V4.6.9-first commit (#899)

* perf: insert mongo dataset data session * perf: dataset data index * remove delay * rename bill schema * rename bill record * perf: bill table * perf: prompt * perf: sub plan * change the usage count * feat: usage bill * publish usages * doc * 新增团队聊天功能 (#20) * perf: doc * feat 添加标签部分 feat 信息团队标签配置 feat 新增团队同步管理 feat team分享页面 feat 完成team分享页面 feat 实现模糊搜索 style 格式化 fix 修复迷糊匹配 style 样式修改 fix 团队标签功能修复 * fix 修复鉴权功能 * merge 合并代码 * fix 修复引用错误 * fix 修复pr问题 * fix 修复ts格式问题 --------- Co-authored-by: archer <545436317@qq.com> Co-authored-by: liuxingwan <liuxingwan.lxw@alibaba-inc.com> * update extra plan * fix: ts * format * perf: bill field * feat: standard plan * fix: ts * feat 个人账号页面修改 (#22) * feat 添加标签部分 feat 信息团队标签配置 feat 新增团队同步管理 feat team分享页面 feat 完成team分享页面 feat 实现模糊搜索 style 格式化 fix 修复迷糊匹配 style 样式修改 fix 团队标签功能修复 * fix 修复鉴权功能 * merge 合并代码 * fix 修复引用错误 * fix 修复pr问题 * fix 修复ts格式问题 * feat 修改个人账号页 --------- Co-authored-by: liuxingwan <liuxingwan.lxw@alibaba-inc.com> * sub plan page (#23) * fix chunk index; error page text * feat: dataset process Integral prediction * feat: stand plan field * feat: sub plan limit * perf: index * query extension * perf: share link push app name * perf: plan point unit * perf: get sub plan * perf: account page * feat 新增套餐详情弹窗代码 (#24) * merge 合并代码 * fix 新增套餐详情弹框 * fix 修复pr问题 * feat: change http node input to prompt editor (#21) * feat: change http node input to prompt editor * fix * split PromptEditor to HttpInput * Team plans (#25) * perf: pay check * perf: team plan test * plan limit check * replace sensitive text * perf: fix some null * collection null check * perf: plans modal * perf: http module * pacakge (#26) * individuation page and pay modal amount (#27) * feat: individuation page * team chat config * pay modal * plan count and replace invalid chars (#29) * fix: user oneapi * fix: training queue * fix: qa queue * perf: remove space chars * replace invalid chars * change httpinput dropdown menu (#28) * perf: http * reseet free plan * perf: plan code to packages * remove llm config to package * perf: code * perf: faq * fix: get team plan --------- Co-authored-by: yst <77910600+yu-and-liu@users.noreply.github.com> Co-authored-by: liuxingwan <liuxingwan.lxw@alibaba-inc.com> Co-authored-by: heheer <71265218+newfish-cmyk@users.noreply.github.com>
2025-07-22 04:06:18 +00:00 · 2024-02-28 13:19:15 +08:00
parent 32686f9e3e
commit 064c64e74c
282 changed files with 7223 additions and 4731 deletions
--- a/.vscode/settings.json
+++ b/.vscode/settings.json
@@ -10,6 +10,6 @@
    "i18n-ally.keystyle": "nested",
    "i18n-ally.sortKeys": true,
    "i18n-ally.keepFulfilled": true,
-    "i18n-ally.sourceLanguage": "zh", // 根据此语言文件翻译其他语言文件的变量和内容
+    "i18n-ally.sourceLanguage": "en", // 根据此语言文件翻译其他语言文件的变量和内容
    "i18n-ally.displayLanguage": "en", // 显示语言
 }
--- a/docSite/content/docs/course/data_search.md
+++ b/docSite/content/docs/course/data_search.md
@@ -56,7 +56,7 @@ FastGPT 采用了`PostgresSQL`的`PG Vector`插件作为向量检索器，索引

 ### 检索方案

-1. 通过`问题补全`实现指代消除和问题扩展，从而增加连续对话的检索能力以及语义丰富度。
+1. 通过`问题优化`实现指代消除和问题扩展，从而增加连续对话的检索能力以及语义丰富度。
 2. 通过`Concat query`来增加`Rerank`连续对话的时，排序的准确性。
 3. 通过`RRF`合并方式，综合多个渠道的检索效果。
 4. 通过`Rerank`来二次排序，提高精度。
@@ -97,7 +97,7 @@ FastGPT 采用了`PostgresSQL`的`PG Vector`插件作为向量检索器，索引

 #### 结果重排

-利用`ReRank`模型对搜索结果进行重排，绝大多数情况下，可以有效提高搜索结果的准确率。不过，重排模型与问题的完整度（主谓语齐全）有一些关系，通常会先走问题补全后再进行搜索-重排。重排后可以得到一个`0-1`的得分，代表着搜索内容与问题的相关度，该分数通常比向量的得分更加精确，可以根据得分进行过滤。
+利用`ReRank`模型对搜索结果进行重排，绝大多数情况下，可以有效提高搜索结果的准确率。不过，重排模型与问题的完整度（主谓语齐全）有一些关系，通常会先走问题优化后再进行搜索-重排。重排后可以得到一个`0-1`的得分，代表着搜索内容与问题的相关度，该分数通常比向量的得分更加精确，可以根据得分进行过滤。

 FastGPT 会使用 `RRF` 对重排结果、向量搜索结果、全文检索结果进行合并，得到最终的搜索结果。

@@ -115,7 +115,7 @@ FastGPT 会使用 `RRF` 对重排结果、向量搜索结果、全文检索结

 该值仅在`语义检索`或使用`结果重排`时生效。

-### 问题补全
+### 问题优化

 #### 背景

@@ -125,7 +125,7 @@ FastGPT 会使用 `RRF` 对重排结果、向量搜索结果、全文检索结

 ![](/imgs/coreferenceResolution2.jpg)

-用户在提问“第二点是什么”的时候，只会去知识库里查找“第二点是什么”，压根查不到内容。实际上需要查询的是“QA结构是什么”。因此我们需要引入一个【问题补全】模块，来对用户当前的问题进行补全，从而使得知识库搜索能够搜索到合适的内容。使用补全后效果如下：
+用户在提问“第二点是什么”的时候，只会去知识库里查找“第二点是什么”，压根查不到内容。实际上需要查询的是“QA结构是什么”。因此我们需要引入一个【问题优化】模块，来对用户当前的问题进行补全，从而使得知识库搜索能够搜索到合适的内容。使用补全后效果如下：

 ![](/imgs/coreferenceResolution3.jpg)

--- a/docSite/content/docs/development/configuration.md
+++ b/docSite/content/docs/development/configuration.md
@@ -13,163 +13,7 @@ weight: 708

 这个配置文件中包含了系统级参数、AI 对话的模型、function 模型等……

-## 4.6.8 以前版本完整配置参数
-
-**使用时，请务必去除注释！**
-
-以下配置适用于V4.6.6-alpha版本以后
-
-```json
-{
-  "systemEnv": {
-    "vectorMaxProcess": 15, // 向量生成最大进程，结合数据库性能和 key 来设置
-    "qaMaxProcess": 15,  // QA 生成最大进程，结合数据库性能和 key 来设置
-    "pgHNSWEfSearch": 100  // pg vector 索引参数，越大精度高但速度慢
-  },
-  "chatModels": [ // 对话模型
-    {
-      "model": "gpt-3.5-turbo-1106",
-      "name": "GPT35-1106",
-      "inputPrice": 0, // 输入价格。 xx元/1k tokens
-      "outputPrice": 0, // 输出价格。 xx元/1k tokens
-      "maxContext": 16000, // 最大上下文长度
-      "maxResponse": 4000, // 最大回复长度
-      "quoteMaxToken": 2000, // 最大引用内容长度
-      "maxTemperature": 1.2, // 最大温度值
-      "censor": false, // 是否开启敏感词过滤(商业版)
-      "vision": false, // 支持图片输入
-      "defaultSystemChatPrompt": ""
-    },
-    {
-      "model": "gpt-3.5-turbo-16k",
-      "name": "GPT35-16k",
-      "maxContext": 16000,
-      "maxResponse": 16000,
-      "inputPrice": 0,
-      "outputPrice": 0,
-      "quoteMaxToken": 8000,
-      "maxTemperature": 1.2,
-      "censor": false,
-      "vision": false,
-      "defaultSystemChatPrompt": ""
-    },
-    {
-      "model": "gpt-4",
-      "name": "GPT4-8k",
-      "maxContext": 8000,
-      "maxResponse": 8000,
-      "inputPrice": 0,
-      "outputPrice": 0,
-      "quoteMaxToken": 4000,
-      "maxTemperature": 1.2,
-      "censor": false,
-      "vision": false,
-      "defaultSystemChatPrompt": ""
-    },
-    {
-      "model": "gpt-4-vision-preview",
-      "name": "GPT4-Vision",
-      "maxContext": 128000,
-      "maxResponse": 4000,
-      "inputPrice": 0,
-      "outputPrice": 0,
-      "quoteMaxToken": 100000,
-      "maxTemperature": 1.2,
-      "censor": false,
-      "vision": true,
-      "defaultSystemChatPrompt": ""
-    }
-  ],
-  "qaModels": [ // QA 生成模型
-    {
-      "model": "gpt-3.5-turbo-16k",
-      "name": "GPT35-16k",
-      "maxContext": 16000,
-      "maxResponse": 16000,
-      "inputPrice": 0,
-      "outputPrice": 0
-    }
-  ],
-  "cqModels": [ // 问题分类模型
-    {
-      "model": "gpt-3.5-turbo-1106",
-      "name": "GPT35-1106",
-      "maxContext": 16000,
-      "maxResponse": 4000,
-      "inputPrice": 0,
-      "outputPrice": 0,
-      "toolChoice": true, // 是否支持openai的 toolChoice， 不支持的模型需要设置为 false，会走提示词生成
-      "functionPrompt": ""
-    },
-    {
-      "model": "gpt-4",
-      "name": "GPT4-8k",
-      "maxContext": 8000,
-      "maxResponse": 8000,
-      "inputPrice": 0,
-      "outputPrice": 0,
-      "toolChoice": true,
-      "functionPrompt": ""
-    }
-  ],
-  "extractModels": [ // 内容提取模型
-    {
-      "model": "gpt-3.5-turbo-1106",
-      "name": "GPT35-1106",
-      "maxContext": 16000,
-      "maxResponse": 4000,
-      "inputPrice": 0,
-      "outputPrice": 0,
-      "toolChoice": true,
-      "functionPrompt": ""
-    }
-  ],
-  "qgModels": [ // 生成下一步指引
-    {
-      "model": "gpt-3.5-turbo-1106",
-      "name": "GPT35-1106",
-      "maxContext": 1600,
-      "maxResponse": 4000,
-      "inputPrice": 0,
-      "outputPrice": 0
-    }
-  ],
-  "vectorModels": [ // 向量模型
-    {
-      "model": "text-embedding-ada-002",
-      "name": "Embedding-2",
-      "inputPrice": 0,
-      "defaultToken": 700,
-      "maxToken": 3000
-    }
-  ],
-  "reRankModels": [], // 重排模型,暂时填空数组
-  "audioSpeechModels": [
-    {
-      "model": "tts-1",
-      "name": "OpenAI TTS1",
-      "inputPrice": 0,
-      "baseUrl": "",
-      "key": "",
-      "voices": [
-        { "label": "Alloy", "value": "alloy", "bufferId": "openai-Alloy" },
-        { "label": "Echo", "value": "echo", "bufferId": "openai-Echo" },
-        { "label": "Fable", "value": "fable", "bufferId": "openai-Fable" },
-        { "label": "Onyx", "value": "onyx", "bufferId": "openai-Onyx" },
-        { "label": "Nova", "value": "nova", "bufferId": "openai-Nova" },
-        { "label": "Shimmer", "value": "shimmer", "bufferId": "openai-Shimmer" }
-      ]
-    }
-  ],
-  "whisperModel": {
-    "model": "whisper-1",
-    "name": "Whisper1",
-    "inputPrice": 0
-  }
-}
-```
-
-## 4.6.8 新配置文件
+## 4.6.8+ 版本新配置文件

 llm模型全部合并

@@ -189,11 +33,10 @@ llm模型全部合并
      "maxResponse": 4000, // 最大回复
      "quoteMaxToken": 13000, // 最大引用内容
      "maxTemperature": 1.2, // 最大温度
-      "inputPrice": 0, 
-      "outputPrice": 0,
+      "charsPointsPrice": 0, 
      "censor": false,
      "vision": false, // 是否支持图片输入
-      "datasetProcess": false, // 是否设置为知识库处理模型
+      "datasetProcess": false, // 是否设置为知识库处理模型（QA），务必保证至少有一个为true，否则知识库会报错
      "toolChoice": true, // 是否支持工具选择
      "functionCall": false, // 是否支持函数调用
      "customCQPrompt": "", // 自定义文本分类提示词（不支持工具和函数调用的模型
@@ -208,8 +51,7 @@ llm模型全部合并
      "maxResponse": 16000,
      "quoteMaxToken": 13000,
      "maxTemperature": 1.2,
-      "inputPrice": 0,
-      "outputPrice": 0,
+      "charsPointsPrice": 0,
      "censor": false,
      "vision": false,
      "datasetProcess": true,
@@ -227,8 +69,7 @@ llm模型全部合并
      "maxResponse": 4000,
      "quoteMaxToken": 100000,
      "maxTemperature": 1.2,
-      "inputPrice": 0,
-      "outputPrice": 0,
+      "charsPointsPrice": 0,
      "censor": false,
      "vision": false,
      "datasetProcess": false,
@@ -246,10 +87,9 @@ llm模型全部合并
      "maxResponse": 4000,
      "quoteMaxToken": 100000,
      "maxTemperature": 1.2,
-      "inputPrice": 0,
-      "outputPrice": 0,
+      "charsPointsPrice": 0,
      "censor": false,
-      "vision": false,
+      "vision": true,
      "datasetProcess": false,
      "toolChoice": true,
      "functionCall": false,
@@ -263,8 +103,7 @@ llm模型全部合并
    {
      "model": "text-embedding-ada-002",
      "name": "Embedding-2",
-      "inputPrice": 0,
-      "outputPrice": 0,
+      "charsPointsPrice": 0,
      "defaultToken": 700,
      "maxToken": 3000,
      "weight": 100,
@@ -276,8 +115,7 @@ llm模型全部合并
    {
      "model": "tts-1",
      "name": "OpenAI TTS1",
-      "inputPrice": 0,
-      "outputPrice": 0,
+      "charsPointsPrice": 0,
      "voices": [
        { "label": "Alloy", "value": "alloy", "bufferId": "openai-Alloy" },
        { "label": "Echo", "value": "echo", "bufferId": "openai-Echo" },
@@ -291,8 +129,7 @@ llm模型全部合并
  "whisperModel": {
    "model": "whisper-1",
    "name": "Whisper1",
-    "inputPrice": 0,
-    "outputPrice": 0
+    "charsPointsPrice": 0
  }
 }
 ```
@@ -313,7 +150,7 @@ llm模型全部合并
        {
            "model": "bge-reranker-base", // 随意
            "name": "检索重排-base", // 随意
-            "inputPrice": 0,
+            "charsPointsPrice": 0,
            "requestUrl": "{{host}}/api/v1/rerank",
            "requestAuth": "安全凭证，已自动补 Bearer"
        }
--- a/docSite/content/docs/development/docker.md
+++ b/docSite/content/docs/development/docker.md
@@ -110,6 +110,7 @@ curl -O https://raw.githubusercontent.com/labring/FastGPT/main/projects/app/data
 cd 项目目录
 # 创建 mongo 密钥
 openssl rand -base64 756 > ./mongodb.key
+# 600不行可以用chmod 999
 chmod 600 ./mongodb.key
 chown 999:root ./mongodb.key
 # 启动容器
--- a/docSite/content/docs/development/one-api.md
+++ b/docSite/content/docs/development/one-api.md
@@ -116,8 +116,7 @@ CHAT_API_KEY=sk-xxxxxx
      "maxResponse": 4000, // 最大回复
      "quoteMaxToken": 13000, // 最大引用内容
      "maxTemperature": 1.2, // 最大温度
-      "inputPrice": 0, 
-      "outputPrice": 0,
+      "charsPointsPrice": 0, 
      "censor": false,
      "vision": false, // 是否支持图片输入
      "datasetProcess": false, // 是否设置为知识库处理模型
--- a/docSite/content/docs/development/openapi/dataset.md
+++ b/docSite/content/docs/development/openapi/dataset.md
@@ -13,12 +13,25 @@ weight: 853



-## 创建训练订单
+## 创建训练订单(4.6.9地址发生改动)

 {{< tabs tabTotal="2" >}}
 {{< tab tabName="请求示例" >}}
 {{< markdownify >}}

+**新例子**
+
+```bash
+curl --location --request POST 'https://api.fastgpt.in/api/support/wallet/usage/createTrainingUsage' \
+--header 'Authorization: Bearer {{apikey}}' \
+--header 'Content-Type: application/json' \
+--data-raw '{
+    "name": "可选，自定义订单名称，例如：文档训练-fastgpt.docx"
+}'
+```
+
+**x例子**
+
 ```bash
 curl --location --request POST 'https://api.fastgpt.in/api/support/wallet/bill/createTrainingBill' \
 --header 'Authorization: Bearer {{apikey}}' \
@@ -154,7 +167,7 @@ curl --location --request GET 'http://localhost:3000/api/core/dataset/list?paren
            "vectorModel": {
                "model": "text-embedding-ada-002",
                "name": "Embedding-2",
-                "inputPrice": 0,
+                "charsPointsPrice": 0,
                "defaultToken": 512,
                "maxToken": 8000,
                "weight": 100
@@ -213,7 +226,7 @@ curl --location --request GET 'http://localhost:3000/api/core/dataset/detail?id=
        "vectorModel": {
            "model": "text-embedding-ada-002",
            "name": "Embedding-2",
-            "inputPrice": 0,
+            "charsPointsPrice": 0,
            "defaultToken": 512,
            "maxToken": 8000,
            "weight": 100
@@ -223,8 +236,7 @@ curl --location --request GET 'http://localhost:3000/api/core/dataset/detail?id=
            "name": "FastAI-16k",
            "maxContext": 16000,
            "maxResponse": 16000,
-            "inputPrice": 0,
-            "outputPrice": 0
+            "charsPointsPrice": 0
        },
        "intro": "",
        "permission": "private",
@@ -800,6 +812,33 @@ curl --location --request DELETE 'http://localhost:3000/api/core/dataset/collect

