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>
2025-06-03 16:30:59 +08:00
parent 9fb5d05865
commit 92c38d9d2f
104 changed files with 2341 additions and 693 deletions
--- a/packages/web/components/common/Icon/constants.ts
+++ b/packages/web/components/common/Icon/constants.ts
@@ -220,9 +220,11 @@ export const iconPaths = {
    import('./icons/core/dataset/feishuDatasetOutline.svg'),
  'core/dataset/fileCollection': () => import('./icons/core/dataset/fileCollection.svg'),
  'core/dataset/fullTextRecall': () => import('./icons/core/dataset/fullTextRecall.svg'),
+  'core/dataset/imageFill': () => import('./icons/core/dataset/imageFill.svg'),
  'core/dataset/manualCollection': () => import('./icons/core/dataset/manualCollection.svg'),
  'core/dataset/mixedRecall': () => import('./icons/core/dataset/mixedRecall.svg'),
  'core/dataset/modeEmbedding': () => import('./icons/core/dataset/modeEmbedding.svg'),
+  'core/dataset/otherDataset': () => import('./icons/core/dataset/otherDataset.svg'),
  'core/dataset/questionExtension': () => import('./icons/core/dataset/questionExtension.svg'),
  'core/dataset/rerank': () => import('./icons/core/dataset/rerank.svg'),
  'core/dataset/searchfilter': () => import('./icons/core/dataset/searchfilter.svg'),
@@ -230,7 +232,6 @@ export const iconPaths = {
  'core/dataset/tableCollection': () => import('./icons/core/dataset/tableCollection.svg'),
  'core/dataset/tag': () => import('./icons/core/dataset/tag.svg'),
  'core/dataset/websiteDataset': () => import('./icons/core/dataset/websiteDataset.svg'),
-  'core/dataset/otherDataset': () => import('./icons/core/dataset/otherDataset.svg'),
  'core/dataset/websiteDatasetColor': () => import('./icons/core/dataset/websiteDatasetColor.svg'),
  'core/dataset/websiteDatasetOutline': () =>
    import('./icons/core/dataset/websiteDatasetOutline.svg'),
@@ -379,10 +380,12 @@ export const iconPaths = {
  fullScreen: () => import('./icons/fullScreen.svg'),
  help: () => import('./icons/help.svg'),
  history: () => import('./icons/history.svg'),
+  image: () => import('./icons/image.svg'),
  infoRounded: () => import('./icons/infoRounded.svg'),
  kbTest: () => import('./icons/kbTest.svg'),
  key: () => import('./icons/key.svg'),
  keyPrimary: () => import('./icons/keyPrimary.svg'),
+  loading: () => import('./icons/loading.svg'),
  menu: () => import('./icons/menu.svg'),
  minus: () => import('./icons/minus.svg'),
  'modal/AddClb': () => import('./icons/modal/AddClb.svg'),
--- a/packages/web/components/common/Icon/icons/core/dataset/imageFill.svg
+++ b/packages/web/components/common/Icon/icons/core/dataset/imageFill.svg
@@ -0,0 +1,3 @@
+<svg xmlns="http://www.w3.org/2000/svg"  viewBox="0 0 21 20" >
+  <path fill-rule="evenodd" clip-rule="evenodd" d="M2.24348 4.15292C1.9165 4.79466 1.9165 5.63474 1.9165 7.31489V12.6852C1.9165 14.3654 1.9165 15.2054 2.24348 15.8472C2.5311 16.4117 2.99005 16.8706 3.55453 17.1582C4.19627 17.4852 5.03635 17.4852 6.7165 17.4852H13.7832C15.4633 17.4852 16.3034 17.4852 16.9451 17.1582C17.5096 16.8706 17.9686 16.4117 18.2562 15.8472C18.5832 15.2054 18.5832 14.3654 18.5832 12.6852V7.31489C18.5832 5.63473 18.5832 4.79466 18.2562 4.15292C17.9686 3.58843 17.5096 3.12949 16.9451 2.84187C16.3034 2.51489 15.4633 2.51489 13.7832 2.51489H6.7165C5.03635 2.51489 4.19627 2.51489 3.55453 2.84187C2.99005 3.12949 2.5311 3.58843 2.24348 4.15292ZM7.88951 6.75656C7.88951 7.67703 7.14331 8.42322 6.22284 8.42322C5.30236 8.42322 4.55617 7.67703 4.55617 6.75656C4.55617 5.83608 5.30236 5.08989 6.22284 5.08989C7.14331 5.08989 7.88951 5.83608 7.88951 6.75656ZM12.8631 8.65525C12.5376 8.32981 12.01 8.32981 11.6845 8.65525L5.92965 14.4101C5.40468 14.9351 5.77648 15.8327 6.5189 15.8327L15.5062 15.8327C16.4267 15.8327 17.1729 15.0865 17.1729 14.1661V13.3103C17.1729 13.0892 17.0851 12.8773 16.9288 12.721L12.8631 8.65525Z" fill="#3370FF"/>
+</svg>
--- a/packages/web/components/common/Icon/icons/image.svg
