FastGPT/packages/web/i18n/en/dataset.json

{
  "Enable": "Enable",
  "add_file": "Import",
  "api_file": "API Dataset",
  "api_url": "API Url",
  "apidataset_configuration": "Configuration information",
  "auto_indexes": "Automatically generate supplementary indexes",
  "auto_indexes_tips": "Additional index generation is performed through large models to improve semantic richness and improve retrieval accuracy.",
  "auto_training_queue": "Enhanced index queueing",
  "backup_collection": "Backup data",
  "backup_dataset": "Backup import",
  "backup_dataset_success": "The backup was created successfully",
  "backup_dataset_tip": "You can reimport the downloaded csv file when exporting the knowledge base.",
  "backup_mode": "Backup import",
  "backup_template_invalid": "The backup file format is incorrect, it should be the csv file with the first column as q,a,indexes",
  "chunk_max_tokens": "max_tokens",
  "chunk_process_params": "Block processing parameters",
  "chunk_size": "Block size",
  "chunk_trigger": "Blocking conditions",
  "chunk_trigger_force_chunk": "Forced chunking",
  "chunk_trigger_max_size": "The original text length is greater than the maximum context of the file processing model 70%",
  "chunk_trigger_min_size": "The original text is greater than",
  "chunk_trigger_tips": "Block storage is triggered when certain conditions are met, otherwise the original text will be stored in full directly",
  "close_auto_sync": "Are you sure you want to turn off automatic sync?",
  "collection.Create update time": "Creation/Update Time",
  "collection.Training type": "Training",
  "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",
  "custom_split_char": "Char",
  "custom_split_sign_tip": "Allows you to chunk according to custom delimiters. \nUsually used for processed data, using specific separators for precise chunking. \nYou can use the | symbol to represent multiple splitters, such as: \".|.\" to represent a period in Chinese and English.\n\nTry to avoid using special symbols related to regular, such as: * () [] {}, etc.",
  "data_amount": "{{dataAmount}} Datas, {{indexAmount}} Indexes",
  "data_error_amount": "{{errorAmount}} Group training exception",
  "data_index_image": "Image index",
  "data_index_num": "Index {{index}}",
  "data_parsing": "Data analysis",
  "data_process_params": "Params",
  "data_process_setting": "Processing config",
  "data_uploading": "Data is being uploaded: {{num}}%",
  "dataset.Chunk_Number": "Block number",
  "dataset.Completed": "Finish",
  "dataset.Delete_Chunk": "delete",
  "dataset.Edit_Chunk": "edit",
  "dataset.Error_Message": "Report an error message",
  "dataset.No_Error": "No exception information yet",
  "dataset.Operation": "operate",
  "dataset.ReTrain": "Retrain",
  "dataset.Training Process": "Training status",
  "dataset.Training_Count": "{{count}} Group training",
  "dataset.Training_Errors": "Errors",
  "dataset.Training_QA": "{{count}} Group Q&A pair training",
  "dataset.Training_Status": "Training status",
  "dataset.Training_Waiting": "Need to wait for {{count}} group data",
  "dataset.Unsupported operation": "dataset.Unsupported operation",
  "dataset.no_collections": "No datasets available",
  "dataset.no_tags": "No tags available",
  "default_params": "default",
  "default_params_desc": "Use system default parameters and rules",
  "download_csv_template": "Click to download the CSV template",
  "edit_dataset_config": "Edit knowledge base configuration",
  "empty_collection": "Blank dataset",
  "enhanced_indexes": "Index enhancement",
  "error.collectionNotFound": "Collection not found~",
  "external_file": "External File Library",
  "external_file_dataset_desc": "You can use external file library to build a knowledge library through the API",
  "external_id": "File Reading ID",
  "external_other_dataset_desc": "Customize API, Feishu, Yuque and other external documents as knowledge bases",
  "external_read_url": "External Preview URL",
  "external_read_url_tip": "Configure the reading URL of your file library for user authentication. Use the {{fileId}} variable to refer to the external file ID.",
  "external_url": "File Access URL",
  "failedToLoadRootDirectories": "Failed to load root directories",
  "failedToLoadSubDirectories": "Failed to load subdirectories",
  "feishu_dataset": "Feishu Dataset",
  "feishu_dataset_config": "Feishu Dataset Config",
  "feishu_dataset_desc": "Can build a dataset using Feishu documents by configuring permissions, without secondary storage",
  "file_list": "File list",
  "file_model_function_tip": "Enhances indexing and QA generation",
  "filename": "Filename",
  "folder_dataset": "Folder",
  "getDirectoryFailed": "Get directory failed",
  "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",
  "import_confirm": "Confirm upload",
  "import_data_preview": "Data preview",
  "import_data_process_setting": "Data processing method settings",
  "import_file_parse_setting": "File parsing settings",
  "import_model_config": "Model selection",
  "import_param_setting": "Parameter settings",
  "import_select_file": "Select a file",
  "import_select_link": "Enter link",
  "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",