 ## 数据

+### 数据的结构
+
+**Data结构**
+
+| 字段 | 类型 | 说明 | 必填 |
+| --- | --- | --- | --- |
+| teamId | String | 团队ID | ✅ |
+| tmbId | String | 成员ID | ✅ |
+| datasetId | String | 知识库ID | ✅ |
+| collectionId | String | 集合ID | ✅ |
+| q | String | 主要数据 | ✅ |
+| a | String | 辅助数据 | ✖ |
+| fullTextToken | String | 分词 | ✖ |
+| indexes | Index[] | 向量索引 | ✅ |
+| updateTime | Date | 更新时间 | ✅ |
+| chunkIndex | Number | 分块下表 | ✖ |
+
+**Index结构**
+
+每组数据的自定义索引最多5个
+
+| 字段 | 类型 | 说明 | 必填 |
+| --- | --- | --- | --- |
+| defaultIndex | Boolean | 是否为默认索引 | ✅ |
+| dataId | String | 关联的向量ID | ✅ |
+| text | String | 文本内容 | ✅ |
+
 ### 为集合批量添加添加数据

 注意，每次最多推送 200 组数据。
@@ -825,11 +864,14 @@ curl --location --request POST 'https://api.fastgpt.in/api/core/dataset/data/pus
        {
            "q": "你会什么？",
            "a": "我什么都会",
-            "indexes": [{
-                "defaultIndex": false,
-                "type":"custom",
-                "text":"自定义索引，不使用默认索引"
-            }]
+            "indexes": [
+                {
+                    "text":"自定义索引1"
+                },
+                {
+                    "text":"自定义索引2"
+                }
+            ]
        }
    ]
 }'
@@ -850,7 +892,7 @@ curl --location --request POST 'https://api.fastgpt.in/api/core/dataset/data/pus
 - data：（具体数据）
  - q: 主要数据（必填）
  - a: 辅助数据（选填）
-  - indexes: 自定义索引（选填），不传入则默认使用q和a构建索引。也可以传入
+  - indexes: 自定义索引（选填）。可以不传或者传空数组，默认都会使用q和a组成一个索引。
 {{% /alert %}}

 {{< /markdownify >}}
@@ -866,7 +908,6 @@ curl --location --request POST 'https://api.fastgpt.in/api/core/dataset/data/pus
    "data": {
        "insertLen": 1, // 最终插入成功的数量
        "overToken": [], // 超出 token 的
-       
        "repeat": [], // 重复的数量
        "error": [] // 其他错误
    }
@@ -1050,7 +1091,16 @@ curl --location --request PUT 'http://localhost:3000/api/core/dataset/data/updat
    "id":"65abd4b29d1448617cba61db",
    "q":"测试111",
    "a":"sss",
-    "indexes":[]
+    "indexes":[
+        {
+            "dataId": "xxx",
+            "defaultIndex":false,
+            "text":"自定义索引1"
+        },
+        {
+            "text":"修改后的自定义索引2。（会删除原来的自定义索引2，并插入新的自定义索引2）"
+        }
+    ]
 }'
 ```

@@ -1064,7 +1114,7 @@ curl --location --request PUT 'http://localhost:3000/api/core/dataset/data/updat
 - id: 数据的id
 - q: 主要数据（选填）
 - a: 辅助数据（选填）
- indexes: 自定义索引（选填），类型参考`为集合批量添加添加数据`，建议直接不传。更新q,a后，如果有默认索引，则会直接更新默认索引。
+- indexes: 自定义索引（选填），类型参考`为集合批量添加添加数据`。如果创建时候有自定义索引，
 {{% /alert %}}

 {{< /markdownify >}}
--- a/docSite/content/docs/development/openapi/share.md
+++ b/docSite/content/docs/development/openapi/share.md
@@ -169,8 +169,6 @@ curl --location --request POST '{{host}}/shareAuth/start' \

 响应值与[chat 接口格式相同](/docs/development/openapi/chat/#响应)，仅多了一个`token`。

-可以重点关注`responseData`里的`price`值，`price`与实际价格的倍率为`100000`，即 100000=1元。
-
 ```bash
 curl --location --request POST '{{host}}/shareAuth/finish' \
 --header 'Content-Type: application/json' \
@@ -178,72 +176,117 @@ curl --location --request POST '{{host}}/shareAuth/finish' \
    "token": "{{authToken}}",
    "responseData": [
        {
-            "moduleName": "KB Search",
-            "price": 1.2000000000000002,
-            "model": "Embedding-2",
-            "tokens": 6,
-            "similarity": 0.61,
-            "limit": 3
+            "moduleName": "core.module.template.Dataset search",
+            "moduleType": "datasetSearchNode",
+            "totalPoints": 1.5278,
+            "query": "导演是谁\n《铃芽之旅》的导演是谁？\n这部电影的导演是谁？\n谁是《铃芽之旅》的导演？",
+            "model": "Embedding-2(旧版，不推荐使用)",
+            "charsLength": 1524,
+            "similarity": 0.83,
+            "limit": 400,
+            "searchMode": "embedding",
+            "searchUsingReRank": false,
+            "extensionModel": "FastAI-4k",
+            "extensionResult": "《铃芽之旅》的导演是谁？\n这部电影的导演是谁？\n谁是《铃芽之旅》的导演？",
+            "runningTime": 2.15
        },
        {
-            "moduleName": "AI Chat",
-            "price": 454.5,
+            "moduleName": "AI 对话",
+            "moduleType": "chatNode",
+            "totalPoints": 0.593,
            "model": "FastAI-4k",
-            "tokens": 303,
-            "question": "导演是谁",
-            "answer": "电影《铃芽之旅》的导演是新海诚。",
-            "maxToken": 2050,
+            "charsLength": 593,
+            "query": "导演是谁",
+            "maxToken": 2000,
            "quoteList": [
                {
-                    "dataset_id": "646627f4f7b896cfd8910e38",
-                    "id": "8099",
-                    "q": "本作的主人公是谁？",
-                    "a": "本作的主人公是名叫铃芽的少女。",
-                    "source": "手动修改"
-                },
-                {
-                    "dataset_id": "646627f4f7b896cfd8910e38",
-                    "id": "8686",
-                    "q": "电影《铃芽之旅》男主角是谁？",
-                    "a": "电影《铃芽之旅》男主角是宗像草太，由松村北斗配音。",
-                    "source": ""
-                },
-                {
-                    "dataset_id": "646627f4f7b896cfd8910e38",
-                    "id": "19339",
-                    "q": "电影《铃芽之旅》的导演是谁？22",
+                    "id": "65bb346a53698398479a8854",
+                    "q": "导演是谁？",
                    "a": "电影《铃芽之旅》的导演是新海诚。",
-                    "source": "手动修改"
+                    "chunkIndex": 0,
+                    "datasetId": "65af9b947916ae0e47c834d2",
+                    "collectionId": "65bb345c53698398479a868f",
+                    "sourceName": "dataset - 2024-01-23T151114.198.csv",
+                    "sourceId": "65bb345b53698398479a868d",
+                    "score": [
+                        {
+                            "type": "embedding",
+                            "value": 0.9377183318138123,
+                            "index": 0
+                        },
+                        {
+                            "type": "rrf",
+                            "value": 0.06557377049180328,
+                            "index": 0
+                        }
+                    ]
                }
            ],
-            "completeMessages": [
-                {
-                    "obj": "System",
-                    "value": "下面是知识库内容:\n1. [本作的主人公是谁？\n本作的主人公是名叫铃芽的少女。]\n2. [电影《铃芽之旅》男主角是谁？\n电影《铃芽之旅》男主角是宗像草太，由松村北斗配音。]\n3. [电影《铃芽之旅》的导演是谁？22\n电影《铃芽之旅》的导演是新海诚。]\n"
-                },
-                {
-                    "obj": "System",
-                    "value": "1.请记住，你的身份是百度的下一代知识增强语言模型，能够完全根据知识库提供的内容回答问题。\n\n2. 你忘记了关于电影《铃芽之旅》以外的内容。"
-                },
-                {
-                    "obj": "System",
-                    "value": "你仅回答关于电影《玲芽之旅》的问题，其余问题直接回复: 我不清楚。"
-                },
+            "historyPreview": [
                {
                    "obj": "Human",
-                    "value": "导演是谁"
+                    "value": "使用 <Data></Data> 标记中的内容作为你的知识:\n\n<Data>\n导演是谁？\n电影《铃芽之旅》的导演是新海诚。\n------\n电影《铃芽之旅》的编剧是谁？22\n新海诚是本片的编剧。\n------\n电影《铃芽之旅》的女主角是谁？\n电影的女主角是铃芽。\n------\n电影《铃芽之旅》的制作团队中有哪位著名人士？2\n川村元气是本片的制作团队成员之一。\n------\n你是谁？\n我是电影《铃芽之旅》助手\n------\n电影《铃芽之旅》男主角是谁？\n电影《铃芽之旅》男主角是宗像草太，由松村北斗配音。\n------\n电影《铃芽之旅》的作者新海诚写了一本小说，叫什么名字？\n小说名字叫《铃芽之旅》。\n------\n电影《铃芽之旅》的女主角是谁？\n电影《铃芽之旅》的女主角是岩户铃芽，由原菜乃华配音。\n------\n电影《铃芽之旅》的故事背景是什么？\n日本\n------\n谁担任电影《铃芽之旅》中岩户环的配音？\n深津绘里担任电影《铃芽之旅》中岩户环的配音。\n</Data>\n\n回答要求：\n- 如果你不清楚答案，你需要澄清。\n- 避免提及你是从 <Data></Data> 获取的知识。\n- 保持答案与 <Data></Data> 中描述的一致。\n- 使用 Markdown 语法优化回答格式。\n- 使用与问题相同的语言回答。\n\n问题:\"\"\"导演是谁\"\"\""
                },
                {
                    "obj": "AI",
                    "value": "电影《铃芽之旅》的导演是新海诚。"
                }
-            ]
+            ],
+            "contextTotalLen": 2,
+            "runningTime": 1.32
        }
    ]
+        
+    
 }'
 ```

+**responseData 完整字段说明：**

+```ts
+type ResponseType = {
+    moduleType: `${FlowNodeTypeEnum}`; // 模块类型
+    moduleName: string; // 模块名
+    moduleLogo?: string; // logo
+    runningTime?: number; // 运行时间
+    query?: string; // 用户问题/检索词
+    textOutput?: string; // 文本输出
+
+    charsLength?: number; // 上下文总字数
+    model?: string; // 使用到的模型
+    contextTotalLen?: number; // 上下文总长度
+    totalPoints?: number; // 总消耗AI积分
+
+    temperature?: number; // 温度
+    maxToken?: number; // 模型的最大token
+    quoteList?: SearchDataResponseItemType[]; // 引用列表
+    historyPreview?: ChatItemType[]; // 上下文预览（历史记录会被裁剪）
+
+    similarity?: number; // 最低相关度
+    limit?: number; // 引用上限token
+    searchMode?: `${DatasetSearchModeEnum}`; // 搜索模式
+    searchUsingReRank?: boolean; // 是否使用rerank
+    extensionModel?: string; // 问题扩展模型
+    extensionResult?: string; // 问题扩展结果
+    extensionCharsLength?: number; // 问题扩展总字符长度
+
+    cqList?: ClassifyQuestionAgentItemType[]; // 分类问题列表
+    cqResult?: string; // 分类问题结果
+
+    extractDescription?: string; // 内容提取描述
+    extractResult?: Record<string, any>; // 内容提取结果
+
+    params?: Record<string, any>; // HTTP模块params
+    body?: Record<string, any>;  // HTTP模块body
+    headers?: Record<string, any>; // HTTP模块headers
+    httpResult?: Record<string, any>; // HTTP模块结果
+
+    pluginOutput?: Record<string, any>; // 插件输出
+    pluginDetail?: ChatHistoryItemResType[]; // 插件详情
+
+    tfSwitchResult?: boolean; // 判断器结果
+}
+```

 ## 实践案例

--- a/docSite/content/docs/development/upgrading/465.md
+++ b/docSite/content/docs/development/upgrading/465.md
@@ -15,13 +15,13 @@ weight: 831

 1. 主要是修改模型的`functionCall`字段，改成`toolChoice`即可。设置为`true`的模型，会默认走 openai 的 tools 模式；未设置或设置为`false`的，会走提示词生成模式。

-问题补全模型与内容提取模型使用同一组配置。
+问题优化模型与内容提取模型使用同一组配置。

 2. 增加 `"ReRankModels": []`

 ## V4.6.5 功能介绍

-1. 新增 - [问题补全模块](/docs/workflow/modules/coreferenceresolution/)
+1. 新增 - [问题优化模块](/docs/workflow/modules/coreferenceresolution/)
 2. 新增 - [文本编辑模块](/docs/workflow/modules/text_editor/)
 3. 新增 - [判断器模块](/docs/workflow/modules/tfswitch/)
 4. 新增 - [自定义反馈模块](/docs/workflow/modules/custom_feedback/)
--- a/docSite/content/docs/development/upgrading/467.md
+++ b/docSite/content/docs/development/upgrading/467.md
@@ -11,7 +11,7 @@ weight: 829

 发起 1 个 HTTP 请求 ({{rootkey}} 替换成环境变量里的 `rootkey`，{{host}} 替换成自己域名)

-1. https://xxxxx/api/admin/initv464
+1. https://xxxxx/api/admin/initv467

 ```bash
 curl --location --request POST 'https://{{host}}/api/admin/initv467' \
--- a/docSite/content/docs/development/upgrading/468.md
+++ b/docSite/content/docs/development/upgrading/468.md
@@ -36,6 +36,7 @@ mongo:
 cd 项目目录
 # 创建 mongo 密钥
 openssl rand -base64 756 > ./mongodb.key
+# 600不行可以用chmod 999
 chmod 600 ./mongodb.key
 chown 999:root ./mongodb.key
 # 重启 Mongo
--- a/docSite/content/docs/development/upgrading/469.md
+++ b/docSite/content/docs/development/upgrading/469.md
@@ -0,0 +1,30 @@
+---
+title: 'V4.6.9（进行中）'
+description: 'FastGPT V4.6.9更新说明'
+icon: 'upgrade'
+draft: false
+toc: true
+weight: 827
+---
+
+## 初始化脚本
+
+从任意终端，发起 1 个 HTTP 请求。其中 {{rootkey}} 替换成环境变量里的 `rootkey`；{{host}} 替换成自己域名
+
+```bash
+curl --location --request POST 'https://{{host}}/api/init/v469' \
+--header 'rootkey: {{rootkey}}' \
+--header 'Content-Type: application/json'
+```
+
+会重置计量表。
+
+
+## V4.6.9 更新说明
+
+1. 新增 - 完善了HTTP模块的变量提示。
+2. 新增 - HTTP模块支持OpenAI单接口导入。
+3. 优化 - 问题补全。增加英文类型。同时可以设置为单独模块，方便复用。
+4. 优化 - 重写了计量模式
+5. 修复 - 标注功能。
+6. 修复 - qa生成线程计数错误。
--- a/docSite/content/docs/workflow/examples/dalle3.md
+++ b/docSite/content/docs/workflow/examples/dalle3.md
@@ -66,7 +66,7 @@ Body:

 Headers:

-`Authorization: sk-xxx`
+`Authorization: Bearer sk-xxx`

 Response:

--- a/docSite/content/docs/workflow/examples/google_search.md
+++ b/docSite/content/docs/workflow/examples/google_search.md
@@ -135,7 +135,7 @@ export default async function (ctx: FunctionContext) {
      },
      {
        "key": "model",
-        "type": "selectExtractModel",
+        "type": "selectLLMModel",
        "valueType": "string",
        "label": "core.module.input.label.LLM",
        "required": true,
@@ -264,7 +264,7 @@ export default async function (ctx: FunctionContext) {
      },
      {
        "key": "model",
-        "type": "selectChatModel",
+        "type": "selectLLMModel",
        "label": "core.module.input.label.aiModel",
        "required": true,
        "valueType": "string",
@@ -635,7 +635,7 @@ export default async function (ctx: FunctionContext) {
      },
      {
        "key": "model",
-        "type": "selectChatModel",
+        "type": "selectLLMModel",
        "label": "core.module.input.label.aiModel",
        "required": true,
        "valueType": "string",
--- a/docSite/content/docs/workflow/examples/lab_appointment.md
+++ b/docSite/content/docs/workflow/examples/lab_appointment.md
@@ -139,7 +139,7 @@ HTTP 模块允许你调用任意 GET/POST 类型的 HTTP 接口，从而实现
      },
      {
        "key": "model",
-        "type": "selectExtractModel",
+        "type": "selectLLMModel",
        "valueType": "string",
        "label": "core.module.input.label.LLM",
        "required": true,
@@ -401,7 +401,7 @@ HTTP 模块允许你调用任意 GET/POST 类型的 HTTP 接口，从而实现
      },
      {
        "key": "model",
-        "type": "selectCQModel",
+        "type": "selectLLMModel",
        "valueType": "string",
        "label": "core.module.input.label.Classify model",
        "required": true,
@@ -614,7 +614,7 @@ HTTP 模块允许你调用任意 GET/POST 类型的 HTTP 接口，从而实现
      },
      {
        "key": "model",
-        "type": "selectChatModel",
+        "type": "selectLLMModel",
        "label": "core.module.input.label.aiModel",
        "required": true,
        "valueType": "string",
@@ -835,7 +835,7 @@ HTTP 模块允许你调用任意 GET/POST 类型的 HTTP 接口，从而实现
      },
      {
        "key": "model",
-        "type": "selectExtractModel",
+        "type": "selectLLMModel",
        "valueType": "string",
        "label": "core.module.input.label.LLM",
        "required": true,
--- a/docSite/content/docs/workflow/modules/coreferenceResolution.md
+++ b/docSite/content/docs/workflow/modules/coreferenceResolution.md
@@ -1,6 +1,6 @@
 ---
-title: "问题补全（已合并到知识库搜索）"
-description: "问题补全模块介绍和使用"
+title: "问题优化（已合并到知识库搜索）"
+description: "问题优化模块介绍和使用"
 icon: "input"
 draft: false
 toc: true
@@ -23,7 +23,7 @@ weight: 364

 ![](/imgs/coreferenceResolution2.jpg)

-用户在提问“第二点是什么”的时候，只会去知识库里查找“第二点是什么”，压根查不到内容。实际上需要查询的是“QA结构是什么”。因此我们需要引入一个【问题补全】模块，来对用户当前的问题进行补全，从而使得知识库搜索能够搜索到合适的内容。使用补全后效果如下：
+用户在提问“第二点是什么”的时候，只会去知识库里查找“第二点是什么”，压根查不到内容。实际上需要查询的是“QA结构是什么”。因此我们需要引入一个【问题优化】模块，来对用户当前的问题进行补全，从而使得知识库搜索能够搜索到合适的内容。使用补全后效果如下：

 ![](/imgs/coreferenceResolution3.jpg)

--- a/packages/global/common/error/code/team.ts
+++ b/packages/global/common/error/code/team.ts
@@ -3,11 +3,25 @@ import { ErrType } from '../errorCode';
 /* team: 500000 */
 export enum TeamErrEnum {
  teamOverSize = 'teamOverSize',
-  unAuthTeam = 'unAuthTeam'
+  unAuthTeam = 'unAuthTeam',
+  aiPointsNotEnough = 'aiPointsNotEnough',
+  datasetSizeNotEnough = 'datasetSizeNotEnough',
+  datasetAmountNotEnough = 'datasetAmountNotEnough',
+  appAmountNotEnough = 'appAmountNotEnough',
+  pluginAmountNotEnough = 'pluginAmountNotEnough',
+  websiteSyncNotEnough = 'websiteSyncNotEnough',
+  reRankNotEnough = 'reRankNotEnough'
 }
 const teamErr = [
  { statusText: TeamErrEnum.teamOverSize, message: 'error.team.overSize' },
-  { statusText: TeamErrEnum.unAuthTeam, message: '无权操作该团队' }
+  { statusText: TeamErrEnum.unAuthTeam, message: '无权操作该团队' },
+  { statusText: TeamErrEnum.aiPointsNotEnough, message: 'AI积分已用完~' },
+  { statusText: TeamErrEnum.datasetSizeNotEnough, message: '知识库容量不足，请先扩容~' },
+  { statusText: TeamErrEnum.datasetAmountNotEnough, message: '知识库数量已达上限~' },
+  { statusText: TeamErrEnum.appAmountNotEnough, message: '应用数量已达上限~' },
+  { statusText: TeamErrEnum.pluginAmountNotEnough, message: '插件数量已达上限~' },
+  { statusText: TeamErrEnum.websiteSyncNotEnough, message: '无权使用Web站点同步~' },
+  { statusText: TeamErrEnum.reRankNotEnough, message: '无权使用检索重排~' }
 ];
 export default teamErr.reduce((acc, cur, index) => {
  return {
--- a/packages/global/common/error/utils.ts
+++ b/packages/global/common/error/utils.ts
@@ -1,7 +1,7 @@
-import { replaceSensitiveLink } from '../string/tools';
+import { replaceSensitiveText } from '../string/tools';

 export const getErrText = (err: any, def = '') => {
  const msg: string = typeof err === 'string' ? err : err?.message || def || '';
  msg && console.log('error =>', msg);
-  return replaceSensitiveLink(msg);
+  return replaceSensitiveText(msg);
 };
--- a/packages/global/common/math/tools.ts
+++ b/packages/global/common/math/tools.ts
@@ -0,0 +1,4 @@
+export const formatNumber = (num: number, digit = 1e4) => Math.round(num * digit) / digit;
+
+export const formatNumber2Million = (num: number) => Math.round(num / 1000000);
+export const formatNumber2Thousand = (num: number) => Math.round(num / 1000);
--- a/packages/global/common/string/time.ts
+++ b/packages/global/common/string/time.ts
@@ -2,3 +2,4 @@ import dayjs from 'dayjs';

 export const formatTime2YMDHM = (time?: Date) =>
  time ? dayjs(time).format('YYYY-MM-DD HH:mm') : '';
+export const formatTime2YMD = (time?: Date) => (time ? dayjs(time).format('YYYY-MM-DD') : '');
--- a/packages/global/common/string/tools.ts
+++ b/packages/global/common/string/tools.ts
@@ -38,10 +38,14 @@ export function replaceVariable(text: string, obj: Record<string, string | numbe
  return text || '';
 }

-/* replace sensitive link */
-export const replaceSensitiveLink = (text: string) => {
-  const urlRegex = /(?<=https?:\/\/)[^\s]+/g;
-  return text.replace(urlRegex, 'xxx');
+/* replace sensitive text */
+export const replaceSensitiveText = (text: string) => {
+  // 1. http link
+  text = text.replace(/(?<=https?:\/\/)[^\s]+/g, 'xxx');
+  // 2. nx-xxx 全部替换成xxx
+  text = text.replace(/ns-[\w-]+/g, 'xxx');
+
+  return text;
 };

 export const getNanoid = (size = 12) => {
--- a/packages/global/common/system/types/index.d.ts
+++ b/packages/global/common/system/types/index.d.ts
@@ -30,6 +30,7 @@ export type FastGPTFeConfigsType = {
  show_pay?: boolean;
  show_openai_account?: boolean;
  show_promotion?: boolean;
+  show_team_chat?: boolean;
  hide_app_flow?: boolean;
  concatMd?: string;
  docUrl?: string;
--- a/packages/global/core/ai/model.d.ts
+++ b/packages/global/core/ai/model.d.ts
@@ -6,8 +6,7 @@ export type LLMModelItemType = {
  quoteMaxToken: number;
  maxTemperature: number;

-  inputPrice: number;
-  outputPrice: number;
+  charsPointsPrice: number; // 1k chars=n points

  censor?: boolean;
  vision?: boolean;
@@ -27,8 +26,7 @@ export type VectorModelItemType = {
  model: string;
  name: string;
  defaultToken: number;
-  inputPrice: number;
-  outputPrice: number;
+  charsPointsPrice: number;
  maxToken: number;
  weight: number;
  hidden?: boolean;
@@ -38,8 +36,7 @@ export type VectorModelItemType = {
 export type ReRankModelItemType = {
  model: string;
  name: string;
-  inputPrice: number;
-  outputPrice?: number;
+  charsPointsPrice: number;
  requestUrl?: string;
  requestAuth?: string;
 };
@@ -47,14 +44,12 @@ export type ReRankModelItemType = {
 export type AudioSpeechModelType = {
  model: string;
  name: string;
-  inputPrice: number;
-  outputPrice?: number;
+  charsPointsPrice: number;
  voices: { label: string; value: string; bufferId: string }[];
 };

 export type WhisperModelType = {
  model: string;
  name: string;
-  inputPrice: number;
-  outputPrice?: number;
+  charsPointsPrice: number; // 60s = n points
 };
--- a/packages/global/core/ai/model.ts
+++ b/packages/global/core/ai/model.ts
@@ -2,14 +2,13 @@ import type { LLMModelItemType, VectorModelItemType } from './model.d';

 export const defaultQAModels: LLMModelItemType[] = [
  {
-    model: 'gpt-3.5-turbo-16k',
-    name: 'gpt-3.5-turbo-16k',
+    model: 'gpt-3.5-turbo',
+    name: 'gpt-3.5-turbo',
    maxContext: 16000,
    maxResponse: 16000,
    quoteMaxToken: 13000,
    maxTemperature: 1.2,
-    inputPrice: 0,
-    outputPrice: 0,
+    charsPointsPrice: 0,
    censor: false,
    vision: false,
    datasetProcess: true,
@@ -26,8 +25,7 @@ export const defaultVectorModels: VectorModelItemType[] = [
  {
    model: 'text-embedding-ada-002',
    name: 'Embedding-2',
-    inputPrice: 0,
-    outputPrice: 0,
+    charsPointsPrice: 0,
    defaultToken: 500,
    maxToken: 3000,
    weight: 100
--- a/packages/global/core/app/api.d.ts
+++ b/packages/global/core/app/api.d.ts
@@ -17,6 +17,7 @@ export interface AppUpdateParams {
  intro?: string;
  modules?: AppSchema['modules'];
  permission?: AppSchema['permission'];
+  teamTags?: AppSchema['teamTags'];
 }

 export type FormatForm2ModulesProps = {
--- a/packages/global/core/app/type.d.ts
+++ b/packages/global/core/app/type.d.ts
@@ -5,7 +5,7 @@ import type { AIChatModuleProps, DatasetModuleProps } from '../module/node/type.
 import { VariableInputEnum } from '../module/constants';
 import { SelectedDatasetType } from '../module/api';
 import { DatasetSearchModeEnum } from '../dataset/constants';
-
+import { TeamTagsSchema as TeamTagsSchemaType } from '@fastgpt/global/support/user/team/type.d';
 export interface AppSchema {
  _id: string;
  userId: string;
@@ -20,6 +20,7 @@ export interface AppSchema {
  modules: ModuleItemType[];
  permission: `${PermissionTypeEnum}`;
  inited?: boolean;
+  teamTags: [string];
 }

 export type AppListItemType = {
--- a/packages/global/core/chat/constants.ts
+++ b/packages/global/core/chat/constants.ts
@@ -27,7 +27,8 @@ export enum ChatSourceEnum {
  test = 'test',
  online = 'online',
  share = 'share',
-  api = 'api'
+  api = 'api',
+  team = 'team'
 }
 export const ChatSourceMap = {
  [ChatSourceEnum.test]: {
@@ -41,6 +42,9 @@ export const ChatSourceMap = {
  },
  [ChatSourceEnum.api]: {
    name: 'core.chat.logs.api'
+  },
+  [ChatSourceEnum.team]: {
+    name: 'core.chat.logs.team'
  }
 };

--- a/packages/global/core/chat/type.d.ts
+++ b/packages/global/core/chat/type.d.ts
@@ -4,6 +4,7 @@ import { ChatRoleEnum, ChatSourceEnum, ChatStatusEnum } from './constants';
 import { FlowNodeTypeEnum } from '../module/node/constant';
 import { ModuleOutputKeyEnum } from '../module/constants';
 import { AppSchema } from '../app/type';
+import type { AppSchema as AppType } from '@fastgpt/global/core/app/type.d';
 import { DatasetSearchModeEnum } from '../dataset/constants';

 export type ChatSchema = {
@@ -25,6 +26,23 @@ export type ChatSchema = {
  metadata?: Record<string, any>;
 };

+export type teamInfoType = {
+  avatar: string;
+  balance: number;
+  createTime: string;
+  maxSize: number;
+  name: string;
+  ownerId: string;
+  tagsUrl: string;
+  _id: string;
+};
+
+export type chatAppListSchema = {
+  apps: AppType[];
+  teamInfo: teamInfoSchema;
+  uid?: string;
+};
+
 export type ChatWithAppSchema = Omit<ChatSchema, 'appId'> & {
  appId: AppSchema;
 };
@@ -88,15 +106,15 @@ export type ChatHistoryItemType = HistoryItemType & {
 export type moduleDispatchResType = {
  // common
  moduleLogo?: string;
-  price?: number;
  runningTime?: number;
-  inputTokens?: number;
-  outputTokens?: number;
+  query?: string;
+  textOutput?: string;
+
+  // bill
  charsLength?: number;
  model?: string;
-  query?: string;
  contextTotalLen?: number;
-  textOutput?: string;
+  totalPoints?: number;

  // chat
  temperature?: number;
@@ -111,6 +129,7 @@ export type moduleDispatchResType = {
  searchUsingReRank?: boolean;
  extensionModel?: string;
  extensionResult?: string;
+  extensionCharsLength?: number;

  // cq
  cqList?: ClassifyQuestionAgentItemType[];
--- a/packages/global/core/dataset/constants.ts
+++ b/packages/global/core/dataset/constants.ts
@@ -71,30 +71,6 @@ export const DatasetCollectionSyncResultMap = {
 };

 /* ------------ data -------------- */
-export enum DatasetDataIndexTypeEnum {
-  chunk = 'chunk',
-  qa = 'qa',
-  summary = 'summary',
-  hypothetical = 'hypothetical',
-  custom = 'custom'
-}
-export const DatasetDataIndexTypeMap = {
-  [DatasetDataIndexTypeEnum.chunk]: {
-    name: 'dataset.data.indexes.chunk'
-  },
-  [DatasetDataIndexTypeEnum.summary]: {
-    name: 'dataset.data.indexes.summary'
-  },
-  [DatasetDataIndexTypeEnum.hypothetical]: {
-    name: 'dataset.data.indexes.hypothetical'
-  },
-  [DatasetDataIndexTypeEnum.qa]: {
-    name: 'dataset.data.indexes.qa'
-  },
-  [DatasetDataIndexTypeEnum.custom]: {
-    name: 'dataset.data.indexes.custom'
-  }
-};

 /* ------------ training -------------- */
 export enum TrainingModeEnum {
--- a/packages/global/core/dataset/type.d.ts
+++ b/packages/global/core/dataset/type.d.ts
@@ -3,7 +3,6 @@ import { PermissionTypeEnum } from '../../support/permission/constant';
 import { PushDatasetDataChunkProps } from './api';
 import {
  DatasetCollectionTypeEnum,
-  DatasetDataIndexTypeEnum,
  DatasetStatusEnum,
  DatasetTypeEnum,
  SearchScoreTypeEnum,
@@ -64,7 +63,6 @@ export type DatasetCollectionSchemaType = {
 export type DatasetDataIndexItemType = {
  defaultIndex: boolean;
  dataId: string; // pg data id
-  type: `${DatasetDataIndexTypeEnum}`;
  text: string;
 };
 export type DatasetDataSchemaType = {
@@ -142,6 +140,7 @@ export type DatasetCollectionItemType = CollectionWithDatasetType & {
 /* ================= data ===================== */
 export type DatasetDataItemType = {
  id: string;
+  teamId: string;
  datasetId: string;
  collectionId: string;
  sourceName: string;
@@ -173,7 +172,7 @@ export type DatasetFileSchema = {
 /* ============= search =============== */
 export type SearchDataResponseItemType = Omit<
  DatasetDataItemType,
-  'indexes' | 'isOwner' | 'canWrite'
+  'teamId' | 'indexes' | 'isOwner' | 'canWrite'
 > & {
  score: { type: `${SearchScoreTypeEnum}`; value: number; index: number }[];
  // score: number;
--- a/packages/global/core/dataset/utils.ts
+++ b/packages/global/core/dataset/utils.ts
@@ -1,4 +1,4 @@
-import { TrainingModeEnum, DatasetCollectionTypeEnum, DatasetDataIndexTypeEnum } from './constants';
+import { TrainingModeEnum, DatasetCollectionTypeEnum } from './constants';
 import { getFileIcon } from '../../common/file/icon';
 import { strIsLink } from '../../common/string/tools';

@@ -41,7 +41,6 @@ export function getDefaultIndex(props?: { q?: string; a?: string; dataId?: strin
  const qaStr = `${q}\n${a}`.trim();
  return {
    defaultIndex: true,
-    type: a ? DatasetDataIndexTypeEnum.qa : DatasetDataIndexTypeEnum.chunk,
    text: a ? qaStr : q,
    dataId
  };
--- a/packages/global/core/module/constants.ts
+++ b/packages/global/core/module/constants.ts
@@ -89,9 +89,10 @@ export enum ModuleInputKeyEnum {

 export enum ModuleOutputKeyEnum {
  // common
+  responseData = 'responseData',
+  moduleDispatchBills = 'moduleDispatchBills',
  userChatInput = 'userChatInput',
  finish = 'finish',
-  responseData = 'responseData',
  history = 'history',
  answerText = 'answerText', //  answer module text key
  success = 'success',
--- a/packages/global/core/module/node/constant.ts
+++ b/packages/global/core/module/node/constant.ts
@@ -20,9 +20,7 @@ export enum FlowNodeInputTypeEnum {
  aiSettings = 'aiSettings',