+++ b/packages/web/components/common/Icon/icons/image.svg
@@ -0,0 +1,4 @@
+<svg xmlns="http://www.w3.org/2000/svg"  viewBox="0 0 17 16" >
+    <path d="M5.50794 6.8195C6.06022 6.8195 6.50794 6.37178 6.50794 5.8195C6.50794 5.26721 6.06022 4.8195 5.50794 4.8195C4.95565 4.8195 4.50794 5.26721 4.50794 5.8195C4.50794 6.37178 4.95565 6.8195 5.50794 6.8195Z" />
+    <path fill-rule="evenodd" clip-rule="evenodd" d="M1.55029 5.85187C1.55029 4.50775 1.55029 3.83568 1.81188 3.32229C2.04197 2.87071 2.40913 2.50355 2.86072 2.27346C3.3741 2.01187 4.04617 2.01187 5.39029 2.01187H11.0436C12.3878 2.01187 13.0598 2.01187 13.5732 2.27346C14.0248 2.50355 14.3919 2.87071 14.622 3.32229C14.8836 3.83568 14.8836 4.50775 14.8836 5.85187V10.1481C14.8836 11.4922 14.8836 12.1643 14.622 12.6777C14.3919 13.1293 14.0248 13.4964 13.5732 13.7265C13.0598 13.9881 12.3878 13.9881 11.0436 13.9881H5.39029C4.04617 13.9881 3.3741 13.9881 2.86072 13.7265C2.40913 13.4964 2.04197 13.1293 1.81188 12.6777C1.55029 12.1643 1.55029 11.4922 1.55029 10.1481V5.85187ZM5.39029 3.3452H11.0436C11.7377 3.3452 12.1781 3.34624 12.5114 3.37347C12.8291 3.39944 12.9305 3.44241 12.9679 3.46146C13.1686 3.56373 13.3318 3.72691 13.434 3.92761C13.4531 3.96502 13.4961 4.06638 13.522 4.38413C13.5493 4.71745 13.5503 5.15781 13.5503 5.85187V10.1481C13.5503 10.1562 13.5503 10.1641 13.5503 10.1721L10.3165 6.93829C10.0561 6.67794 9.634 6.67794 9.37365 6.93829L3.70938 12.6026C3.5547 12.5791 3.49333 12.5524 3.46604 12.5385C3.26533 12.4363 3.10215 12.2731 2.99989 12.0724C2.98083 12.035 2.93786 11.9336 2.9119 11.6159C2.88466 11.2825 2.88363 10.8422 2.88363 10.1481V5.85187C2.88363 5.15781 2.88466 4.71745 2.9119 4.38413C2.93786 4.06638 2.98083 3.96502 2.99989 3.92761C3.10215 3.72691 3.26533 3.56373 3.46604 3.46146C3.50344 3.44241 3.6048 3.39944 3.92255 3.37347C4.25587 3.34624 4.69623 3.3452 5.39029 3.3452ZM9.84506 8.3525L5.54277 12.6548H11.0436C11.7377 12.6548 12.1781 12.6538 12.5114 12.6265C12.8291 12.6006 12.9305 12.5576 12.9679 12.5385C13.1686 12.4363 13.3318 12.2731 13.434 12.0724C13.4422 12.0563 13.4549 12.0283 13.4687 11.9762L9.84506 8.3525Z" />
+  </svg>
--- a/packages/web/components/common/Icon/icons/loading.svg
+++ b/packages/web/components/common/Icon/icons/loading.svg
@@ -0,0 +1,4 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="48" height="48" viewBox="0 0 48 48" >
+  <path d="M47.3337 24C47.3337 36.8866 36.887 47.3333 24.0003 47.3333C11.1137 47.3333 0.666992 36.8866 0.666992 24C0.666992 11.1133 11.1137 0.666626 24.0003 0.666626C36.887 0.666626 47.3337 11.1133 47.3337 24ZM5.33366 24C5.33366 34.3093 13.691 42.6666 24.0003 42.6666C34.3096 42.6666 42.667 34.3093 42.667 24C42.667 13.6906 34.3096 5.33329 24.0003 5.33329C13.691 5.33329 5.33366 13.6906 5.33366 24Z" />
+  <path d="M24.0003 2.99996C24.0003 1.71129 25.0476 0.654541 26.3298 0.783194C29.1026 1.06141 31.8097 1.83481 34.3204 3.07293C37.5303 4.6559 40.3331 6.95608 42.5119 9.79553C44.6907 12.635 46.1871 15.9376 46.8853 19.4479C47.4314 22.1934 47.4778 25.0084 47.0289 27.7588C46.8213 29.0306 45.5295 29.7687 44.2848 29.4352C43.04 29.1016 42.3169 27.8222 42.4926 26.5456C42.7752 24.4926 42.7147 22.4014 42.3083 20.3583C41.7497 17.5501 40.5526 14.908 38.8096 12.6364C37.0666 10.3649 34.8243 8.52471 32.2564 7.25833C30.3881 6.33698 28.3838 5.73731 26.3276 5.47894C25.049 5.31827 24.0003 4.28862 24.0003 2.99996Z" />
+</svg>
--- a/packages/web/i18n/en/chat.json
+++ b/packages/web/i18n/en/chat.json
@@ -71,13 +71,13 @@
  "response_embedding_model_tokens": "Vector Model Tokens",
  "response_hybrid_weight": "Embedding : Full text = {{emb}} : {{text}}",
  "response_rerank_tokens": "Rearrange Model Tokens",
+  "search_results": "Search results",
  "select": "Select",
  "select_file": "Upload File",
  "select_file_img": "Upload file / image",
  "select_img": "Upload Image",
  "source_cronJob": "Scheduled execution",
  "stream_output": "Stream Output",
-  "to_dataset": "Go to the Knowledge Base",
  "unsupported_file_type": "Unsupported file types",
