V4.9.4 feature (#4470)

* Training status (#4424) * dataset data training state (#4311) * dataset data training state * fix * fix ts * fix * fix api format * fix * fix * perf: count training * format * fix: dataset training state (#4417) * fix * add test * fix * fix * fix test * fix test * perf: training count * count * loading status --------- Co-authored-by: heheer <heheer@sealos.io> * doc * website sync feature (#4429) * perf: introduce BullMQ for website sync (#4403) * perf: introduce BullMQ for website sync * feat: new redis module * fix: remove graceful shutdown * perf: improve UI in dataset detail - Updated the "change" icon SVG file. - Modified i18n strings. - Added new i18n string "immediate_sync". - Improved UI in dataset detail page, including button icons and background colors. * refactor: Add chunkSettings to DatasetSchema * perf: website sync ux * env template * fix: clean up website dataset when updating chunk settings (#4420) * perf: check setting updated * perf: worker currency * feat: init script for website sync refactor (#4425) * website feature doc --------- Co-authored-by: a.e. <49438478+I-Info@users.noreply.github.com> * pro migration (#4388) (#4433) * pro migration * reuse customPdfParseType Co-authored-by: gggaaallleee <91131304+gggaaallleee@users.noreply.github.com> * perf: remove loading ui * feat: config chat file expired time * Redis cache (#4436) * perf: add Redis cache for vector counting (#4432) * feat: cache * perf: get cache key --------- Co-authored-by: a.e. <49438478+I-Info@users.noreply.github.com> * perf: mobile voice input (#4437) * update:Mobile voice interaction (#4362) * Add files via upload * Add files via upload * Update ollama.md * Update ollama.md * Add files via upload * Update useSpeech.ts * Update ChatInput.tsx * Update useSpeech.ts * Update ChatInput.tsx * Update useSpeech.ts * Update constants.ts * Add files via upload * Update ChatInput.tsx * Update useSpeech.ts * Update useSpeech.ts * Update useSpeech.ts * Update ChatInput.tsx * Add files via upload * Update common.json * Update VoiceInput.tsx * Update ChatInput.tsx * Update VoiceInput.tsx * Update useSpeech.ts * Update useSpeech.ts * Update common.json * Update common.json * Update common.json * Update VoiceInput.tsx * Update VoiceInput.tsx * Update ChatInput.tsx * Update VoiceInput.tsx * Update ChatInput.tsx * Update VoiceInput.tsx * Update ChatInput.tsx * Update useSpeech.ts * Update common.json * Update chat.json * Update common.json * Update chat.json * Update common.json * Update chat.json * Update VoiceInput.tsx * Update ChatInput.tsx * Update useSpeech.ts * Update VoiceInput.tsx * speech ui * 优化语音输入组件，调整输入框显示逻辑，修复语音输入遮罩层样式，更新画布背景透明度，增强用户交互体验。 (#4435) * perf: mobil voice input --------- Co-authored-by: dreamer6680 <1468683855@qq.com> * Test completion v2 (#4438) * add v2 completions (#4364) * add v2 completions * completion config * config version * fix * frontend * doc * fix * fix: completions v2 api --------- Co-authored-by: heheer <heheer@sealos.io> * package * Test mongo log (#4443) * feat: mongodb-log (#4426) * perf: mongo log * feat: completions stop reasoner * mongo db log --------- Co-authored-by: Finley Ge <32237950+FinleyGe@users.noreply.github.com> * update doc * Update doc * fix external var ui (#4444) * action * fix: ts (#4458) * preview doc action add docs preview permission update preview action udpate action * update doc (#4460) * update preview action * update doc * remove * update * schema * update mq export;perf: redis cache (#4465) * perf: redis cache * update mq export * perf: website sync error tip * add error worker * website sync ui (#4466) * Updated the dynamic display of the voice input pop-up (#4469) * Update VoiceInput.tsx * Update VoiceInput.tsx * Update VoiceInput.tsx * fix: voice input --------- Co-authored-by: heheer <heheer@sealos.io> Co-authored-by: a.e. <49438478+I-Info@users.noreply.github.com> Co-authored-by: gggaaallleee <91131304+gggaaallleee@users.noreply.github.com> Co-authored-by: dreamer6680 <1468683855@qq.com> Co-authored-by: Finley Ge <32237950+FinleyGe@users.noreply.github.com>
2025-04-08 12:05:04 +08:00
parent 5839325f77
commit f642c9603b
151 changed files with 5434 additions and 1354 deletions
--- a/packages/web/i18n/zh-CN/chat.json
+++ b/packages/web/i18n/zh-CN/chat.json
@@ -3,6 +3,7 @@
  "Delete_all": "清空词库",
  "LLM_model_response_empty": "模型流响应为空，请检查模型流输出是否正常",
  "ai_reasoning": "思考过程",
+  "back_to_text": "返回输入",
  "chat.quote.No Data": "找不到该文件",
  "chat.quote.deleted": "该数据已被删除～",
  "chat_history": "聊天记录",
@@ -10,12 +11,22 @@
  "chat_test_app": "调试-{{name}}",
  "citations": "{{num}}条引用",
  "click_contextual_preview": "点击查看上下文预览",