  // ai model select
-  selectChatModel = 'selectChatModel',
-  selectCQModel = 'selectCQModel',
-  selectExtractModel = 'selectExtractModel',
+  selectLLMModel = 'selectLLMModel',

  // dataset special input
  selectDataset = 'selectDataset',
@@ -58,7 +56,7 @@ export enum FlowNodeTypeEnum {
  pluginModule = 'pluginModule',
  pluginInput = 'pluginInput',
  pluginOutput = 'pluginOutput',
-  cfr = 'cfr'
+  queryExtension = 'cfr'

  // abandon
 }
--- a/packages/global/core/module/template/system/aiChat.ts
+++ b/packages/global/core/module/template/system/aiChat.ts
@@ -31,7 +31,7 @@ export const AiChatModule: FlowModuleTemplateType = {
    Input_Template_Switch,
    {
      key: ModuleInputKeyEnum.aiModel,
-      type: FlowNodeInputTypeEnum.selectChatModel,
+      type: FlowNodeInputTypeEnum.selectLLMModel,
      label: 'core.module.input.label.aiModel',
      required: true,
      valueType: ModuleIOValueTypeEnum.string,
--- a/packages/global/core/module/template/system/classifyQuestion.ts
+++ b/packages/global/core/module/template/system/classifyQuestion.ts
@@ -24,7 +24,7 @@ export const ClassifyQuestionModule: FlowModuleTemplateType = {
    Input_Template_Switch,
    {
      key: ModuleInputKeyEnum.aiModel,
-      type: FlowNodeInputTypeEnum.selectCQModel,
+      type: FlowNodeInputTypeEnum.selectLLMModel,
      valueType: ModuleIOValueTypeEnum.string,
      label: 'core.module.input.label.Classify model',
      required: true,
--- a/packages/global/core/module/template/system/contextExtract.ts
+++ b/packages/global/core/module/template/system/contextExtract.ts
@@ -24,7 +24,7 @@ export const ContextExtractModule: FlowModuleTemplateType = {
    Input_Template_Switch,
    {
      key: ModuleInputKeyEnum.aiModel,
-      type: FlowNodeInputTypeEnum.selectExtractModel,
+      type: FlowNodeInputTypeEnum.selectLLMModel,
      valueType: ModuleIOValueTypeEnum.string,
      label: 'core.module.input.label.LLM',
      required: true,
--- a/packages/global/core/module/template/system/http468.ts
+++ b/packages/global/core/module/template/system/http468.ts
@@ -85,7 +85,6 @@ export const HttpModule468: FlowModuleTemplateType = {
      ...Input_Template_AddInputParam,
      editField: {
        key: true,
-        name: true,
        description: true,
        required: true,
        dataType: true
@@ -106,7 +105,6 @@ export const HttpModule468: FlowModuleTemplateType = {
      ...Output_Template_AddOutput,
      editField: {
        key: true,
-        name: true,
        description: true,
        dataType: true
      },
--- a/packages/global/core/module/template/system/coreferenceResolution.ts
+++ b/packages/global/core/module/template/system/coreferenceResolution.ts
@@ -3,7 +3,7 @@ import {
  FlowNodeOutputTypeEnum,
  FlowNodeTypeEnum
 } from '../../node/constant';
-import { FlowModuleTemplateType } from '../../type.d';
+import { FlowModuleTemplateType } from '../../type';
 import {
  ModuleIOValueTypeEnum,
  ModuleInputKeyEnum,
@@ -17,19 +17,19 @@ import {
 } from '../input';
 import { Output_Template_UserChatInput } from '../output';

-export const AiCFR: FlowModuleTemplateType = {
+export const AiQueryExtension: FlowModuleTemplateType = {
  id: FlowNodeTypeEnum.chatNode,
  templateType: ModuleTemplateTypeEnum.other,
-  flowType: FlowNodeTypeEnum.cfr,
+  flowType: FlowNodeTypeEnum.queryExtension,
  avatar: '/imgs/module/cfr.svg',
  name: 'core.module.template.Query extension',
-  intro: '该模块已合并到知识库搜索参数中，无需单独使用。模块将于2024/3/31弃用，请尽快修改。',
+  intro: 'core.module.template.Query extension intro',
  showStatus: true,
  inputs: [
    Input_Template_Switch,
    {
      key: ModuleInputKeyEnum.aiModel,
-      type: FlowNodeInputTypeEnum.selectExtractModel,
+      type: FlowNodeInputTypeEnum.selectLLMModel,
      label: 'core.module.input.label.aiModel',
      required: true,
      valueType: ModuleIOValueTypeEnum.string,
@@ -39,7 +39,7 @@ export const AiCFR: FlowModuleTemplateType = {
    {
      key: ModuleInputKeyEnum.aiSystemPrompt,
      type: FlowNodeInputTypeEnum.textarea,
-      label: 'core.module.input.label.Background',
+      label: 'core.app.edit.Query extension background prompt',
      max: 300,
      valueType: ModuleIOValueTypeEnum.string,
      description: 'core.app.edit.Query extension background tip',
@@ -54,7 +54,8 @@ export const AiCFR: FlowModuleTemplateType = {
    Output_Template_UserChatInput,
    {
      key: ModuleOutputKeyEnum.text,
-      label: 'core.module.output.label.cfr result',
+      label: 'core.module.output.label.query extension result',
+      description: 'core.module.output.description.query extension result',
      valueType: ModuleIOValueTypeEnum.string,
      type: FlowNodeOutputTypeEnum.source,
      targets: []
--- a/packages/global/core/module/type.d.ts
+++ b/packages/global/core/module/type.d.ts
@@ -1,6 +1,14 @@
 import { FlowNodeTypeEnum } from './node/constant';
-import { ModuleIOValueTypeEnum, ModuleTemplateTypeEnum, VariableInputEnum } from './constants';
+import {
+  ModuleIOValueTypeEnum,
+  ModuleOutputKeyEnum,
+  ModuleTemplateTypeEnum,
+  VariableInputEnum
+} from './constants';
 import { FlowNodeInputItemType, FlowNodeOutputItemType } from './node/type';
+import { UserModelSchema } from 'support/user/type';
+import { moduleDispatchResType } from '..//chat/type';
+import { ChatModuleBillType } from '../../support/wallet/bill/type';

 export type FlowModuleTemplateType = {
  id: string; // module id, unique
@@ -105,7 +113,7 @@ export type ChatDispatchProps = {
  mode: 'test' | 'chat';
  teamId: string;
  tmbId: string;
-  user: UserType;
+  user: UserModelSchema;
  appId: string;
  chatId?: string;
  responseChatItemId?: string;
@@ -116,7 +124,10 @@ export type ChatDispatchProps = {
 };

 export type ModuleDispatchProps<T> = ChatDispatchProps & {
-  outputs: RunningModuleItemType['outputs'];
-  inputs: RunningModuleItemType['inputs'];
+  module: RunningModuleItemType;
  params: T;
 };
+export type ModuleDispatchResponse<T> = T & {
+  [ModuleOutputKeyEnum.responseData]?: moduleDispatchResType;
+  [ModuleOutputKeyEnum.moduleDispatchBills]?: ChatModuleBillType[];
+};
--- a/packages/global/support/openapi/type.d.ts
+++ b/packages/global/support/openapi/type.d.ts
@@ -1,6 +1,5 @@
 export type OpenApiSchema = {
  _id: string;
-  userId: string;
  teamId: string;
  tmbId: string;
  createTime: Date;
@@ -8,9 +7,9 @@ export type OpenApiSchema = {
  apiKey: string;
  appId?: string;
  name: string;
-  usage: number;
+  usagePoints: number;
  limit?: {
    expiredTime?: Date;
-    credit?: number;
+    maxUsagePoints: number;
  };
 };
--- a/packages/global/support/outLink/api.d.ts
+++ b/packages/global/support/outLink/api.d.ts
@@ -1,5 +1,5 @@
 import type { HistoryItemType, ChatSiteItemType } from '../../core/chat/type.d';
-import { OutLinkSchema } from '@fastgpt/global/support/outLink/type';
+import { OutLinkSchema } from './type.d';

 export type AuthOutLinkInitProps = {
  outLinkUid: string;
--- a/packages/global/support/outLink/type.d.ts
+++ b/packages/global/support/outLink/type.d.ts
@@ -7,14 +7,14 @@ export type OutLinkSchema = {
  tmbId: string;
  appId: string;
  name: string;
-  total: number;
+  usagePoints: number;
  lastTime: Date;
  type: `${OutLinkTypeEnum}`;
  responseDetail: boolean;
  limit?: {
    expiredTime?: Date;
    QPM: number;
-    credit: number;
+    maxUsagePoints: number;
    hookUrl?: string;
  };
 };
--- a/packages/global/support/permission/type.d.ts
+++ b/packages/global/support/permission/type.d.ts
@@ -1,7 +1,6 @@
 import { AuthUserTypeEnum } from './constant';

 export type AuthResponseType = {
-  userId: string;
  teamId: string;
  tmbId: string;
  isOwner: boolean;
--- a/packages/global/support/user/team/constant.ts
+++ b/packages/global/support/user/team/constant.ts
@@ -1,5 +1,6 @@
 export const TeamCollectionName = 'teams';
 export const TeamMemberCollectionName = 'team.members';
+export const TeamTagsCollectionName = 'team.tags';

 export enum TeamMemberRoleEnum {
  owner = 'owner',
--- a/packages/global/support/user/team/controller.d.ts
+++ b/packages/global/support/user/team/controller.d.ts
@@ -15,6 +15,7 @@ export type UpdateTeamProps = {
  teamId: string;
  name?: string;
  avatar?: string;
+  tagsUrl?: string;
 };

 /* ------------- member ----------- */
--- a/packages/global/support/user/team/type.d.ts
+++ b/packages/global/support/user/team/type.d.ts
@@ -9,11 +9,23 @@ export type TeamSchema = {
  createTime: Date;
  balance: number;
  maxSize: number;
+  tagsUrl: string;
  limit: {
    lastExportDatasetTime: Date;
    lastWebsiteSyncTime: Date;
  };
 };
+export type tagsType = {
+  label: string,
+  key: string
+}
+export type TeamTagsSchema = {
+  _id: string;
+  label: string;
+  teamId: string;
+  key: string;
+  createTime: Date;
+};

 export type TeamMemberSchema = {
  _id: string;
@@ -26,13 +38,13 @@ export type TeamMemberSchema = {
  defaultTeam: boolean;
 };

-export type TeamMemberWithUserSchema = TeamMemberSchema & {
+export type TeamMemberWithUserSchema = Omit<TeamMemberSchema, 'userId'> & {
  userId: UserModelSchema;
 };
-export type TeamMemberWithTeamSchema = TeamMemberSchema & {
+export type TeamMemberWithTeamSchema = Omit<TeamMemberSchema, 'teamId'> & {
  teamId: TeamSchema;
 };
-export type TeamMemberWithTeamAndUserSchema = TeamMemberWithTeamSchema & {
+export type TeamMemberWithTeamAndUserSchema = Omit<TeamMemberWithTeamSchema, 'userId'> & {
  userId: UserModelSchema;
 };

--- a/packages/global/support/user/type.d.ts
+++ b/packages/global/support/user/type.d.ts
@@ -29,4 +29,5 @@ export type UserType = {
  promotionRate: UserModelSchema['promotionRate'];
  openaiAccount: UserModelSchema['openaiAccount'];
  team: TeamItemType;
+  standardInfo?: standardInfoType;
 };
--- a/packages/global/support/wallet/bill/api.d.ts
+++ b/packages/global/support/wallet/bill/api.d.ts
@@ -1,25 +1,18 @@
-import { BillSourceEnum } from './constants';
-import { BillListItemCountType, BillListItemType } from './type';
-
-export type CreateTrainingBillProps = {
-  name: string;
-  datasetId: string;
-};
-
-export type ConcatBillProps = BillListItemCountType & {
-  teamId: string;
-  tmbId: string;
-  billId?: string;
-  total: number;
-  listIndex?: number;
-};
+import { BillTypeEnum } from './constants';

 export type CreateBillProps = {
-  teamId: string;
-  tmbId: string;
-  appName: string;
-  appId?: string;
-  total: number;
-  source: `${BillSourceEnum}`;
-  list: BillListItemType[];
+  type: `${BillTypeEnum}`;
+
+  // balance
+  balance?: number; // read
+
+  month?: number;
+  // extra dataset size
+  extraDatasetSize?: number; // 1k
+  extraPoints?: number; // 100w
+};
+export type CreateBillResponse = {
+  billId: string;
+  codeUrl: string;
+  readPrice: number;
 };
--- a/packages/global/support/wallet/bill/constants.ts
+++ b/packages/global/support/wallet/bill/constants.ts
@@ -1,34 +1,57 @@
-// model price: xxx/1k tokens
-// ￥1 = 100000.
-export const PRICE_SCALE = 100000;
-
-export enum BillSourceEnum {
-  fastgpt = 'fastgpt',
-  api = 'api',
-  shareLink = 'shareLink',
-  training = 'training',
-
+export enum BillTypeEnum {
+  balance = 'balance',
  standSubPlan = 'standSubPlan',
-  extraDatasetSub = 'extraDatasetSub'
+  extraDatasetSub = 'extraDatasetSub',
+  extraPoints = 'extraPoints'
 }
-
-export const BillSourceMap = {
-  [BillSourceEnum.fastgpt]: {
-    label: '在线使用'
+export const billTypeMap = {
+  [BillTypeEnum.balance]: {
+    label: 'support.wallet.subscription.type.balance'
  },
-  [BillSourceEnum.api]: {
-    label: 'Api'
-  },
-  [BillSourceEnum.shareLink]: {
-    label: '免登录链接'
-  },
-  [BillSourceEnum.training]: {
-    label: 'dataset.Training Name'
-  },
-  [BillSourceEnum.standSubPlan]: {
+  [BillTypeEnum.standSubPlan]: {
    label: 'support.wallet.subscription.type.standard'
  },
-  [BillSourceEnum.extraDatasetSub]: {
+  [BillTypeEnum.extraDatasetSub]: {
    label: 'support.wallet.subscription.type.extraDatasetSize'
+  },
+  [BillTypeEnum.extraPoints]: {
+    label: 'support.wallet.subscription.type.extraPoints'
  }
 };
+
+export enum BillStatusEnum {
+  SUCCESS = 'SUCCESS',
+  REFUND = 'REFUND',
+  NOTPAY = 'NOTPAY',
+  CLOSED = 'CLOSED'
+}
+export const billStatusMap = {
+  [BillStatusEnum.SUCCESS]: {
+    label: 'support.wallet.bill.status.success'
+  },
+  [BillStatusEnum.REFUND]: {
+    label: 'support.wallet.bill.status.refund'
+  },
+  [BillStatusEnum.NOTPAY]: {
+    label: 'support.wallet.bill.status.notpay'
+  },
+  [BillStatusEnum.CLOSED]: {
+    label: 'support.wallet.bill.status.closed'
+  }
+};
+
+export enum BillPayWayEnum {
+  balance = 'balance',
+  wx = 'wx'
+}
+export const billPayWayMap = {
+  [BillPayWayEnum.balance]: {
+    label: 'support.wallet.bill.payWay.balance'
+  },
+  [BillPayWayEnum.wx]: {
+    label: 'support.wallet.bill.payWay.wx'
+  }
+};
+
+export const SUB_DATASET_SIZE_RATE = 1000;
+export const SUB_EXTRA_POINT_RATE = 1000;
--- a/packages/global/support/wallet/bill/tools.ts
+++ b/packages/global/support/wallet/bill/tools.ts
@@ -1,26 +0,0 @@
-/* bill common  */
-import { PRICE_SCALE } from './constants';
-import { BillSourceEnum } from './constants';
-import { AuthUserTypeEnum } from '../../permission/constant';
-
-/**
- * dataset price / PRICE_SCALE = real price
- */
-export const formatStorePrice2Read = (val = 0, multiple = 1) => {
-  return Number(((val / PRICE_SCALE) * multiple).toFixed(10));
-};
-export const formatModelPrice2Read = (val = 0) => {
-  return Number((val / 1000).toFixed(10));
-};
-
-export const getBillSourceByAuthType = ({
-  shareId,
-  authType
-}: {
-  shareId?: string;
-  authType?: `${AuthUserTypeEnum}`;
-}) => {
-  if (shareId) return BillSourceEnum.shareLink;
-  if (authType === AuthUserTypeEnum.apikey) return BillSourceEnum.api;
-  return BillSourceEnum.fastgpt;
-};
--- a/packages/global/support/wallet/bill/type.d.ts
+++ b/packages/global/support/wallet/bill/type.d.ts
@@ -1,35 +1,29 @@
-import { CreateBillProps } from './api';
-import { BillSourceEnum } from './constants';
+import { StandardSubLevelEnum, SubModeEnum, SubTypeEnum } from '../sub/constants';
+import { BillPayWayEnum, BillTypeEnum } from './constants';

-export type BillListItemCountType = {
-  inputTokens?: number;
-  outputTokens?: number;
-  charsLength?: number;
-  duration?: number;
-
-  // sub
-  datasetSize?: number;
-
-  // abandon
-  tokenLen?: number;
-};
-export type BillListItemType = BillListItemCountType & {
-  moduleName: string;
-  amount: number;
-  model?: string;
-};
-
-export type BillSchema = CreateBillProps & {
+export type BillSchemaType = {
  _id: string;
-  time: Date;
+  userId: string;
+  teamId: string;
+  tmbId: string;
+  createTime: Date;
+  orderId: string;
+  status: 'SUCCESS' | 'REFUND' | 'NOTPAY' | 'CLOSED';
+  type: `${BillTypeEnum}`;
+  price: number;
+  metadata: {
+    payWay: `${BillPayWayEnum}`;
+    subMode?: `${SubModeEnum}`;
+    standSubLevel?: `${StandardSubLevelEnum}`;
+    month?: number;
+    datasetSize?: number;
+    extraPoints?: number;
+  };
 };