  "upload": "Upload",
  "variable_invisable_in_share": "Custom variables are not visible in login-free links",
--- a/packages/web/i18n/en/common.json
+++ b/packages/web/i18n/en/common.json
@@ -180,7 +180,7 @@
  "code_error.user_error.balance_not_enough": "Insufficient Account Balance",
  "code_error.user_error.bin_visitor_guest": "You Are Currently a Guest, Unauthorized to Operate",
  "code_error.user_error.un_auth_user": "User Not Found",
-  "comfirm_import": "comfirm_import",
+  "comfirm_import": "Confirm import",
  "comfirm_leave_page": "Confirm to Leave This Page?",
  "comfirn_create": "Confirm Creation",
  "commercial_function_tip": "Please Upgrade to the Commercial Version to Use This Feature: https://doc.fastgpt.cn/docs/commercial/intro/",
@@ -403,7 +403,6 @@
  "core.chat.response.module model": "Model",
  "core.chat.response.module name": "Model Name",
  "core.chat.response.module query": "Question/Search Term",
-  "core.chat.response.module quoteList": "Quote Content",
  "core.chat.response.module similarity": "Similarity",
  "core.chat.response.module temperature": "Temperature",
  "core.chat.response.module time": "Run Time",
@@ -434,7 +433,6 @@
  "core.dataset.Text collection": "Text Dataset",
  "core.dataset.apiFile": "API File",
  "core.dataset.collection.Click top config website": "Click to Configure Website",
-  "core.dataset.collection.Collection name": "Dataset Name",
  "core.dataset.collection.Collection raw text": "Dataset Content",
  "core.dataset.collection.Empty Tip": "The Dataset is Empty",
  "core.dataset.collection.QA Prompt": "QA Split Prompt",
@@ -451,7 +449,6 @@
  "core.dataset.collection.metadata.metadata": "Metadata",
  "core.dataset.collection.metadata.read source": "View Original Content",
  "core.dataset.collection.metadata.source": "Data Source",
-  "core.dataset.collection.metadata.source name": "Source Name",
  "core.dataset.collection.metadata.source size": "Source Size",
  "core.dataset.collection.status.active": "Ready",
  "core.dataset.collection.status.error": "Error",
@@ -743,7 +740,7 @@
  "core.workflow.value": "Value",
  "core.workflow.variable": "Variable",
  "create": "Create",
-  "create_failed": "Creation Failed",
+  "create_failed": "Create failed",
  "create_success": "Created Successfully",
  "create_time": "Creation Time",
  "cron_job_run_app": "Scheduled Task",
@@ -788,7 +785,6 @@
  "dataset.dataset_name": "Dataset Name",
  "dataset.deleteFolderTips": "Confirm to Delete This Folder and All Its Contained Datasets? Data Cannot Be Recovered After Deletion, Please Confirm!",
  "dataset.test.noResult": "No Search Results",
-  "dataset_data_import_q_placeholder": "Up to {{maxToken}} words.",
  "dataset_data_input_a": "Answer",
  "dataset_data_input_chunk": "Chunk",
  "dataset_data_input_chunk_content": "Chunk",
@@ -802,7 +798,6 @@
  "delete_success": "Deleted Successfully",
  "delete_warning": "Deletion Warning",
  "embedding_model_not_config": "No index model is detected",
-  "error.Create failed": "Create failed",
  "error.code_error": "Verification code error",
  "error.fileNotFound": "File not found~",
  "error.inheritPermissionError": "Inherit permission Error",
@@ -1208,6 +1203,7 @@
  "templateTags.Writing": "Writing",
  "template_market": "Template Market",
  "textarea_variable_picker_tip": "Enter \"/\" to select a variable",
+  "to_dataset": "To dataset",
  "ui.textarea.Magnifying": "Magnifying",
  "un_used": "Unused",
  "unauth_token": "The certificate has expired, please log in again",
--- a/packages/web/i18n/en/dataset.json
+++ b/packages/web/i18n/en/dataset.json
@@ -28,16 +28,21 @@
  "collection.training_type": "Chunk type",
  "collection_data_count": "Data amount",
  "collection_metadata_custom_pdf_parse": "PDF enhancement analysis",
+  "collection_name": "Collection name",
  "collection_not_support_retraining": "This collection type does not support retuning parameters",
  "collection_not_support_sync": "This collection does not support synchronization",
