Add image index and pdf parse (#3956)

* feat: think tag parse

* feat: parse think tag test

* feat: pdf parse ux

* feat: doc2x parse

* perf: rewrite training mode setting

* feat: image parse queue

* perf: image index

* feat: image parse process

* feat: add init sh

* fix: ts

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

@@ -565,10 +565,7 @@
   "core.dataset.file": "文件",
   "core.dataset.folder": "目录",
   "core.dataset.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",
-  "core.dataset.import.Auto process": "自动",
-  "core.dataset.import.Auto process desc": "自动设置分割和预处理规则",
   "core.dataset.import.Chunk Range": "范围：{{min}}~{{max}}",
-  "core.dataset.import.Chunk Split": "直接分段",
   "core.dataset.import.Chunk Split Tip": "将文本按一定的规则进行分段处理后，转成可进行语义搜索的格式，适合绝大多数场景。不需要调用模型额外处理，成本低。",
   "core.dataset.import.Continue upload": "继续上传",
   "core.dataset.import.Custom process": "自定义规则",
@@ -578,7 +575,6 @@
   "core.dataset.import.Custom split char Tips": "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。",
   "core.dataset.import.Custom text": "自定义文本",
   "core.dataset.import.Custom text desc": "手动输入一段文本作为数据集",
-  "core.dataset.import.Data Preprocessing": "数据处理",
   "core.dataset.import.Data process params": "数据处理参数",
   "core.dataset.import.Down load csv template": "点击下载 CSV 模板",
   "core.dataset.import.Embedding Estimated Price Tips": "仅使用索引模型，消耗少量 AI 积分：{{price}} 积分/1K tokens",
@@ -600,7 +596,6 @@
   "core.dataset.import.Source name": "来源名",
   "core.dataset.import.Sources list": "来源列表",
   "core.dataset.import.Start upload": "开始上传",
-  "core.dataset.import.Total files": "共 {{total}} 个文件",
   "core.dataset.import.Upload complete": "完成上传",
   "core.dataset.import.Upload data": "确认上传",
   "core.dataset.import.Upload file progress": "文件上传进度",
@@ -650,12 +645,12 @@
   "core.dataset.test.test result placeholder": "测试结果将在这里展示",
   "core.dataset.test.test result tip": "根据知识库内容与测试文本的相似度进行排序，你可以根据测试结果调整对应的文本。\n注意：测试记录中的数据可能已经被修改过，点击某条测试数据后将展示最新的数据。",
   "core.dataset.training.Agent queue": "QA 训练排队",
-  "core.dataset.training.Auto mode": "增强处理",
+  "core.dataset.training.Auto mode": "补充索引",
   "core.dataset.training.Auto mode Tip": "通过子索引以及调用模型生成相关问题与摘要，来增加数据块的语义丰富度，更利于检索。需要消耗更多的存储空间和增加 AI 调用次数。",
-  "core.dataset.training.Chunk mode": "直接分段",
+  "core.dataset.training.Chunk mode": "直接分块",
   "core.dataset.training.Full": "预计 5 分钟以上",
   "core.dataset.training.Leisure": "空闲",
-  "core.dataset.training.QA mode": "问答拆分",
+  "core.dataset.training.QA mode": "问答对提取",
   "core.dataset.training.Vector queue": "索引排队",
   "core.dataset.training.Waiting": "预计 5 分钟",
   "core.dataset.training.Website Sync": "Web 站点同步",
@@ -864,7 +859,6 @@
   "dataset.collections.Select Collection": "选择文件",
   "dataset.collections.Select One Collection To Store": "选择一个文件进行存储",
   "dataset.data.Can not edit": "无编辑权限",
-  "dataset.data.Custom Index Number": "自定义索引{{number}}",
   "dataset.data.Default Index": "默认索引",
   "dataset.data.Delete Tip": "确认删除该条数据？",
   "dataset.data.Index Placeholder": "输入索引文本内容",
@@ -959,6 +953,7 @@
   "new_create": "新建",
   "no": "否",
   "no_laf_env": "系统未配置Laf环境",
+  "not_model_config": "未配置相关模型",
   "not_yet_introduced": "暂无介绍",
   "option": "选项",
   "pay.amount": "金额",
@@ -1124,7 +1119,6 @@
   "support.wallet.invoice_detail": "发票详情",
   "support.wallet.invoice_info": "发票将在 3-7 个工作日内发送至邮箱，请耐心等待",
   "support.wallet.invoicing": "开票",
-  "support.wallet.moduleName.index": "索引生成",
   "support.wallet.moduleName.qa": "QA 拆分",
   "support.wallet.noBill": "无账单记录~",
   "support.wallet.no_invoice": "暂无开票记录",