-export type BillItemType = {
-  id: string;
-  // memberName: string;
-  time: Date;
-  appName: string;
-  source: BillSchema['source'];
-  total: number;
-  list: BillSchema['list'];
+export type ChatModuleBillType = {
+  totalPoints: number;
+  moduleName: string;
+  model?: string;
+  charsLength?: number;
 };
--- a/packages/global/support/wallet/constants.ts
+++ b/packages/global/support/wallet/constants.ts
@@ -0,0 +1,3 @@
+// model price: xxx/1k tokens
+// ￥1 = 100000.
+export const PRICE_SCALE = 100000;
--- a/packages/global/support/wallet/pay/constants.ts
+++ b/packages/global/support/wallet/pay/constants.ts
@@ -1,41 +0,0 @@
-export enum PayTypeEnum {
-  balance = 'balance',
-  subStandard = 'subStandard',
-  subExtraDatasetSize = 'subExtraDatasetSize',
-  subExtraPoints = 'subExtraPoints'
-}
-export const payTypeMap = {
-  [PayTypeEnum.balance]: {
-    label: 'support.user.team.pay.type.balance'
-  },
-  [PayTypeEnum.subStandard]: {
-    label: 'support.wallet.subscription.type.standard'
-  },
-  [PayTypeEnum.subExtraDatasetSize]: {
-    label: 'support.wallet.subscription.type.extraDatasetSize'
-  },
-  [PayTypeEnum.subExtraPoints]: {
-    label: 'support.wallet.subscription.type.extraPoints'
-  }
-};
-
-export enum PayStatusEnum {
-  SUCCESS = 'SUCCESS',
-  REFUND = 'REFUND',
-  NOTPAY = 'NOTPAY',
-  CLOSED = 'CLOSED'
-}
-export const payStatusMap = {
-  [PayStatusEnum.SUCCESS]: {
-    label: 'support.user.team.pay.status.success'
-  },
-  [PayStatusEnum.REFUND]: {
-    label: 'support.user.team.pay.status.refund'
-  },
-  [PayStatusEnum.NOTPAY]: {
-    label: 'support.user.team.pay.status.notpay'
-  },
-  [PayStatusEnum.CLOSED]: {
-    label: 'support.user.team.pay.status.closed'
-  }
-};
--- a/packages/global/support/wallet/pay/type.d.ts
+++ b/packages/global/support/wallet/pay/type.d.ts
@@ -1,18 +0,0 @@
-import { SubModeEnum, SubTypeEnum } from '../sub/constants';
-import { PayTypeEnum } from './constants';
-
-export type PaySchema = {
-  _id: string;
-  userId: string;
-  teamId: string;
-  tmbId: string;
-  createTime: Date;
-  orderId: string;
-  status: 'SUCCESS' | 'REFUND' | 'NOTPAY' | 'CLOSED';
-  type: `${PayType}`;
-
-  price: number;
-  payWay: 'balance' | 'wx';
-
-  subMetadata: {};
-};
--- a/packages/global/support/wallet/sub/api.d.ts
+++ b/packages/global/support/wallet/sub/api.d.ts
@@ -1,26 +1,14 @@
 import { StandardSubLevelEnum, SubModeEnum } from './constants';
 import { TeamSubSchema } from './type.d';

-export type SubDatasetSizeParams = {
-  size: number;
-};
 export type StandardSubPlanParams = {
  level: `${StandardSubLevelEnum}`;
  mode: `${SubModeEnum}`;
 };

-export type SubDatasetSizePreviewCheckResponse = {
-  payForNewSub: boolean; // Does this change require payment
-  newSubSize: number; // new sub dataset size
-  alreadySubSize: number; // old sub dataset size
-  payPrice: number; // this change require payment
-  newPlanPrice: number; // the new sub price
-  newSubStartTime: Date;
-  newSubExpiredTime: Date;
-  balanceEnough: boolean; // team balance is enough
-};
 export type StandardSubPlanUpdateResponse = {
  balanceEnough: boolean; // team balance is enough
+  teamBalance: number;
  payPrice?: number;
  planPrice: number;
  planPointPrice: number;
--- a/packages/global/support/wallet/sub/constants.ts
+++ b/packages/global/support/wallet/sub/constants.ts
@@ -1,38 +1,36 @@
-export const POINTS_SCALE = 10000;
-
 export enum SubTypeEnum {
  standard = 'standard',
  extraDatasetSize = 'extraDatasetSize',
  extraPoints = 'extraPoints'
 }
+
 export const subTypeMap = {
  [SubTypeEnum.standard]: {
-    label: 'support.wallet.subscription.type.standard'
+    label: 'support.wallet.subscription.type.standard',
+    icon: 'support/account/plans'
  },
  [SubTypeEnum.extraDatasetSize]: {
-    label: 'support.wallet.subscription.type.extraDatasetSize'
+    label: 'support.wallet.subscription.type.extraDatasetSize',
+    icon: 'core/dataset/datasetLight'
  },
  [SubTypeEnum.extraPoints]: {
-    label: 'support.wallet.subscription.type.extraPoints'
+    label: 'support.wallet.subscription.type.extraPoints',
+    icon: 'core/chat/chatLight'
  }
 };

 export enum SubStatusEnum {
  active = 'active',
-  canceled = 'canceled'
+  expired = 'expired'
 }
 export const subStatusMap = {
  [SubStatusEnum.active]: {
    label: 'support.wallet.subscription.status.active'
  },
-  [SubStatusEnum.canceled]: {
+  [SubStatusEnum.expired]: {
    label: 'support.wallet.subscription.status.canceled'
  }
 };
-export const subSelectMap = {
-  true: SubStatusEnum.active,
-  false: SubStatusEnum.canceled
-};

 export enum SubModeEnum {
  month = 'month',
@@ -40,11 +38,11 @@ export enum SubModeEnum {
 }
 export const subModeMap = {
  [SubModeEnum.month]: {
-    label: 'support.wallet.subscription.mode.month',
+    label: 'support.wallet.subscription.mode.Month',
    durationMonth: 1
  },
  [SubModeEnum.year]: {
-    label: 'support.wallet.subscription.mode.year',
+    label: 'support.wallet.subscription.mode.Year',
    durationMonth: 12
  }
 };
@@ -63,7 +61,7 @@ export const standardSubLevelMap = {
  },
  [StandardSubLevelEnum.experience]: {
    label: 'support.wallet.subscription.standardSubLevel.experience',
-    desc: 'support.wallet.subscription.standardSubLevel.experience desc'
+    desc: ''
  },
  [StandardSubLevelEnum.team]: {
    label: 'support.wallet.subscription.standardSubLevel.team',
--- a/packages/global/support/wallet/sub/type.d.ts
+++ b/packages/global/support/wallet/sub/type.d.ts
@@ -2,19 +2,19 @@ import { StandardSubLevelEnum, SubModeEnum, SubStatusEnum, SubTypeEnum } from '.

 // Content of plan
 export type TeamStandardSubPlanItemType = {
-  price: number; // read price
-  pointPrice: number; // read price/ one ten thousand
+  price: number; // read price / month
+  pointPrice: number; // read price/ one thousand
+  totalPoints: number; // n
  maxTeamMember: number;
  maxAppAmount: number; // max app or plugin amount
  maxDatasetAmount: number;
  chatHistoryStoreDuration: number; // n day
  maxDatasetSize: number;
-  customApiKey: boolean;
-  customCopyright: boolean; // feature
-  websiteSyncInterval: number; // n hours
  trainingWeight: number; // 1~4
-  reRankWeight: number; // 1~4
-  totalPoints: number; // n ten thousand
+  permissionCustomApiKey: boolean;
+  permissionCustomCopyright: boolean; // feature
+  permissionWebsiteSync: boolean;
+  permissionReRank: boolean;
 };

 export type StandSubPlanLevelMapType = Record<
@@ -27,6 +27,9 @@ export type SubPlanType = {
  [SubTypeEnum.extraDatasetSize]: {
    price: number;
  };
+  [SubTypeEnum.extraPoints]: {
+    price: number;
+  };
 };

 export type TeamSubSchema = {
@@ -34,40 +37,30 @@ export type TeamSubSchema = {
  teamId: string;
  type: `${SubTypeEnum}`;
  status: `${SubStatusEnum}`;
-  currentMode: `${SubModeEnum}`;
-  nextMode: `${SubModeEnum}`;
  startTime: Date;
  expiredTime: Date;
  price: number;

+  currentMode: `${SubModeEnum}`;
+  nextMode: `${SubModeEnum}`;
  currentSubLevel: `${StandardSubLevelEnum}`;
  nextSubLevel: `${StandardSubLevelEnum}`;
+
  pointPrice: number;
  totalPoints: number;
-
-  currentExtraDatasetSize: number;
-  nextExtraDatasetSize: number;
-
-  currentExtraPoints: number;
-  nextExtraPoints: number;
-
  surplusPoints: number;

-  // abandon
-  datasetStoreAmount?: number;
-  renew?: boolean;
+  currentExtraDatasetSize: number;
 };

-export type FeTeamSubType = {
+export type FeTeamPlanStatusType = {
  [SubTypeEnum.standard]?: TeamSubSchema;
-  [SubTypeEnum.extraDatasetSize]?: TeamSubSchema;
-  [SubTypeEnum.extraPoints]?: TeamSubSchema;
+  standardConstants?: TeamStandardSubPlanItemType;

-  standardMaxDatasetSize: number;
  totalPoints: number;
  usedPoints: number;

-  standardMaxPoints: number;
+  // standard + extra
  datasetMaxSize: number;
  usedDatasetSize: number;
 };
--- a/packages/global/support/wallet/usage/api.d.ts
+++ b/packages/global/support/wallet/usage/api.d.ts
@@ -0,0 +1,26 @@
+import { UsageSourceEnum } from './constants';
+import { UsageListItemCountType, UsageListItemType } from './type';
+
+export type CreateTrainingUsageProps = {
+  name: string;
+  datasetId: string;
+};
+
+export type ConcatUsageProps = UsageListItemCountType & {
+  teamId: string;
+  tmbId: string;
+  billId?: string;
+  totalPoints: number;
+  listIndex?: number;
+};
+
+export type CreateUsageProps = {
+  teamId: string;
+  tmbId: string;
+  appName: string;
+  appId?: string;
+  totalPoints: number;
+  // inputTokens: number;
+  source: `${UsageSourceEnum}`;
+  list: UsageListItemType[];
+};
--- a/packages/global/support/wallet/usage/constants.ts
+++ b/packages/global/support/wallet/usage/constants.ts
@@ -0,0 +1,21 @@
+export enum UsageSourceEnum {
+  fastgpt = 'fastgpt',
+  api = 'api',
+  shareLink = 'shareLink',
+  training = 'training'
+}
+
+export const UsageSourceMap = {
+  [UsageSourceEnum.fastgpt]: {
+    label: '在线使用'
+  },
+  [UsageSourceEnum.api]: {
+    label: 'Api'
+  },
+  [UsageSourceEnum.shareLink]: {
+    label: '免登录链接'
+  },
+  [UsageSourceEnum.training]: {
+    label: 'dataset.Training Name'
+  }
+};
--- a/packages/global/support/wallet/usage/tools.ts
+++ b/packages/global/support/wallet/usage/tools.ts
@@ -0,0 +1,23 @@
+/* bill common  */
+import { PRICE_SCALE } from '../constants';
+import { UsageSourceEnum } from './constants';
+import { AuthUserTypeEnum } from '../../permission/constant';
+
+/**
+ * dataset price / PRICE_SCALE = real price
+ */
+export const formatStorePrice2Read = (val = 0, multiple = 1) => {
+  return Number(((val / PRICE_SCALE) * multiple).toFixed(10));
+};
+
+export const getUsageSourceByAuthType = ({
+  shareId,
+  authType
+}: {
+  shareId?: string;
+  authType?: `${AuthUserTypeEnum}`;
+}) => {
+  if (shareId) return UsageSourceEnum.shareLink;
+  if (authType === AuthUserTypeEnum.apikey) return UsageSourceEnum.api;
+  return UsageSourceEnum.fastgpt;
+};
--- a/packages/global/support/wallet/usage/type.d.ts
+++ b/packages/global/support/wallet/usage/type.d.ts
@@ -0,0 +1,26 @@
+import { CreateUsageProps } from './api';
+import { UsageSourceEnum } from './constants';
+
+export type UsageListItemCountType = {
+  charsLength?: number;
+  duration?: number;
+};
+export type UsageListItemType = UsageListItemCountType & {
+  moduleName: string;
+  amount: number;
+  model?: string;
+};
+
+export type UsageSchemaType = CreateUsageProps & {
+  _id: string;
+  time: Date;
+};
+
+export type UsageItemType = {
+  id: string;
+  time: Date;
+  appName: string;
+  source: UsageSchemaType['source'];
+  totalPoints: number;
+  list: UsageSchemaType['list'];
+};
--- a/packages/service/common/response/index.ts
+++ b/packages/service/common/response/index.ts
@@ -3,7 +3,7 @@ import { sseResponseEventEnum } from './constant';
 import { proxyError, ERROR_RESPONSE, ERROR_ENUM } from '@fastgpt/global/common/error/errorCode';
 import { addLog } from '../system/log';
 import { clearCookie } from '../../support/permission/controller';
-import { replaceSensitiveLink } from '@fastgpt/global/common/string/tools';
+import { replaceSensitiveText } from '@fastgpt/global/common/string/tools';

 export interface ResponseType<T = any> {
  code: number;
@@ -53,7 +53,7 @@ export const jsonRes = <T = any>(
  res.status(code).json({
    code,
    statusText: '',
-    message: replaceSensitiveLink(message || msg),
+    message: replaceSensitiveText(message || msg),
    data: data !== undefined ? data : null
  });
 };
@@ -91,7 +91,7 @@ export const sseErrRes = (res: NextApiResponse, error: any) => {
  responseWrite({
    res,
    event: sseResponseEventEnum.error,
-    data: JSON.stringify({ message: replaceSensitiveLink(msg) })
+    data: JSON.stringify({ message: replaceSensitiveText(msg) })
  });
 };

--- a/packages/service/common/system/tools.ts
+++ b/packages/service/common/system/tools.ts
@@ -1,3 +1,4 @@
+import { FastGPTConfigFileType } from '@fastgpt/global/common/system/types';
 import { isIPv6 } from 'net';

 export const SERVICE_LOCAL_PORT = `${process.env.PORT || 3000}`;
@@ -5,3 +6,16 @@ export const SERVICE_LOCAL_HOST =
  process.env.HOSTNAME && isIPv6(process.env.HOSTNAME)
    ? `[${process.env.HOSTNAME}]:${SERVICE_LOCAL_PORT}`
    : `${process.env.HOSTNAME || 'localhost'}:${SERVICE_LOCAL_PORT}`;
+
+export const initFastGPTConfig = (config?: FastGPTConfigFileType) => {
+  if (!config) return;
+
+  global.feConfigs = config.feConfigs;
+  global.subPlans = config.subPlans;
+
+  global.llmModels = config.llmModels;
+  global.vectorModels = config.vectorModels;
+  global.audioSpeechModels = config.audioSpeechModels;
+  global.whisperModel = config.whisperModel;
+  global.reRankModels = config.reRankModels;
+};
--- a/packages/service/common/vectorStore/controller.ts
+++ b/packages/service/common/vectorStore/controller.ts
@@ -11,7 +11,6 @@ const getVectorObj = () => {
 export const initVectorStore = getVectorObj().init;
 export const deleteDatasetDataVector = getVectorObj().delete;
 export const recallFromVectorStore = getVectorObj().recall;
-export const checkVectorDataExist = getVectorObj().checkDataExist;
 export const getVectorDataByTime = getVectorObj().getVectorDataByTime;
 export const getVectorCountByTeamId = getVectorObj().getVectorCountByTeamId;

@@ -38,22 +37,22 @@ export const insertDatasetDataVector = async ({
  };
 };

-export const updateDatasetDataVector = async ({
-  id,
-  ...props
-}: InsertVectorProps & {
-  id: string;
-  query: string;
-  model: VectorModelItemType;
-}) => {
-  // insert new vector
-  const { charsLength, insertId } = await insertDatasetDataVector(props);
+// export const updateDatasetDataVector = async ({
+//   id,
+//   ...props
+// }: InsertVectorProps & {
+//   id: string;
+//   query: string;
+//   model: VectorModelItemType;
+// }) => {
+//   // insert new vector
+//   const { charsLength, insertId } = await insertDatasetDataVector(props);

-  // delete old vector
-  await deleteDatasetDataVector({
-    teamId: props.teamId,
-    id
-  });
+//   // delete old vector
+//   await deleteDatasetDataVector({
+//     teamId: props.teamId,
+//     id
+//   });

