarea_variable_picker_tip": "输入\"/\"可选择变量",
+  "to_dataset": "前往知识库",
   "ui.textarea.Magnifying": "放大",
   "un_used": "未使用",
   "unauth_token": "凭证已过期，请重新登录",

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

@@ -28,16 +28,21 @@
   "collection.training_type": "处理模式",
   "collection_data_count": "数据量",
   "collection_metadata_custom_pdf_parse": "PDF增强解析",
+  "collection_name": "数据集名称",
   "collection_not_support_retraining": "该集合类型不支持重新调整参数",
   "collection_not_support_sync": "该集合不支持同步",
   "collection_sync": "立即同步",
   "collection_sync_confirm_tip": "确认开始同步数据？系统将会拉取最新数据进行比较，如果内容不相同，则会创建一个新的集合并删除旧的集合，请确认！",
   "collection_tags": "集合标签",
+  "common.dataset.data.Input Error Tip": "[图片数据集] 处理过程错误:",
+  "common.error.unKnow": "未知错误",
   "common_dataset": "通用知识库",
   "common_dataset_desc": "通过导入文件、网页链接或手动录入形式构建知识库",
   "condition": "条件",
   "config_sync_schedule": "配置定时同步",
+  "confirm_import_images": "共 {{num}} 张图片 | 确认创建",
   "confirm_to_rebuild_embedding_tip": "确认为知识库切换索引？\n切换索引是一个非常重量的操作，需要对您知识库内所有数据进行重新索引，时间可能较长，请确保账号内剩余积分充足。\n\n此外，你还需要注意修改选择该知识库的应用，避免它们与其他索引模型知识库混用。",
+  "core.dataset.Image collection": "图片数据集",
   "core.dataset.import.Adjust parameters": "调整参数",
   "custom_data_process_params": "自定义",
   "custom_data_process_params_desc": "自定义设置数据处理规则",
@@ -90,6 +95,7 @@
   "image_auto_parse": "图片自动索引",
   "image_auto_parse_tips": "调用 VLM 自动标注文档里的图片，并生成额外的检索索引",
   "image_training_queue": "图片处理排队",
+  "images_creating": "正在创建",
   "immediate_sync": "立即同步",
   "import.Auto mode Estimated Price Tips": "需调用文本理解模型，需要消耗较多AI 积分：{{price}} 积分/1K tokens",
   "import.Embedding Estimated Price Tips": "仅使用索引模型，消耗少量 AI 积分：{{price}} 积分/1K tokens",
@@ -104,6 +110,8 @@
   "index_size": "索引大小",
   "index_size_tips": "向量化时内容的长度，系统会自动按该大小对分块进行进一步的分割。",
   "input_required_field_to_select_baseurl": "请先输入必填信息",
+  "insert_images": "新增图片",
+  "insert_images_success": "新增图片成功，需等待训练完成才会展示",
   "is_open_schedule": "启用定时同步",
   "keep_image": "保留图片",
   "loading": "加载中...",
@@ -135,6 +143,7 @@
   "process.Image_Index": "图片索引生成",
   "process.Is_Ready": "已就绪",
   "process.Is_Ready_Count": "{{count}} 组已就绪",
+  "process.Parse_Image": "图片解析中",
   "process.Parsing": "内容解析中",
   "process.Vectorizing": "索引向量化",
   "process.Waiting": "排队中",
@@ -176,11 +185,14 @@
   "the_knowledge_base_has_indexes_that_are_being_trained_or_being_rebuilt": "知识库有训练中或正在重建的索引",
   "total_num_files": "共 {{total}} 个文件",
   "training.Error": "{{count}} 组异常",
+  "training.Image mode": "图片处理",
   "training.Normal": "正常",
   "training_mode": "处理方式",
   "training_ready": "{{count}} 组",
+  "uploading_progress": "上传中: {{num}}%",
   "vector_model_max_tokens_tip": "每个分块数据，最大长度为 3000 tokens",
   "vllm_model": "图片理解模型",
+  "vlm_model_required_warning": "需要图片理解模型",
   "website_dataset": "Web 站点同步",
   "website_dataset_desc": "通过爬虫，批量爬取网页数据构建知识库",
   "website_info": "网站信息",

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

@@ -1,9 +1,33 @@
 {
+  "Action": "请选择要上传的图片",
+  "All images import failed": "所有图片导入失败",
+  "Dataset_ID_not_found": "数据集ID不存在",
+  "Failed_to_get_token": "获取令牌失败",
+  "Image_ID_copied": "已复制ID",
+  "Image_Preview": "图片预览",
+  "Image_dataset_requires_VLM_model_to_be_configured": "图片数据集需要配置图片理解模型(VLM)才能使用，请先在模型配置中添加支持图片理解的模型",
+  "Image_does_not_belong_to_current_team": "图片不属于当前团队",
+  "Image_file_does_not_exist": "图片不存在",
+  "Loading_image": "加载图片中...",
+  "Loading_image failed": "预览加载失败",
+  "Only_support_uploading_one_image": "仅支持上传一张图片",
+  "image_description_tip": "请输入图片的描述内容",
+  "Please select the image to upload": "请选择要上传的图片",
+  "Please wait for all files to upload": "请等待所有文件上传完成",
   "bucket_chat": "对话文件",
   "bucket_file": "知识库文件",
   "click_to_view_raw_source": "点击查看来源",
+  "common.Some images failed to process": "部分图片处理失败",
+  "common.dataset_data_input_image_support_format": "支持 .jpg, .jpeg, .png, .gif, .webp 格式",
+  "count.core.dataset.collection.Create Success": "成功导入 {{count}} 张图片",
+  "delete_image": "删除图片",
   "file_name": "文件名",
   "file_size": "文件大小",
+  "image": "图片",
+  "image_collection": "图片集合",
+  "image_description": "图片描述",
+  "please_upload_image_first": "请先上传图片",
+  "reached_max_file_count": "已达到最大文件数量",
   "release_the_mouse_to_upload_the_file": "松开鼠标上传文件",
   "select_and_drag_file_tip": "点击或拖动文件到此处上传",
   "select_file_amount_limit": "最多选择 {{max}} 个文件",
@@ -12,7 +36,9 @@
   "support_file_type": "支持 {{fileType}} 类型文件",
   "support_max_count": "最多支持 {{maxCount}} 个文件",
   "support_max_size": "单个文件最大 {{maxSize}}",
+  "total_files": "共{{selectFiles.length}}个文件",
+  "upload_error_description": "单次只支持上传多个文件或者一个文件夹",
   "upload_failed": "上传异常",
-  "reached_max_file_count": "已达到最大文件数量",
-  "upload_error_description": "单次只支持上传多个文件或者一个文件夹"
-}
+  "upload_file_error": "请上传图片",
+  "uploading": "正在上传..."
+}