  "collection_sync": "Sync data",
  "collection_sync_confirm_tip": "Confirm to start synchronizing data? \nThe system will pull the latest data for comparison. If the contents are different, a new collection will be created and the old collection will be deleted. Please confirm!",
  "collection_tags": "Collection Tags",
+  "common.dataset.data.Input Error Tip": "[Image Dataset] Process error:",
+  "common.error.unKnow": "Unknown error",
  "common_dataset": "General Dataset",
  "common_dataset_desc": "Building a knowledge base by importing files, web page links, or manual entry",
  "condition": "condition",
  "config_sync_schedule": "Configure scheduled synchronization",
+  "confirm_import_images": "Total {{num}} | Confirm create",
  "confirm_to_rebuild_embedding_tip": "Are you sure you want to switch the index for the Dataset?\nSwitching the index is a significant operation that requires re-indexing all data in your Dataset, which may take a long time. Please ensure your account has sufficient remaining points.\n\nAdditionally, you need to update the applications that use this Dataset to avoid conflicts with other indexed model Datasets.",
+  "core.dataset.Image collection": "Image dataset",
  "core.dataset.import.Adjust parameters": "Adjust parameters",
  "custom_data_process_params": "Custom",
  "custom_data_process_params_desc": "Customize data processing rules",
@@ -90,6 +95,7 @@
  "image_auto_parse": "Automatic image indexing",
  "image_auto_parse_tips": "Call VLM to automatically label the pictures in the document and generate additional search indexes",
  "image_training_queue": "Queue of image processing",
+  "images_creating": "Creating",
  "immediate_sync": "Immediate Synchronization",
  "import.Auto mode Estimated Price Tips": "The text understanding model needs to be called, which requires more points: {{price}} points/1K tokens",
  "import.Embedding Estimated Price Tips": "Only use the index model and consume a small amount of AI points: {{price}} points/1K tokens",
@@ -104,6 +110,8 @@
  "index_size": "Index size",
  "index_size_tips": "When vectorized, the system will automatically further segment the blocks according to this size.",
  "input_required_field_to_select_baseurl": "Please enter the required information first",
+  "insert_images": "Added pictures",
+  "insert_images_success": "The new picture is successfully added, and you need to wait for the training to be completed before it will be displayed.",
  "is_open_schedule": "Enable scheduled synchronization",
  "keep_image": "Keep the picture",
  "loading": "Loading...",
@@ -135,6 +143,7 @@
  "process.Image_Index": "Image index generation",
  "process.Is_Ready": "Ready",
  "process.Is_Ready_Count": "{{count}} Group is ready",
+  "process.Parse_Image": "Image analysis",
  "process.Parsing": "Parsing",
  "process.Vectorizing": "Index vectorization",
  "process.Waiting": "Queue",
@@ -179,13 +188,19 @@
  "training.Error": "{{count}} Group exception",
  "training.Normal": "Normal",
  "training_mode": "Chunk mode",
+  "training_queue_tip": "Training queue status",
  "training_ready": "{{count}} Group",
+  "uploading_progress": "Uploading: {{num}}%",
  "vector_model_max_tokens_tip": "Each chunk of data has a maximum length of 3000 tokens",
+  "vector_training_queue": "Vector training queue",
  "vllm_model": "Image understanding model",
+  "vlm_model_required_tooltip": "A Vision Language Model is required to create image collections",
+  "vlm_model_required_warning": "Image datasets require a Vision Language Model (VLM) to be configured. Please add a model that supports image understanding in the model configuration first.",
+  "waiting_for_training": "Waiting for training",
  "website_dataset": "Website Sync",
  "website_dataset_desc": "Build knowledge base by crawling web page data in batches",
  "website_info": "Website Information",
-  "yuque_dataset": "Yuque Dataset",