-  return { charsLength, insertId };
-};
+//   return { charsLength, insertId };
+// };
--- a/packages/service/common/vectorStore/pg/class.ts
+++ b/packages/service/common/vectorStore/pg/class.ts
@@ -4,8 +4,7 @@ import {
  deleteDatasetDataVector,
  embeddingRecall,
  getVectorDataByTime,
-  getVectorCountByTeamId,
-  checkDataExist
+  getVectorCountByTeamId
 } from './controller';

 export class PgVector {
@@ -14,7 +13,6 @@ export class PgVector {
  insert = insertDatasetDataVector;
  delete = deleteDatasetDataVector;
  recall = embeddingRecall;
-  checkDataExist = checkDataExist;
  getVectorCountByTeamId = getVectorCountByTeamId;
  getVectorDataByTime = getVectorDataByTime;
 }
--- a/packages/service/common/vectorStore/pg/controller.ts
+++ b/packages/service/common/vectorStore/pg/controller.ts
@@ -25,6 +25,18 @@ export async function initPg() {
    await PgClient.query(
      `CREATE INDEX CONCURRENTLY IF NOT EXISTS vector_index ON ${PgDatasetTableName} USING hnsw (vector vector_ip_ops) WITH (m = 32, ef_construction = 64);`
    );
+    await PgClient.query(
+      `CREATE INDEX CONCURRENTLY IF NOT EXISTS team_dataset_index ON ${PgDatasetTableName} USING btree(team_id, dataset_id);`
+    );
+    await PgClient.query(
+      ` CREATE INDEX CONCURRENTLY IF NOT EXISTS team_collection_index ON ${PgDatasetTableName} USING btree(team_id, collection_id);`
+    );
+    await PgClient.query(
+      `CREATE INDEX CONCURRENTLY IF NOT EXISTS team_id_index ON ${PgDatasetTableName} USING btree(team_id, id);`
+    );
+    await PgClient.query(
+      `CREATE INDEX CONCURRENTLY IF NOT EXISTS create_time_index ON ${PgDatasetTableName} USING btree(createtime);`
+    );

    console.log('init pg successful');
  } catch (error) {
@@ -152,11 +164,6 @@ export const embeddingRecall = async (
  }
 };

-export const checkDataExist = async (id: string) => {
-  const { rows } = await PgClient.query(`SELECT id FROM ${PgDatasetTableName} WHERE id=${id};`);
-
-  return rows.length > 0;
-};
 export const getVectorCountByTeamId = async (teamId: string) => {
  const total = await PgClient.count(PgDatasetTableName, {
    where: [['team_id', String(teamId)]]
--- a/packages/service/core/ai/config.ts
+++ b/packages/service/core/ai/config.ts
@@ -11,6 +11,7 @@ export const getAIApi = (props?: {
  timeout?: number;
 }) => {
  const { userKey, timeout } = props || {};
+
  return new OpenAI({
    apiKey: userKey?.key || systemAIChatKey,
    baseURL: userKey?.baseUrl || baseUrl,
--- a/packages/service/core/ai/embedding/index.ts
+++ b/packages/service/core/ai/embedding/index.ts
@@ -1,5 +1,6 @@
 import { VectorModelItemType } from '@fastgpt/global/core/ai/model.d';
 import { getAIApi } from '../config';
+import { replaceValidChars } from '../../chat/utils';

 type GetVectorProps = {
  model: VectorModelItemType;
@@ -36,7 +37,7 @@ export async function getVectorsByText({ model, input }: GetVectorProps) {
        }

        return {
-          charsLength: input.length,
+          charsLength: replaceValidChars(input).length,
          vectors: await Promise.all(res.data.map((item) => unityDimensional(item.embedding)))
        };
      });
--- a/packages/service/core/ai/functions/cfr.ts
+++ b/packages/service/core/ai/functions/cfr.ts
@@ -1,159 +0,0 @@
-import { replaceVariable } from '@fastgpt/global/common/string/tools';
-import { getAIApi } from '../config';
-import { ChatItemType } from '@fastgpt/global/core/chat/type';
-
-/* 
-    cfr:  coreference resolution - 指代消除
-    可以根据上下文，完事当前问题指代内容，利于检索。
-*/
-
-const defaultPrompt = `请不要回答任何问题。
-你的任务是结合历史记录，为当前问题，实现代词替换，确保问题描述的对象清晰明确。例如：
-历史记录: 
-"""
-Q: 对话背景。
-A: 关于 FatGPT 的介绍和使用等问题。
-"""
-当前问题: 怎么下载
-输出: FastGPT 怎么下载？
----------------
-历史记录: 
-"""
-Q: 报错 "no connection"
-A: FastGPT 报错"no connection"可能是因为……
-"""
-当前问题: 怎么解决
-输出: FastGPT 报错"no connection"如何解决？
----------------
-历史记录: 
-"""
-Q: 作者是谁？
-A: FastGPT 的作者是 labring。
-"""
-当前问题: 介绍下他
-输出: 介绍下 FastGPT 的作者 labring。
----------------
-历史记录: 
-"""
-Q: 作者是谁？
-A: FastGPT 的作者是 labring。
-"""
-当前问题: 我想购买商业版。
-输出: FastGPT 商业版如何购买？
----------------
-历史记录:
-"""
-Q: 对话背景。
-A: 关于 FatGPT 的介绍和使用等问题。
-"""
-当前问题: nh
-输出: nh
----------------
-历史记录:
-"""
-Q: FastGPT 如何收费？
-A: FastGPT 收费可以参考……
-"""
-当前问题: 你知道 laf 么？
-输出: 你知道 laf 么？
----------------
-历史记录:
-"""
-Q: FastGPT 的优势
-A: 1. 开源
-   2. 简便
-   3. 扩展性强
-"""
-当前问题: 介绍下第2点。
-输出: 介绍下 FastGPT 简便的优势。
----------------
-历史记录:
-"""
-Q: 什么是 FastGPT？
-A: FastGPT 是一个 RAG 平台。
-Q: 什么是 Sealos？
-A: Sealos 是一个云操作系统。
-"""
-当前问题: 它们有什么关系？
-输出: FastGPT 和 Sealos 有什么关系？
----------------
-历史记录:
-"""
-{{histories}}
-"""
-当前问题: {{query}}
-输出: `;
-
-export const queryCfr = async ({
-  chatBg,
-  query,
-  histories = [],
-  model
-}: {
-  chatBg?: string;
-  query: string;
-  histories: ChatItemType[];
-  model: string;
-}) => {
-  if (histories.length === 0 && !chatBg) {
-    return {
-      rawQuery: query,
-      cfrQuery: query,
-      model,
-      inputTokens: 0,
-      outputTokens: 0
-    };
-  }
-
-  const systemFewShot = chatBg
-    ? `Q: 对话背景。
-A: ${chatBg}
-`
-    : '';
-  const historyFewShot = histories
-    .map((item) => {
-      const role = item.obj === 'Human' ? 'Q' : 'A';
-      return `${role}: ${item.value}`;
-    })
-    .join('\n');
-  const concatFewShot = `${systemFewShot}${historyFewShot}`.trim();
-
-  const ai = getAIApi({
-    timeout: 480000
-  });
-
-  const result = await ai.chat.completions.create({
-    model: model,
-    temperature: 0.01,
-    max_tokens: 150,
-    messages: [
-      {
-        role: 'user',
-        content: replaceVariable(defaultPrompt, {
-          query: `${query}`,
-          histories: concatFewShot
-        })
-      }
-    ],
-    stream: false
-  });
-
-  const answer = result.choices?.[0]?.message?.content || '';
-  if (!answer) {
-    return {
-      rawQuery: query,
-      cfrQuery: query,
-      model,
-      inputTokens: 0,
-      outputTokens: 0
-    };
-  }
-
-  return {
-    rawQuery: query,
-    cfrQuery: answer,
-    model,
-    inputTokens: result.usage?.prompt_tokens || 0,
-    outputTokens: result.usage?.completion_tokens || 0
-  };
-};
--- a/packages/service/core/ai/functions/createQuestionGuide.ts
+++ b/packages/service/core/ai/functions/createQuestionGuide.ts
@@ -1,5 +1,6 @@
 import type { ChatMessageItemType } from '@fastgpt/global/core/ai/type.d';
 import { getAIApi } from '../config';
+import { countGptMessagesChars } from '../../chat/utils';

 export const Prompt_QuestionGuide = `我不太清楚问你什么问题，请帮我生成 3 个问题，引导我继续提问。问题的长度应小于20个字符，按 JSON 格式返回: ["问题1", "问题2", "问题3"]`;

@@ -10,6 +11,13 @@ export async function createQuestionGuide({
  messages: ChatMessageItemType[];
  model: string;
 }) {
+  const concatMessages: ChatMessageItemType[] = [
+    ...messages,
+    {
+      role: 'user',
+      content: Prompt_QuestionGuide
+    }
+  ];
  const ai = getAIApi({
    timeout: 480000
  });
@@ -17,28 +25,21 @@ export async function createQuestionGuide({
    model: model,
    temperature: 0.1,
    max_tokens: 200,
-    messages: [
-      ...messages,
-      {
-        role: 'user',
-        content: Prompt_QuestionGuide
-      }
-    ],
+    messages: concatMessages,
    stream: false
  });

  const answer = data.choices?.[0]?.message?.content || '';
-  const inputTokens = data.usage?.prompt_tokens || 0;
-  const outputTokens = data.usage?.completion_tokens || 0;

  const start = answer.indexOf('[');
  const end = answer.lastIndexOf(']');

+  const charsLength = countGptMessagesChars(concatMessages);
+
  if (start === -1 || end === -1) {
    return {
      result: [],
-      inputTokens,
-      outputTokens
+      charsLength: 0
    };
  }

@@ -50,14 +51,12 @@ export async function createQuestionGuide({
  try {
    return {
      result: JSON.parse(jsonStr),
-      inputTokens,
-      outputTokens
+      charsLength
    };
  } catch (error) {
    return {
      result: [],
-      inputTokens,
-      outputTokens
+      charsLength: 0
    };
  }
 }
--- a/packages/service/core/ai/functions/queryExtension.ts
+++ b/packages/service/core/ai/functions/queryExtension.ts
@@ -1,18 +1,19 @@
 import { replaceVariable } from '@fastgpt/global/common/string/tools';
 import { getAIApi } from '../config';
 import { ChatItemType } from '@fastgpt/global/core/chat/type';
+import { countGptMessagesChars } from '../../chat/utils';

 /* 
    query extension - 问题扩展
    可以根据上下文，消除指代性问题以及扩展问题，利于检索。
 */

-const defaultPrompt = `作为一个向量检索助手，你的任务是结合历史记录，从不同角度，为“原问题”生成个不同版本的“检索词”，从而提高向量检索的语义丰富度，提高向量检索的精度。生成的问题要求指向对象清晰明确。例如：
+const defaultPrompt = `作为一个向量检索助手，你的任务是结合历史记录，从不同角度，为“原问题”生成个不同版本的“检索词”，从而提高向量检索的语义丰富度，提高向量检索的精度。生成的问题要求指向对象清晰明确，并与原问题语言相同。例如：
 历史记录: 
 """
 """
 原问题: 介绍下剧情。
-检索词: ["发生了什么故事？","故事梗概是什么？","讲述了什么故事？"]
+检索词: ["介绍下故事的背景和主要人物。","故事的主题是什么？","剧情是是如何发展的？"]
 ----------------
 历史记录: 
 """
@@ -20,7 +21,7 @@ Q: 对话背景。
 A: 当前对话是关于 FatGPT 的介绍和使用等。
 """
 原问题: 怎么下载
-检索词: ["FastGPT 怎么下载？","下载 FastGPT 需要什么条件？","有哪些渠道可以下载 FastGPT？"]
+检索词: ["FastGPT 如何下载？","下载 FastGPT 需要什么条件？","有哪些渠道可以下载 FastGPT？"]
 ----------------
 历史记录: 
 """
@@ -30,15 +31,15 @@ Q: 报错 "no connection"
 A: 报错"no connection"可能是因为……
 """
 原问题: 怎么解决
-检索词: ["FastGPT 报错"no connection"如何解决？", "报错 'no connection' 是什么原因？", "FastGPT提示'no connection'，要怎么办？"]
+检索词: ["FastGPT 报错"no connection"如何解决？", "造成 'no connection' 报错的原因。", "FastGPT提示'no connection'，要怎么办？"]
 ----------------
 历史记录: 
 """
 Q: 作者是谁？
 A: FastGPT 的作者是 labring。
 """
-原问题: 介绍下他
-检索词: ["介绍下 FastGPT 的作者 labring。","作者 labring 的背景信息。","labring 为什么要做 FastGPT?"]
+原问题: Tell me about him
+检索词: ["Introduce labring, the author of FastGPT." ," Background information on author labring." "," Why does labring do FastGPT?"]
 ----------------
 历史记录: 
 """
@@ -105,8 +106,7 @@ export const queryExtension = async ({
  rawQuery: string;
  extensionQueries: string[];
  model: string;
-  inputTokens: number;
-  outputTokens: number;
+  charsLength: number;
 }> => {
  const systemFewShot = chatBg
    ? `Q: 对话背景。
@@ -125,18 +125,20 @@ A: ${chatBg}
    timeout: 480000
  });

+  const messages = [
+    {
+      role: 'user',
+      content: replaceVariable(defaultPrompt, {
+        query: `${query}`,
+        histories: concatFewShot
+      })
+    }
+  ];
  const result = await ai.chat.completions.create({
    model: model,
    temperature: 0.01,
-    messages: [
-      {
-        role: 'user',
-        content: replaceVariable(defaultPrompt, {
-          query: `${query}`,
-          histories: concatFewShot
-        })
-      }
-    ],
+    // @ts-ignore
+    messages,
    stream: false
  });

@@ -146,8 +148,7 @@ A: ${chatBg}
      rawQuery: query,
      extensionQueries: [],
      model,
-      inputTokens: 0,
-      outputTokens: 0
+      charsLength: 0
    };
  }

@@ -160,8 +161,7 @@ A: ${chatBg}
      rawQuery: query,
      extensionQueries: queries,
      model,
-      inputTokens: result.usage?.prompt_tokens || 0,
-      outputTokens: result.usage?.completion_tokens || 0
+      charsLength: countGptMessagesChars(messages)
    };
  } catch (error) {
    console.log(error);
@@ -169,8 +169,7 @@ A: ${chatBg}
      rawQuery: query,
      extensionQueries: [],
      model,
-      inputTokens: 0,
-      outputTokens: 0
+      charsLength: 0
    };
  }
 };
--- a/projects/app/src/service/core/ai/model.ts
+++ b/projects/app/src/service/core/ai/model.ts
--- a/packages/service/core/app/schema.ts
+++ b/packages/service/core/app/schema.ts
@@ -61,6 +61,9 @@ const AppSchema = new Schema({
    type: String,
    enum: Object.keys(PermissionTypeMap),
    default: PermissionTypeEnum.private
+  },
+  teamTags: {
+    type: [String]
  }
 });

--- a/packages/service/core/chat/chatItemSchema.ts
+++ b/packages/service/core/chat/chatItemSchema.ts
@@ -92,6 +92,8 @@ try {
  ChatItemSchema.index({ appId: 1, chatId: 1, dataId: 1 }, { background: true });
  // admin charts
  ChatItemSchema.index({ time: -1, obj: 1 }, { background: true });
+  // timer, clear history
+  ChatItemSchema.index({ teamId: 1, time: -1 }, { background: true });
 } catch (error) {
  console.log(error);
 }
--- a/packages/service/core/chat/chatSchema.ts
+++ b/packages/service/core/chat/chatSchema.ts
@@ -83,6 +83,9 @@ try {
  ChatSchema.index({ teamId: 1, appId: 1, updateTime: -1 }, { background: true });
  // get share chat history
  ChatSchema.index({ shareId: 1, outLinkUid: 1, updateTime: -1, source: 1 }, { background: true });
+
+  // timer, clear history
+  ChatSchema.index({ teamId: 1, updateTime: -1 }, { background: true });
 } catch (error) {
  console.log(error);
 }
--- a/packages/service/core/chat/utils.ts
+++ b/packages/service/core/chat/utils.ts
@@ -2,7 +2,10 @@ import type { ChatItemType } from '@fastgpt/global/core/chat/type.d';
 import { ChatRoleEnum, IMG_BLOCK_KEY } from '@fastgpt/global/core/chat/constants';
 import { countMessagesTokens, countPromptTokens } from '@fastgpt/global/common/string/tiktoken';
 import { adaptRole_Chat2Message } from '@fastgpt/global/core/chat/adapt';
-import type { ChatCompletionContentPart } from '@fastgpt/global/core/ai/type.d';
+import type {
+  ChatCompletionContentPart,
+  ChatMessageItemType
+} from '@fastgpt/global/core/ai/type.d';
 import axios from 'axios';

 /* slice chat context by tokens */
@@ -56,6 +59,16 @@ export function ChatContextFilter({
  return [...systemPrompts, ...chats];
 }

+export const replaceValidChars = (str: string) => {
+  const reg = /[\s\r\n]+/g;
+  return str.replace(reg, '');
+};
+export const countMessagesChars = (messages: ChatItemType[]) => {
+  return messages.reduce((sum, item) => sum + replaceValidChars(item.value).length, 0);
+};
+export const countGptMessagesChars = (messages: ChatMessageItemType[]) =>
+  messages.reduce((sum, item) => sum + replaceValidChars(item.content).length, 0);
+
 /**
    string to vision model. Follow the markdown code block rule for interception:

--- a/packages/service/core/dataset/collection/controller.ts
+++ b/packages/service/core/dataset/collection/controller.ts
@@ -147,8 +147,6 @@ export async function delCollectionAndRelatedSources({
    collectionId: { $in: collectionIds }
  });

-  await delay(2000);
-
  // delete dataset.datas
  await MongoDatasetData.deleteMany({ teamId, collectionId: { $in: collectionIds } }, { session });
  // delete imgs
--- a/packages/service/core/dataset/controller.ts
+++ b/packages/service/core/dataset/controller.ts
@@ -66,6 +66,11 @@ export async function delDatasetRelevantData({
  if (!datasets.length) return;

  const teamId = datasets[0].teamId;
+
+  if (!teamId) {
+    return Promise.reject('teamId is required');
+  }
+
  const datasetIds = datasets.map((item) => String(item._id));

