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

{
  "Enable": "启用",
  "add_file": "添加文件",
  "api_file": "API 文件库",
  "api_url": "接口地址",
  "apidataset_configuration": "配置信息",
  "auto_indexes": "自动生成补充索引",
  "auto_indexes_tips": "通过大模型进行额外索引生成，提高语义丰富度，提高检索的精度。",
  "auto_training_queue": "增强索引排队",
  "backup_collection": "备份数据",
  "backup_dataset": "备份导入",
  "backup_dataset_success": "备份创建成功",
  "backup_dataset_tip": "可以将导出知识库时，下载的 csv 文件重新导入。",
  "backup_mode": "备份导入",
  "backup_template_invalid": "备份文件格式不正确，应该是首列为 q,a,indexes 的 csv 文件",
  "chunk_max_tokens": "分块上限",
  "chunk_process_params": "分块处理参数",
  "chunk_size": "分块大小",
  "chunk_trigger": "分块条件",
  "chunk_trigger_force_chunk": "强制分块",
  "chunk_trigger_max_size": "原文长度大于文件处理模型最大上下文70%",
  "chunk_trigger_min_size": "原文长度大于",
  "chunk_trigger_tips": "当满足一定条件时才触发分块存储，否则会直接完整存储原文",
  "close_auto_sync": "确认关闭自动同步功能？",
  "collection.Create update time": "创建/更新时间",
  "collection.Training type": "训练模式",
  "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",
  "custom_split_sign_tip": "允许你根据自定义的分隔符进行分块。通常用于已处理好的数据，使用特定的分隔符来精确分块。可以使用 | 符号表示多个分割符，例如：“。|.” 表示中英文句号。\n尽量避免使用正则相关特殊符号，例如: * () [] {} 等。",
  "data_amount": "{{dataAmount}} 组数据, {{indexAmount}} 组索引",
  "data_error_amount": "{{errorAmount}} 组训练异常",
  "data_index_image": "图片索引",
  "data_index_num": "索引 {{index}}",
  "data_parsing": "数据解析中",
  "data_process_params": "处理参数",
  "data_process_setting": "数据处理配置",
  "data_uploading": "数据上传中: {{num}}%",
  "dataset.Chunk_Number": "分块号",
  "dataset.Completed": "完成",
  "dataset.Delete_Chunk": "删除",
  "dataset.Edit_Chunk": "编辑",
  "dataset.Error_Message": "报错信息",
  "dataset.No_Error": "暂无异常信息",
  "dataset.Operation": "操作",
  "dataset.ReTrain": "重试",
  "dataset.Training Process": "训练状态",
  "dataset.Training_Count": "{{count}} 组训练中",
  "dataset.Training_Errors": "异常 ({{count}})",
  "dataset.Training_QA": "{{count}} 组问答对训练中",
  "dataset.Training_Status": "训练状态",
  "dataset.Training_Waiting": "需等待 {{count}} 组数据",
  "dataset.Unsupported operation": "操作不支持",
  "dataset.no_collections": "暂无数据集",
  "dataset.no_tags": "暂无标签",
  "default_params": "默认",
  "default_params_desc": "使用系统默认的参数和规则",
  "download_csv_template": "点击下载 CSV 模板",
  "edit_dataset_config": "编辑知识库配置",
  "empty_collection": "空白数据集",
  "enhanced_indexes": "索引增强",
  "error.collectionNotFound": "集合找不到了~",
  "external_file": "外部文件库",
  "external_file_dataset_desc": "可以通过 API，使用外部文件库构建知识库",
  "external_id": "文件阅读 ID",
  "external_other_dataset_desc": "自定义API、飞书、语雀等外部文档作为知识库",
  "external_read_url": "外部预览地址",
  "external_read_url_tip": "可以配置你文件库的阅读地址。便于对用户进行阅读鉴权操作。目前可以使用 {{fileId}} 变量来指代外部文件 ID。",
  "external_url": "文件访问 URL",
  "failedToLoadRootDirectories": "加载根目录失败",
  "failedToLoadSubDirectories": "加载子目录失败",
  "feishu_dataset": "飞书知识库",
  "feishu_dataset_config": "配置飞书知识库",
  "feishu_dataset_desc": "可通过配置飞书文档权限，使用飞书文档构建知识库，文档不会进行二次存储",
  "file_list": "文件列表",
  "file_model_function_tip": "用于增强索引和 QA 生成",
  "filename": "文件名",
  "folder_dataset": "文件夹",
  "getDirectoryFailed": "获取目录失败",
  "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",