-  "yuque_dataset_config": "Yuque Dataset Config",
-  "yuque_dataset_desc": "Can build a dataset using Yuque documents by configuring permissions, without secondary storage"
+  "yuque_dataset": "Yuque Knowledge Base",
+  "yuque_dataset_config": "Configure Yuque Knowledge Base",
+  "yuque_dataset_desc": "Build knowledge base using Yuque documents by configuring document permissions, documents will not be stored twice"
 }
--- a/packages/web/i18n/en/file.json
+++ b/packages/web/i18n/en/file.json
@@ -1,9 +1,32 @@
 {
+  "Action": "Please select the image to upload",
+  "All images import failed": "All pictures failed to import",
+  "Dataset_ID_not_found": "The dataset ID does not exist",
+  "Failed_to_get_token": "Failed to obtain the token",
+  "Image_ID_copied": "Copy ID",
+  "Image_Preview": "Picture preview",
+  "Image_dataset_requires_VLM_model_to_be_configured": "The image dataset needs to be configured with the image understanding model (VLM) to be used. Please add a model that supports image understanding in the model configuration first.",
+  "Image_does_not_belong_to_current_team": "The picture does not belong to the current team",
+  "Image_file_does_not_exist": "The picture does not exist",
+  "Loading_image": "Loading the picture...",
+  "Loading_image failed": "Preview loading failed",
+  "Only_support_uploading_one_image": "Only support uploading one image",
+  "Please select the image to upload": "Please select the image to upload",
+  "Please select the image to upload select the image to upload": "",
+  "Please wait for all files to upload": "Please wait for all files to be uploaded to complete",
  "bucket_chat": "Conversation Files",
  "bucket_file": "Dataset Documents",
  "click_to_view_raw_source": "Click to View Original Source",
+  "common.dataset_data_input_image_support_format": "Support .jpg, .jpeg, .png, .gif, .webp formats",
+  "delete_image": "Delete pictures",
  "file_name": "Filename",
  "file_size": "Filesize",
+  "image": "picture",
+  "image_collection": "Picture collection",
+  "image_description": "Image description",
+  "image_description_tip": "Please enter the description of the picture",
+  "please_upload_image_first": "Please upload the picture first",
+  "reached_max_file_count": "Maximum file count reached",
  "release_the_mouse_to_upload_the_file": "Release Mouse to Upload File",
  "select_and_drag_file_tip": "Click or Drag Files Here to Upload",
  "select_file_amount_limit": "You can select up to {{max}} files",
@@ -12,7 +35,9 @@
  "support_file_type": "Supports {{fileType}} file types",
  "support_max_count": "Supports up to {{maxCount}} files",
  "support_max_size": "Maximum file size is {{maxSize}}",
+  "total_files": "Total {{selectFiles.length}} files",
+  "upload_error_description": "Only multiple files or a single folder can be uploaded at a time",
  "upload_failed": "Upload Failed",
-  "reached_max_file_count": "Maximum file count reached",
-  "upload_error_description": "Only multiple files or a single folder can be uploaded at a time"
-}
+  "upload_file_error": "Please upload pictures",
+  "uploading": "Uploading..."
+}
--- a/packages/web/i18n/zh-CN/chat.json
+++ b/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",
--- a/packages/web/i18n/zh-CN/common.json
+++ b/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",
--- a/packages/web/i18n/zh-CN/dataset.json
+++ b/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",
--- a/packages/web/i18n/zh-CN/file.json
+++ b/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..."
+}
--- a/packages/web/i18n/zh-Hant/chat.json
+++ b/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",
--- a/packages/web/i18n/zh-Hant/common.json
+++ b/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",
--- a/packages/web/i18n/zh-Hant/dataset.json
+++ b/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",
--- a/packages/web/i18n/zh-Hant/file.json
+++ b/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..."
+}