  // Get _id, teamId, fileId, metadata.relatedImgId for all collections
--- a/packages/service/core/dataset/data/schema.ts
+++ b/packages/service/core/dataset/data/schema.ts
@@ -7,10 +7,6 @@ import {
 } from '@fastgpt/global/support/user/team/constant';
 import { DatasetCollectionName } from '../schema';
 import { DatasetColCollectionName } from '../collection/schema';
-import {
-  DatasetDataIndexTypeEnum,
-  DatasetDataIndexTypeMap
-} from '@fastgpt/global/core/dataset/constants';

 export const DatasetDataCollectionName = 'dataset.datas';

@@ -54,11 +50,6 @@ const DatasetDataSchema = new Schema({
          type: Boolean,
          default: false
        },
-        type: {
-          type: String,
-          enum: Object.keys(DatasetDataIndexTypeMap),
-          default: DatasetDataIndexTypeEnum.custom
-        },
        dataId: {
          type: String,
          required: true
--- a/packages/service/core/dataset/search/utils.ts
+++ b/packages/service/core/dataset/search/utils.ts
@@ -14,22 +14,54 @@ export const datasetSearchQueryExtension = async ({
  extensionBg?: string;
  histories?: ChatItemType[];
 }) => {
-  // concat query
-  let queries = [query];
-  let rewriteQuery =
-    histories.length > 0
-      ? `${histories
-          .map((item) => {
-            return `${item.obj}: ${item.value}`;
-          })
-          .join('\n')}
-    Human: ${query}
-    `
-      : query;
+  const filterSamQuery = (queries: string[]) => {
+    const set = new Set<string>();
+    const filterSameQueries = queries.filter((item) => {
+      // 删除所有的标点符号与空格等，只对文本进行比较
+      const str = hashStr(item.replace(/[^\p{L}\p{N}]/gu, ''));
+      if (set.has(str)) return false;
+      set.add(str);
+      return true;
+    });
+
+    return filterSameQueries;
+  };
+
+  let { queries, rewriteQuery, alreadyExtension } = (() => {
+    // concat query
+    let rewriteQuery =
+      histories.length > 0
+        ? `${histories
+            .map((item) => {
+              return `${item.obj}: ${item.value}`;
+            })
+            .join('\n')}
+  Human: ${query}
+  `
+        : query;
+
+    /* if query already extension, direct parse */
+    try {
+      const jsonParse = JSON.parse(query);
+      const queries: string[] = Array.isArray(jsonParse) ? filterSamQuery(jsonParse) : [query];
+      const alreadyExtension = Array.isArray(jsonParse);
+      return {
+        queries,
+        rewriteQuery: alreadyExtension ? queries.join('\n') : rewriteQuery,
+        alreadyExtension: alreadyExtension
+      };
+    } catch (error) {
+      return {
+        queries: [query],
+        rewriteQuery,
+        alreadyExtension: false
+      };
+    }
+  })();

  // ai extension
  const aiExtensionResult = await (async () => {
-    if (!extensionModel) return;
+    if (!extensionModel || alreadyExtension) return;
    const result = await queryExtension({
      chatBg: extensionBg,
      query,
@@ -39,23 +71,13 @@ export const datasetSearchQueryExtension = async ({
    if (result.extensionQueries?.length === 0) return;
    return result;
  })();
-
  if (aiExtensionResult) {
-    queries = queries.concat(aiExtensionResult.extensionQueries);
+    queries = filterSamQuery(queries.concat(aiExtensionResult.extensionQueries));
    rewriteQuery = queries.join('\n');
  }

-  const set = new Set<string>();
-  const filterSameQueries = queries.filter((item) => {
-    // 删除所有的标点符号与空格等，只对文本进行比较
-    const str = hashStr(item.replace(/[^\p{L}\p{N}]/gu, ''));
-    if (set.has(str)) return false;
-    set.add(str);
-    return true;
-  });
-
  return {
-    concatQueries: filterSameQueries,
+    concatQueries: queries,
    rewriteQuery,
    aiExtensionResult
  };
--- a/packages/service/core/dataset/training/controller.ts
+++ b/packages/service/core/dataset/training/controller.ts
@@ -11,7 +11,7 @@ import { simpleText } from '@fastgpt/global/common/string/tools';
 import { countPromptTokens } from '@fastgpt/global/common/string/tiktoken';
 import type { VectorModelItemType, LLMModelItemType } from '@fastgpt/global/core/ai/model.d';

-export const lockTrainingDataByTeamId = async (teamId: string, retry = 3): Promise<any> => {
+export const lockTrainingDataByTeamId = async (teamId: string): Promise<any> => {
  try {
    await MongoDatasetTraining.updateMany(
      {
@@ -21,13 +21,7 @@ export const lockTrainingDataByTeamId = async (teamId: string, retry = 3): Promi
        lockTime: new Date('2999/5/5')
      }
    );
-  } catch (error) {
-    if (retry > 0) {
-      await delay(1000);
-      return lockTrainingDataByTeamId(teamId, retry - 1);
-    }
-    return Promise.reject(error);
-  }
+  } catch (error) {}
 };

 export async function pushDataListToTrainingQueue({
@@ -51,17 +45,15 @@ export async function pushDataListToTrainingQueue({
    datasetId: { _id: datasetId, vectorModel, agentModel }
  } = await getCollectionWithDataset(collectionId);

-  const checkModelValid = async ({ collectionId }: { collectionId: string }) => {
-    if (!collectionId) return Promise.reject(`CollectionId is empty`);
-
+  const checkModelValid = async () => {
    if (trainingMode === TrainingModeEnum.chunk) {
      const vectorModelData = vectorModelList?.find((item) => item.model === vectorModel);
      if (!vectorModelData) {
-        return Promise.reject(`Model ${vectorModel} is inValid`);
+        return Promise.reject(`File model ${vectorModel} is inValid`);
      }

      return {
-        maxToken: vectorModelData.maxToken * 1.5,
+        maxToken: vectorModelData.maxToken * 1.3,
        model: vectorModelData.model,
        weight: vectorModelData.weight
      };
@@ -70,7 +62,7 @@ export async function pushDataListToTrainingQueue({
    if (trainingMode === TrainingModeEnum.qa) {
      const qaModelData = datasetModelList?.find((item) => item.model === agentModel);
      if (!qaModelData) {
-        return Promise.reject(`Model ${agentModel} is inValid`);
+        return Promise.reject(`Vector model ${agentModel} is inValid`);
      }
      return {
        maxToken: qaModelData.maxContext * 0.8,
@@ -81,9 +73,7 @@ export async function pushDataListToTrainingQueue({
    return Promise.reject(`Training mode "${trainingMode}" is inValid`);
  };

-  const { model, maxToken, weight } = await checkModelValid({
-    collectionId
-  });
+  const { model, maxToken, weight } = await checkModelValid();

  // format q and a, remove empty char
  data.forEach((item) => {
--- a/packages/service/core/dataset/training/schema.ts
+++ b/packages/service/core/dataset/training/schema.ts
@@ -2,7 +2,7 @@
 import { connectionMongo, type Model } from '../../../common/mongo';
 const { Schema, model, models } = connectionMongo;
 import { DatasetTrainingSchemaType } from '@fastgpt/global/core/dataset/type';
-import { DatasetDataIndexTypeMap, TrainingTypeMap } from '@fastgpt/global/core/dataset/constants';
+import { TrainingTypeMap } from '@fastgpt/global/core/dataset/constants';
 import { DatasetColCollectionName } from '../collection/schema';
 import { DatasetCollectionName } from '../schema';
 import {
@@ -86,11 +86,6 @@ const TrainingDataSchema = new Schema({
  indexes: {
    type: [
      {
-        type: {
-          type: String,
-          enum: Object.keys(DatasetDataIndexTypeMap),
-          required: true
-        },
        text: {
          type: String,
          required: true
--- a/packages/service/package.json
+++ b/packages/service/package.json
@@ -15,7 +15,7 @@
    "nextjs-cors": "^2.1.2",
    "node-cron": "^3.0.3",
    "pg": "^8.10.0",
-    "date-fns": "^2.30.0",
+    "date-fns": "2.30.0",
    "tunnel": "^0.0.6"
  },
  "devDependencies": {
--- a/packages/service/support/openapi/auth.ts
+++ b/packages/service/support/openapi/auth.ts
@@ -19,14 +19,15 @@ export async function authOpenApiKey({ apikey }: { apikey: string }) {
    // auth limit
    // @ts-ignore
    if (global.feConfigs?.isPlus) {
-      await POST('/support/openapi/authLimit', { openApi } as AuthOpenApiLimitProps);
+      await POST('/support/openapi/authLimit', {
+        openApi: openApi.toObject()
+      } as AuthOpenApiLimitProps);
    }

    updateApiKeyUsedTime(openApi._id);

    return {
      apikey,
-      userId: String(openApi.userId),
      teamId: String(openApi.teamId),
      tmbId: String(openApi.tmbId),
      appId: openApi.appId || ''
--- a/packages/service/support/openapi/schema.ts
+++ b/packages/service/support/openapi/schema.ts
@@ -1,8 +1,6 @@
 import { connectionMongo, type Model } from '../../common/mongo';
 const { Schema, model, models } = connectionMongo;
 import type { OpenApiSchema } from '@fastgpt/global/support/openapi/type';
-import { PRICE_SCALE } from '@fastgpt/global/support/wallet/bill/constants';
-import { formatStorePrice2Read } from '@fastgpt/global/support/wallet/bill/tools';
 import {
  TeamCollectionName,
  TeamMemberCollectionName
@@ -10,10 +8,6 @@ import {

 const OpenApiSchema = new Schema(
  {
-    userId: {
-      type: Schema.Types.ObjectId,
-      ref: 'user'
-    },
    teamId: {
      type: Schema.Types.ObjectId,
      ref: TeamCollectionName,
@@ -44,22 +38,17 @@ const OpenApiSchema = new Schema(
      type: String,
      default: 'Api Key'
    },
-    usage: {
-      // total usage. value from bill total
+    usagePoints: {
      type: Number,
-      default: 0,
-      get: (val: number) => formatStorePrice2Read(val)
+      default: 0
    },
    limit: {
      expiredTime: {
        type: Date
      },
-      credit: {
-        // value from user settings
+      maxUsagePoints: {
        type: Number,
-        default: -1,
-        set: (val: number) => val * PRICE_SCALE,
-        get: (val: number) => formatStorePrice2Read(val)
+        default: -1
      }
    }
  },
--- a/packages/service/support/openapi/tools.ts
+++ b/packages/service/support/openapi/tools.ts
@@ -8,15 +8,21 @@ export function updateApiKeyUsedTime(id: string) {
  });
 }

-export function updateApiKeyUsage({ apikey, usage }: { apikey: string; usage: number }) {
+export function updateApiKeyUsage({
+  apikey,
+  totalPoints
+}: {
+  apikey: string;
+  totalPoints: number;
+}) {
  MongoOpenApi.findOneAndUpdate(
    { apiKey: apikey },
    {
      $inc: {
-        usage
+        usagePoints: totalPoints
      }
    }
  ).catch((err) => {
-    console.log('update apiKey usage error', err);
+    console.log('update apiKey totalPoints error', err);
  });
 }
--- a/packages/service/support/outLink/schema.ts
+++ b/packages/service/support/outLink/schema.ts
@@ -35,8 +35,7 @@ const OutLinkSchema = new Schema({
    type: String,
    required: true
  },
-  total: {
-    // total amount
+  usagePoints: {
    type: Number,
    default: 0
  },
@@ -48,6 +47,10 @@ const OutLinkSchema = new Schema({
    default: false
  },
  limit: {
+    maxUsagePoints: {
+      type: Number,
+      default: -1
+    },
    expiredTime: {
      type: Date
    },
@@ -55,16 +58,18 @@ const OutLinkSchema = new Schema({
      type: Number,
      default: 1000
    },
-    credit: {
-      type: Number,
-      default: -1
-    },
    hookUrl: {
      type: String
    }
  }
 });

+try {
+  OutLinkSchema.index({ shareId: -1 });
+} catch (error) {
+  console.log(error);
+}
+
 export const MongoOutLink: Model<SchemaType> =
  models['outlinks'] || model('outlinks', OutLinkSchema);

--- a/packages/service/support/outLink/tools.ts
+++ b/packages/service/support/outLink/tools.ts
@@ -1,18 +1,19 @@
 import axios from 'axios';
 import { MongoOutLink } from './schema';
 import { FastGPTProUrl } from '../../common/system/constants';
+import { ChatHistoryItemResType } from '@fastgpt/global/core/chat/type';

-export const updateOutLinkUsage = async ({
+export const addOutLinkUsage = async ({
  shareId,
-  total
+  totalPoints
 }: {
  shareId: string;
-  total: number;
+  totalPoints: number;
 }) => {
  MongoOutLink.findOneAndUpdate(
    { shareId },
    {
-      $inc: { total },
+      $inc: { usagePoints: totalPoints },
      lastTime: new Date()
    }
  ).catch((err) => {
@@ -23,11 +24,13 @@ export const updateOutLinkUsage = async ({
 export const pushResult2Remote = async ({
  outLinkUid,
  shareId,
+  appName,
  responseData
 }: {
  outLinkUid?: string; // raw id, not parse
  shareId?: string;
-  responseData?: any[];
+  appName: string;
+  responseData?: ChatHistoryItemResType[];
 }) => {
  if (!shareId || !outLinkUid || !FastGPTProUrl) return;
  try {
@@ -42,6 +45,7 @@ export const pushResult2Remote = async ({
      url: '/shareAuth/finish',
      data: {
        token: outLinkUid,
+        appName,
        responseData
      }
    });
--- a/packages/service/support/permission/auth/dataset.ts
+++ b/packages/service/support/permission/auth/dataset.ts
@@ -107,7 +107,7 @@ export async function authDatasetCollection({
    collection: CollectionWithDatasetType;
  }
 > {
-  const { userId, teamId, tmbId } = await parseHeaderCert(props);
+  const { teamId, tmbId } = await parseHeaderCert(props);
  const { role } = await getTmbInfoByTmbId({ tmbId });

  const { collection, isOwner, canWrite } = await (async () => {
@@ -143,7 +143,6 @@ export async function authDatasetCollection({
  })();

  return {
-    userId,
    teamId,
    tmbId,
    collection,
@@ -163,7 +162,7 @@ export async function authDatasetFile({
    file: DatasetFileSchema;
  }
 > {
-  const { userId, teamId, tmbId } = await parseHeaderCert(props);
+  const { teamId, tmbId } = await parseHeaderCert(props);

  const [file, collection] = await Promise.all([
    getFileById({ bucketName: BucketNameEnum.dataset, fileId }),
@@ -190,7 +189,6 @@ export async function authDatasetFile({
    });

    return {
-      userId,
      teamId,
      tmbId,
      file,
--- a/packages/service/support/permission/auth/user.ts
+++ b/packages/service/support/permission/auth/user.ts
@@ -12,7 +12,7 @@ export async function authUserNotVisitor(props: AuthModeType): Promise<
    role: `${TeamMemberRoleEnum}`;
  }
 > {
-  const { userId, teamId, tmbId } = await parseHeaderCert(props);
+  const { teamId, tmbId } = await parseHeaderCert(props);
  const team = await getTmbInfoByTmbId({ tmbId });

  if (team.role === TeamMemberRoleEnum.visitor) {
@@ -20,7 +20,6 @@ export async function authUserNotVisitor(props: AuthModeType): Promise<
  }

  return {
-    userId,
    teamId,
    tmbId,
    team,
--- a/packages/service/support/permission/controller.ts
+++ b/packages/service/support/permission/controller.ts
@@ -94,10 +94,10 @@ export async function parseHeaderCert({
    })();