+  "completion_finish_close": "连接断开",
+  "completion_finish_content_filter": "触发安全风控",
+  "completion_finish_function_call": "函数调用",
+  "completion_finish_length": "超出回复限制",
+  "completion_finish_null": "未知",
+  "completion_finish_reason": "完成原因",
+  "completion_finish_stop": "正常完成",
+  "completion_finish_tool_calls": "工具调用",
  "config_input_guide": "配置输入引导",
  "config_input_guide_lexicon": "配置词库",
  "config_input_guide_lexicon_title": "配置词库",
  "content_empty": "内容为空",
  "contextual": "{{num}}条上下文",
  "contextual_preview": "上下文预览 {{num}} 条",
+  "core.chat.moveCancel": "上滑取消",
+  "core.chat.shortSpeak": "说话时间太短",
  "csv_input_lexicon_tip": "仅支持 CSV 批量导入，点击下载模板",
  "custom_input_guide_url": "自定义词库地址",
  "data_source": "来源知识库: {{name}}",
@@ -41,11 +52,14 @@
  "not_query": "缺少查询内容",
  "not_select_file": "未选择文件",
  "plugins_output": "插件输出",
+  "press_to_speak": "按住说话",
  "query_extension_IO_tokens": "问题优化输入/输出 Tokens",
  "query_extension_result": "问题优化结果",
  "question_tip": "从上到下，为各个模块的响应顺序",
  "read_raw_source": "打开原文",
  "reasoning_text": "思考过程",
+  "release_cancel": "松开取消",
+  "release_send": "松开发送，上滑取消",
  "response.child total points": "子工作流积分消耗",
  "response.dataset_concat_length": "合并后总数",
  "response.node_inputs": "节点输入",
--- a/packages/web/i18n/zh-CN/common.json
+++ b/packages/web/i18n/zh-CN/common.json
@@ -1,5 +1,6 @@
 {
  "App": "应用",
+  "Click_to_expand": "点击查看详情",
  "Download": "下载",
  "Export": "导出",
  "FAQ.ai_point_a": "每次调用AI模型时，都会消耗一定的AI积分。具体的计算标准可参考上方的“AI 积分计算标准”。\nToken计算采用GPT3.5相同公式，1Token≈0.7中文字符≈0.9英文单词，连续出现的字符可能被认为是1个Tokens。",
@@ -514,7 +515,7 @@
  "core.dataset.Query extension intro": "开启问题优化功能，可以提高提高连续对话时，知识库搜索的精度。开启该功能后，在进行知识库搜索时，会根据对话记录，利用 AI 补全问题缺失的信息。",
  "core.dataset.Quote Length": "引用内容长度",
  "core.dataset.Read Dataset": "查看知识库详情",
-  "core.dataset.Set Website Config": "开始配置网站信息",
+  "core.dataset.Set Website Config": "开始配置",
  "core.dataset.Start export": "已开始导出",
  "core.dataset.Table collection": "表格数据集",
  "core.dataset.Text collection": "文本数据集",
@@ -530,7 +531,6 @@
  "core.dataset.collection.Website Empty Tip": "还没有关联网站",
  "core.dataset.collection.Website Link": "Web 站点地址",
  "core.dataset.collection.id": "集合 ID",
-  "core.dataset.collection.metadata.Chunk Size": "分割大小",
  "core.dataset.collection.metadata.Createtime": "创建时间",
  "core.dataset.collection.metadata.Raw text length": "原文长度",
  "core.dataset.collection.metadata.Updatetime": "更新时间",
@@ -541,6 +541,7 @@
  "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",
  "core.dataset.collection.sync.result.sameRaw": "内容未变动，无需更新",
  "core.dataset.collection.sync.result.success": "开始同步",
  "core.dataset.data.Data Content": "相关数据内容",
@@ -631,6 +632,7 @@
  "core.dataset.search.search mode": "搜索方式",
  "core.dataset.status.active": "已就绪",
  "core.dataset.status.syncing": "同步中",
+  "core.dataset.status.waiting": "排队中",
  "core.dataset.test.Batch test": "批量测试",
  "core.dataset.test.Batch test Placeholder": "选择一个 CSV 文件",
  "core.dataset.test.Search Test": "搜索测试",
@@ -1289,4 +1291,4 @@
  "yes": "是",
  "yesterday": "昨天",
  "yesterday_detail_time": "昨天 {{time}}"
-}
+}
--- a/packages/web/i18n/zh-CN/dataset.json
+++ b/packages/web/i18n/zh-CN/dataset.json
@@ -7,6 +7,7 @@
  "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",
  "chunk_max_tokens": "分块上限",
+  "chunk_size": "分块大小",
  "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",
@@ -28,9 +29,24 @@
  "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_num": "索引 {{index}}",
  "data_process_params": "处理参数",
  "data_process_setting": "数据处理配置",
+  "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",
@@ -55,6 +71,7 @@
  "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",
+  "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",
@@ -71,6 +88,7 @@
  "keep_image": "保留图片",
  "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。",
  "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。",
+  "params_config": "配置",
  "params_setting": "参数设置",
  "pdf_enhance_parse": "PDF增强解析",
  "pdf_enhance_parse_price": "{{price}}积分/页",
@@ -82,6 +100,14 @@
  "preview_chunk_empty": "无法读取该文件内容",
  "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.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",
@@ -99,6 +125,7 @@
  "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。",
@@ -114,11 +141,15 @@
  "tag.total_tags": "共{{total}}个标签",
  "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.Normal": "正常",
  "training_mode": "处理方式",
+  "training_ready": "{{count}} 组",
  "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",
  "website_dataset": "Web 站点同步",
  "website_dataset_desc": "Web 站点同步允许你直接使用一个网页链接构建知识库",
+  "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"