  "llm_paragraph_mode": "LLM recognition paragraph(Beta)",
  "llm_paragraph_mode_auto": "automatic",
  "llm_paragraph_mode_auto_desc": "Enable the model to automatically recognize the title when the file content does not contain a Markdown title.",
  "llm_paragraph_mode_forbid": "Disabled",
  "llm_paragraph_mode_forbid_desc": "Force the disabling of the model's automatic paragraph recognition",
  "loading": "Loading...",
  "max_chunk_size": "Maximum chunk size",
  "move.hint": "After moving, the selected knowledge base/folder will inherit the permission settings of the new folder, and the original permission settings will become invalid.",
  "noChildren": "No subdirectories",
  "noSelectedFolder": "No selected folder",
  "noSelectedId": "No selected ID",
  "noValidId": "No valid ID",
  "open_auto_sync": "After scheduled synchronization is turned on, the system will try to synchronize the collection from time to time every day. During the collection synchronization period, the collection data will not be searched.",
  "other_dataset": "Third-party knowledge base",
  "paragraph_max_deep": "Maximum paragraph depth",
  "paragraph_split": "Partition by paragraph",
  "paragraph_split_tip": "Priority is given to chunking according to the Makdown title paragraph. If the chunking is too long, then chunking is done according to the length.",
  "params_config": "Config",
  "pdf_enhance_parse": "PDF enhancement analysis",
  "pdf_enhance_parse_price": "{{price}} points/page",
  "pdf_enhance_parse_tips": "Calling PDF recognition model for parsing, you can convert it into Markdown and retain pictures in the document. At the same time, you can also identify scanned documents, which will take a long time to identify them.",
  "permission.des.manage": "Can manage the entire knowledge base data and information",
  "permission.des.read": "View knowledge base content",
  "permission.des.write": "Ability to add and change knowledge base content",
  "pleaseFillUserIdAndToken": "Please fill in User ID and Token",
  "preview_chunk": "Preview chunks",
  "preview_chunk_empty": "File content is empty",
  "preview_chunk_intro": "A total of {{total}} blocks, up to 10",
  "preview_chunk_not_selected": "Click on the file on the left to preview",
  "process.Auto_Index": "Automatic index generation",
  "process.Get QA": "Q&A extraction",
  "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",
  "rebuild_embedding_start_tip": "Index model switching task has started",
  "rebuilding_index_count": "Number of indexes being rebuilt: {{count}}",
  "request_headers": "Request headers, will automatically append 'Bearer '",
  "retain_collection": "Adjust Training Parameters",
  "retrain_task_submitted": "The retraining task has been submitted",
  "rootDirectoryFormatError": "Root directory data format is incorrect",
  "rootdirectory": "/rootdirectory",
  "same_api_collection": "The same API set exists",
  "selectDirectory": "Choose",
  "selectRootFolder": "Select Root Folder",
  "split_chunk_char": "Block by specified splitter",
  "split_chunk_size": "Block by length",
  "split_sign_break": "1 newline character",
  "split_sign_break2": "2 newline characters",
  "split_sign_custom": "Customize",
  "split_sign_exclamatiob": "exclamation mark",
  "split_sign_null": "Not set",
  "split_sign_period": "period",
  "split_sign_question": "question mark",
  "split_sign_semicolon": "semicolon",
  "start_sync_website_tip": "Confirm to start synchronizing data? \nThe old data will be deleted and retrieved again, please confirm!",
  "status_error": "Running exception",
  "sync_collection_failed": "Synchronization collection error, please check whether the source file can be accessed normally",
  "sync_schedule": "Timing synchronization",
  "sync_schedule_tip": "Only existing collections will be synchronized. \nIncludes linked collections and all collections in the API knowledge base. \nThe system will poll for updates every day, and the specific update time cannot be determined.",
  "table_model_tip": "Store each row of data as a chunk",
  "tag.Add_new_tag": "add_new Tag",
  "tag.Edit_tag": "Edit Tag",
  "tag.add": "Create",
  "tag.add_new": "add_new",
  "tag.cancel": "Cancel",
  "tag.delete_tag_confirm": "Confirm to delete the tag?",
  "tag.manage": "Tagging",
  "tag.searchOrAddTag": "Search or Add Tag",
  "tag.tags": "Tags",
  "tag.total_tags": "Total {{total}} tags",
  "template_dataset": "Template import",
  "template_file_invalid": "The template file format is incorrect, it should be the csv file with the first column as q,a,indexes",
  "template_mode": "Template import",
  "the_knowledge_base_has_indexes_that_are_being_trained_or_being_rebuilt": "The Dataset has indexes that are being trained or rebuilt",
  "total_num_files": "Total {{total}} files",
  "training.Error": "{{count}} Group exception",
  "training.Normal": "Normal",
  "training_mode": "Chunk mode",
  "training_queue_tip": "Training queue status",
  "training_ready": "{{count}} Group",
  "upload_by_template_format": "Upload by template file",
  "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 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"
}