  "import_confirm": "确认上传",
  "import_data_preview": "数据预览",
  "import_data_process_setting": "数据处理方式设置",
  "import_file_parse_setting": "文件解析设置",
  "import_model_config": "模型选择",
  "import_param_setting": "参数设置",
  "import_select_file": "选择文件",
  "import_select_link": "输入链接",
  "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...",
  "max_chunk_size": "最大分块大小",
  "move.hint": "移动后，所选知识库/文件夹将继承新文件夹的权限设置，原先的权限设置失效。",
  "noChildren": "无子目录",
  "noSelectedFolder": "没有选择文件夹",
  "noSelectedId": "没有选择 ID",
  "noValidId": "没有有效的 ID",
  "open_auto_sync": "开启定时同步后，系统将会每天不定时尝试同步集合，集合同步期间，会出现无法搜索到该集合数据现象。",
  "other_dataset": "第三方知识库",
  "paragraph_max_deep": "最大段落深度",
  "paragraph_split": "按段落分块",
  "paragraph_split_tip": "优先按 Makdown 标题段落进行分块，如果分块过长，再按长度进行二次分块",
  "params_config": "配置",
  "pdf_enhance_parse": "PDF增强解析",
  "pdf_enhance_parse_price": "{{price}}积分/页",
  "pdf_enhance_parse_tips": "调用 PDF 识别模型进行解析，可以将其转换成 Markdown 并保留文档中的图片，同时也可以对扫描件进行识别，识别时间较长。",
  "permission.des.manage": "可管理整个知识库数据和信息",
  "permission.des.read": "可查看知识库内容",
  "permission.des.write": "可增加和变更知识库内容",
  "pleaseFillUserIdAndToken": "请填写 User ID 和 Token",
  "preview_chunk": "分块预览",
  "preview_chunk_empty": "文件内容为空",
  "preview_chunk_intro": "共 {{total}} 个分块，最多展示 10 个",
  "preview_chunk_not_selected": "点击左侧文件后进行预览",
  "process.Auto_Index": "自动索引生成",
  "process.Get QA": "问答对提取",
  "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",
  "rebuild_embedding_start_tip": "切换索引模型任务已开始",
  "rebuilding_index_count": "重建中索引数量：{{count}}",
  "request_headers": "请求头参数，会自动补充 Bearer",
  "retain_collection": "调整训练参数",
  "retrain_task_submitted": "重新训练任务已提交",
  "rootDirectoryFormatError": "根目录数据格式不正确",
  "rootdirectory": "/根目录",
  "same_api_collection": "存在相同的 API 集合",
  "selectDirectory": "选择",
  "selectRootFolder": "选择根目录",
  "split_chunk_char": "按指定分割符分块",
  "split_chunk_size": "按长度分块",
  "split_sign_break": "1 个换行符",
  "split_sign_break2": "2 个换行符",
  "split_sign_custom": "自定义",
  "split_sign_exclamatiob": "感叹号",
  "split_sign_null": "不设置",
  "split_sign_period": "句号",
  "split_sign_question": "问号",
  "split_sign_semicolon": "分号",
  "start_sync_website_tip": "确认开始同步数据？将会删除旧数据后重新获取，请确认！",
  "status_error": "运行异常",
  "sync_collection_failed": "同步集合错误，请检查是否能正常访问源文件",
  "sync_schedule": "定时同步",
  "sync_schedule_tip": "仅会同步已存在的集合。包括链接集合以及 API 知识库里所有集合。系统会每天进行轮询更新，无法确定具体的更新时间。",
  "tag.Add_new_tag": "新建标签",
  "tag.Edit_tag": "编辑标签",
  "tag.add": "创建",
  "tag.add_new": "新建",
  "tag.cancel": "取消选择",
  "tag.delete_tag_confirm": "确定删除标签？",
  "tag.manage": "标签管理",
  "tag.searchOrAddTag": "搜索或添加标签",
  "tag.tags": "标签",
  "tag.total_tags": "共{{total}}个标签",
  "template_dataset": "模版导入",
  "template_file_invalid": "模板文件格式不正确，应该是首列为 q,a,indexes 的 csv 文件",
  "template_mode": "模板导入",
  "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",
  "upload_by_template_format": "按模版文件上传",
  "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",
  "yuque_dataset": "语雀知识库",
  "yuque_dataset_config": "配置语雀知识库",
  "yuque_dataset_desc": "可通过配置语雀文档权限，使用语雀文档构建知识库，文档不会进行二次存储"
}