    // auth apikey
-    const { userId, teamId, tmbId, appId: apiKeyAppId = '' } = await authOpenApiKey({ apikey });
+    const { teamId, tmbId, appId: apiKeyAppId = '' } = await authOpenApiKey({ apikey });

    return {
-      uid: userId,
+      uid: '',
      teamId,
      tmbId,
      apikey,
--- a/packages/service/support/permission/limit/dataset.ts
+++ b/packages/service/support/permission/limit/dataset.ts
@@ -1,23 +0,0 @@
-import { StandSubPlanLevelMapType } from '@fastgpt/global/support/wallet/sub/type';
-import { getVectorCountByTeamId } from '../../../common/vectorStore/controller';
-import { getTeamDatasetMaxSize } from '../../wallet/sub/utils';
-
-export const checkDatasetLimit = async ({
-  teamId,
-  insertLen = 0,
-  standardPlans
-}: {
-  teamId: string;
-  insertLen?: number;
-  standardPlans?: StandSubPlanLevelMapType;
-}) => {
-  const [{ maxSize }, usedSize] = await Promise.all([
-    getTeamDatasetMaxSize({ teamId, standardPlans }),
-    getVectorCountByTeamId(teamId)
-  ]);
-
-  if (usedSize + insertLen >= maxSize) {
-    return Promise.reject(`数据库容量不足，无法继续添加。可以在账号页面进行扩容。`);
-  }
-  return;
-};
--- a/packages/service/support/permission/teamLimit.ts
+++ b/packages/service/support/permission/teamLimit.ts
@@ -0,0 +1,91 @@
+import { getVectorCountByTeamId } from '../../common/vectorStore/controller';
+import { getTeamPlanStatus, getTeamStandPlan } from '../../support/wallet/sub/utils';
+import { MongoApp } from '../../core/app/schema';
+import { MongoPlugin } from '../../core/plugin/schema';
+import { MongoDataset } from '../../core/dataset/schema';
+import { DatasetTypeEnum } from '@fastgpt/global/core/dataset/constants';
+import { TeamErrEnum } from '@fastgpt/global/common/error/code/team';
+
+export const checkDatasetLimit = async ({
+  teamId,
+  insertLen = 0
+}: {
+  teamId: string;
+  insertLen?: number;
+}) => {
+  const [{ standardConstants, totalPoints, usedPoints, datasetMaxSize }, usedSize] =
+    await Promise.all([getTeamPlanStatus({ teamId }), getVectorCountByTeamId(teamId)]);
+
+  if (!standardConstants) return;
+
+  if (usedSize + insertLen >= datasetMaxSize) {
+    return Promise.reject(TeamErrEnum.datasetSizeNotEnough);
+  }
+
+  if (usedPoints >= totalPoints) {
+    return Promise.reject(TeamErrEnum.aiPointsNotEnough);
+  }
+  return;
+};
+
+export const checkTeamAIPoints = async (teamId: string) => {
+  const { standardConstants, totalPoints, usedPoints } = await getTeamPlanStatus({
+    teamId
+  });
+
+  if (!standardConstants) return;
+
+  if (usedPoints >= totalPoints) {
+    return Promise.reject(TeamErrEnum.aiPointsNotEnough);
+  }
+
+  return {
+    totalPoints,
+    usedPoints
+  };
+};
+
+export const checkTeamDatasetLimit = async (teamId: string) => {
+  const [{ standardConstants }, datasetCount] = await Promise.all([
+    getTeamStandPlan({ teamId }),
+    MongoDataset.countDocuments({
+      teamId,
+      type: { $ne: DatasetTypeEnum.folder }
+    })
+  ]);
+
+  if (standardConstants && datasetCount >= standardConstants.maxDatasetAmount) {
+    return Promise.reject(TeamErrEnum.datasetAmountNotEnough);
+  }
+};
+export const checkTeamAppLimit = async (teamId: string) => {
+  const [{ standardConstants }, appCount] = await Promise.all([
+    getTeamStandPlan({ teamId }),
+    MongoApp.count({ teamId })
+  ]);
+
+  if (standardConstants && appCount >= standardConstants.maxAppAmount) {
+    return Promise.reject(TeamErrEnum.appAmountNotEnough);
+  }
+};
+export const checkTeamPluginLimit = async (teamId: string) => {
+  const [{ standardConstants }, pluginCount] = await Promise.all([
+    getTeamStandPlan({ teamId }),
+    MongoPlugin.count({ teamId })
+  ]);
+
+  if (standardConstants && pluginCount >= standardConstants.maxAppAmount) {
+    return Promise.reject(TeamErrEnum.pluginAmountNotEnough);
+  }
+};
+
+export const checkTeamReRankPermission = async (teamId: string) => {
+  const { standardConstants } = await getTeamStandPlan({
+    teamId
+  });
+
+  if (standardConstants && !standardConstants?.permissionReRank) {
+    return false;
+  }
+  return true;
+};
--- a/packages/service/support/user/controller.ts
+++ b/packages/service/support/user/controller.ts
@@ -2,7 +2,6 @@ import { UserType } from '@fastgpt/global/support/user/type';
 import { MongoUser } from './schema';
 import { getTmbInfoByTmbId, getUserDefaultTeam } from './team/controller';
 import { ERROR_ENUM } from '@fastgpt/global/common/error/errorCode';
-import { UserErrEnum } from '@fastgpt/global/common/error/code/user';

 export async function authUserExist({ userId, username }: { userId?: string; username?: string }) {
  if (userId) {
@@ -47,22 +46,3 @@ export async function getUserDetail({
    team: tmb
  };
 }
-
-export async function getUserAndAuthBalance({
-  tmbId,
-  minBalance
-}: {
-  tmbId: string;
-  minBalance?: number;
-}) {
-  const user = await getUserDetail({ tmbId });
-
-  if (!user) {
-    return Promise.reject(UserErrEnum.unAuthUser);
-  }
-  if (minBalance !== undefined && user.team.balance < minBalance) {
-    return Promise.reject(UserErrEnum.balanceNotEnough);
-  }
-
-  return user;
-}
--- a/packages/service/support/user/schema.ts
+++ b/packages/service/support/user/schema.ts
@@ -1,7 +1,7 @@
 import { connectionMongo, type Model } from '../../common/mongo';
 const { Schema, model, models } = connectionMongo;
 import { hashStr } from '@fastgpt/global/common/string/tools';
-import { PRICE_SCALE } from '@fastgpt/global/support/wallet/bill/constants';
+import { PRICE_SCALE } from '@fastgpt/global/support/wallet/constants';
 import type { UserModelSchema } from '@fastgpt/global/support/user/type';
 import { UserStatusEnum, userStatusMap } from '@fastgpt/global/support/user/constant';

@@ -63,6 +63,8 @@ const UserSchema = new Schema({
 });

 try {
+  // login
+  UserSchema.index({ username: 1, password: 1 });
  UserSchema.index({ createTime: -1 });
 } catch (error) {
  console.log(error);
--- a/packages/service/support/user/team/controller.ts
+++ b/packages/service/support/user/team/controller.ts
@@ -36,7 +36,7 @@ export async function getTmbInfoByTmbId({ tmbId }: { tmbId: string }) {
    return Promise.reject('tmbId or userId is required');
  }
  return getTeamMember({
-    _id: new Types.ObjectId(tmbId),
+    _id: new Types.ObjectId(String(tmbId)),
    status: notLeaveStatus
  });
 }
--- a/packages/service/support/user/team/teamSchema.ts
+++ b/packages/service/support/user/team/teamSchema.ts
@@ -27,7 +27,10 @@ const TeamSchema = new Schema({
  },
  maxSize: {
    type: Number,
-    default: 3
+    default: 1
+  },
+  tagsUrl: {
+    type: String
  },
  limit: {
    lastExportDatasetTime: {
--- a/packages/service/support/user/team/teamTagsSchema.ts
+++ b/packages/service/support/user/team/teamTagsSchema.ts
@@ -0,0 +1,35 @@
+import { connectionMongo, type Model } from '../../../common/mongo';
+const { Schema, model, models } = connectionMongo;
+import { TeamTagsSchema as TeamTagsSchemaType } from '@fastgpt/global/support/user/team/type.d';
+import {
+  TeamCollectionName,
+  TeamTagsCollectionName
+} from '@fastgpt/global/support/user/team/constant';
+
+const TeamTagsSchema = new Schema({
+  label: {
+    type: String,
+    required: true
+  },
+  teamId: {
+    type: Schema.Types.ObjectId,
+    ref: TeamCollectionName,
+    required: true
+  },
+  key: {
+    type: String
+  },
+  createTime: {
+    type: Date,
+    default: () => new Date()
+  }
+});
+
+try {
+  TeamTagsSchema.index({ teamId: 1 });
+} catch (error) {
+  console.log(error);
+}
+
+export const MongoTeamTags: Model<TeamTagsSchemaType> =
+  models[TeamTagsCollectionName] || model(TeamTagsCollectionName, TeamTagsSchema);
--- a/packages/service/support/wallet/sub/schema.ts
+++ b/packages/service/support/wallet/sub/schema.ts
@@ -1,3 +1,8 @@
+/* 
+  user sub plan
+  1. type=standard: There will only be 1, and each team will have one
+  2. type=extraDatasetSize/extraPoints: Can buy multiple
+*/
 import { connectionMongo, type Model } from '../../../common/mongo';
 const { Schema, model, models } = connectionMongo;
 import { TeamCollectionName } from '@fastgpt/global/support/user/team/constant';
@@ -23,25 +28,10 @@ const SubSchema = new Schema({
    required: true
  },
  status: {
-    // active: continue sub; canceled: canceled sub;
    type: String,
    enum: Object.keys(subStatusMap),
    required: true
  },
-  mode: {
-    type: String,
-    enum: Object.keys(subModeMap)
-  },
-  currentMode: {
-    type: String,
-    enum: Object.keys(subModeMap),
-    required: true
-  },
-  nextMode: {
-    type: String,
-    enum: Object.keys(subModeMap),
-    required: true
-  },
  startTime: {
    type: Date,
    default: () => new Date()
@@ -55,12 +45,16 @@ const SubSchema = new Schema({
    type: Number,
    required: true
  },
-  pointPrice: {
-    // stand level point total price
-    type: Number
-  },

-  // sub content
+  // standard sub
+  currentMode: {
+    type: String,
+    enum: Object.keys(subModeMap)
+  },
+  nextMode: {
+    type: String,
+    enum: Object.keys(subModeMap)
+  },
  currentSubLevel: {
    type: String,
    enum: Object.keys(standardSubLevelMap)
@@ -69,79 +63,32 @@ const SubSchema = new Schema({
    type: String,
    enum: Object.keys(standardSubLevelMap)
  },
+
+  // stand sub and extra points sub. Plan total points
  totalPoints: {
    type: Number
  },
+  pointPrice: {
+    // stand level point total price
+    type: Number
+  },
+  surplusPoints: {
+    // plan surplus points
+    type: Number
+  },

+  // extra dataset size
  currentExtraDatasetSize: {
    type: Number
-  },
-  nextExtraDatasetSize: {
-    type: Number
-  },
-
-  currentExtraPoints: {
-    type: Number
-  },
-  nextExtraPoints: {
-    type: Number
-  },
-
-  // standard sub limit
-  // maxTeamMember: {
-  //   type: Number
-  // },
-  // maxAppAmount: {
-  //   type: Number
-  // },
-  // maxDatasetAmount: {
-  //   type: Number
-  // },
-  // chatHistoryStoreDuration: {
-  //   // n day
-  //   type: Number
-  // },
-  // maxDatasetSize: {
-  //   type: Number
-  // },
-  // trainingWeight: {
-  //   // 0 1 2 3
-  //   type: Number
-  // },
-  // customApiKey: {
-  //   type: Boolean
-  // },
-  // customCopyright: {
-  //   type: Boolean
-  // },
-  // websiteSyncInterval: {
-  //   // hours
-  //   type: Number
-  // },
-  // reRankWeight: {
-  //   // 0 1 2 3
-  //   type: Number
-  // },
-  // totalPoints: {
-  //   // record standard sub points
-  //   type: Number
-  // },
-
-  surplusPoints: {
-    // standard sub / extra points sub
-    type: Number
-  },
-
-  // abandon
-  renew: Boolean, //决定是否续费
-  datasetStoreAmount: Number
+  }
 });

 try {
-  SubSchema.index({ teamId: 1 });
-  SubSchema.index({ status: 1 });
-  SubSchema.index({ type: 1 });
-  SubSchema.index({ expiredTime: -1 });
+  // get team plan
+  SubSchema.index({ teamId: 1, type: 1, expiredTime: -1 });
+
+  // timer task. check expired plan; update standard plan;
+  SubSchema.index({ type: 1, currentSubLevel: 1, expiredTime: -1 });
 } catch (error) {
  console.log(error);
 }
--- a/packages/service/support/wallet/sub/utils.ts
+++ b/packages/service/support/wallet/sub/utils.ts
@@ -1,87 +1,147 @@
-import { SubTypeEnum } from '@fastgpt/global/support/wallet/sub/constants';
+import {
+  StandardSubLevelEnum,
+  SubModeEnum,
+  SubStatusEnum,
+  SubTypeEnum
+} from '@fastgpt/global/support/wallet/sub/constants';
 import { MongoTeamSub } from './schema';
-import { addHours } from 'date-fns';
-import { FeTeamSubType, StandSubPlanLevelMapType } from '@fastgpt/global/support/wallet/sub/type.d';
+import { FeTeamPlanStatusType } from '@fastgpt/global/support/wallet/sub/type.d';
 import { getVectorCountByTeamId } from '../../../common/vectorStore/controller';
+import dayjs from 'dayjs';
+import { ClientSession } from '../../../common/mongo';
+import { addMonths } from 'date-fns';

-/* get team dataset max size */
-export const getTeamDatasetMaxSize = async ({
-  teamId,
-  standardPlans
-}: {
-  teamId: string;
-  standardPlans?: StandSubPlanLevelMapType;
-}) => {
-  if (!standardPlans) {
-    return {
-      maxSize: Infinity,
-      sub: null
-    };
-  }
+export const getStandardPlans = () => {
+  return global?.subPlans?.standard;
+};
+export const getStandardPlan = (level: `${StandardSubLevelEnum}`) => {
+  return global.subPlans?.standard?.[level];
+};

-  const plans = await MongoTeamSub.find({
-    teamId,
-    expiredTime: { $gte: addHours(new Date(), -3) }
-  }).lean();
-
-  const standard = plans.find((plan) => plan.type === SubTypeEnum.standard);
-  const extraDatasetSize = plans.find((plan) => plan.type === SubTypeEnum.extraDatasetSize);
-
-  const standardMaxDatasetSize =
-    standard?.currentSubLevel && standardPlans
-      ? standardPlans[standard.currentSubLevel]?.maxDatasetSize || Infinity
-      : Infinity;
-  const totalDatasetSize =
-    standardMaxDatasetSize + (extraDatasetSize?.currentExtraDatasetSize || 0);
+export const getTeamStandPlan = async ({ teamId }: { teamId: string }) => {
+  const standardPlans = global.subPlans?.standard;
+  const standard = await MongoTeamSub.findOne({ teamId, type: SubTypeEnum.standard }).lean();

  return {
-    maxSize: totalDatasetSize,
-    sub: extraDatasetSize
+    [SubTypeEnum.standard]: standard,
+    standardConstants:
+      standard?.currentSubLevel && standardPlans
+        ? standardPlans[standard.currentSubLevel]
+        : undefined
  };
 };

-export const getTeamSubPlanStatus = async ({
+export const initTeamStandardPlan2Free = async ({
  teamId,
-  standardPlans
+  session
 }: {
  teamId: string;
-  standardPlans?: StandSubPlanLevelMapType;
-}): Promise<FeTeamSubType> => {
+  session?: ClientSession;
+}) => {
+  const freePoints = global?.subPlans?.standard?.free?.totalPoints || 100;
+
+  const teamStandardSub = await MongoTeamSub.findOne({ teamId, type: SubTypeEnum.standard });
+
+  if (teamStandardSub) {
+    teamStandardSub.status = SubStatusEnum.active;
+    teamStandardSub.currentMode = SubModeEnum.month;
+    teamStandardSub.nextMode = SubModeEnum.month;
+    teamStandardSub.startTime = new Date();
+    teamStandardSub.expiredTime = addMonths(new Date(), 1);
+
+    teamStandardSub.currentSubLevel = StandardSubLevelEnum.free;
+    teamStandardSub.nextSubLevel = StandardSubLevelEnum.free;
+
+    teamStandardSub.price = 0;
+    teamStandardSub.pointPrice = 0;
+
+    teamStandardSub.totalPoints = freePoints;
+    teamStandardSub.surplusPoints =
+      teamStandardSub.surplusPoints && teamStandardSub.surplusPoints < 0
+        ? teamStandardSub.surplusPoints + freePoints
+        : freePoints;
+    return teamStandardSub.save({ session });
+  }
+
+  return MongoTeamSub.create(
+    [
+      {
+        teamId,
+        type: SubTypeEnum.standard,
+        status: SubStatusEnum.active,
+        currentMode: SubModeEnum.month,
+        nextMode: SubModeEnum.month,
+        startTime: new Date(),
+        expiredTime: addMonths(new Date(), 1),
+        price: 0,
+        pointPrice: 0,
+
+        currentSubLevel: StandardSubLevelEnum.free,
+        nextSubLevel: StandardSubLevelEnum.free,
+
+        totalPoints: freePoints,
+        surplusPoints: freePoints
+      }
+    ],
+    { session }
+  );
+};
+
+export const getTeamPlanStatus = async ({
+  teamId
+}: {
+  teamId: string;
+}): Promise<FeTeamPlanStatusType> => {
+  const standardPlans = global.subPlans?.standard;
+
  const [plans, usedDatasetSize] = await Promise.all([
    MongoTeamSub.find({ teamId }).lean(),
    getVectorCountByTeamId(teamId)
  ]);

  const standard = plans.find((plan) => plan.type === SubTypeEnum.standard);
-  const extraDatasetSize = plans.find((plan) => plan.type === SubTypeEnum.extraDatasetSize);
-  const extraPoints = plans.find((plan) => plan.type === SubTypeEnum.extraPoints);
+  const extraDatasetSize = plans.filter((plan) => plan.type === SubTypeEnum.extraDatasetSize);
+  const extraPoints = plans.filter((plan) => plan.type === SubTypeEnum.extraPoints);
+
+  // Free user, first login after expiration. The free subscription plan will be reset
+  if (
+    standard &&
+    standard.expiredTime &&
+    standard.currentSubLevel === StandardSubLevelEnum.free &&
+    dayjs(standard.expiredTime).isBefore(new Date())
+  ) {
+    console.log('Init free stand plan', { teamId });
+    await initTeamStandardPlan2Free({ teamId });
+    return getTeamPlanStatus({ teamId });
+  }
+
+  const totalPoints = standardPlans
+    ? (standard?.totalPoints || 0) +
+      extraPoints.reduce((acc, cur) => acc + (cur.totalPoints || 0), 0)
+    : Infinity;
+  const surplusPoints =
+    (standard?.surplusPoints || 0) +
+    extraPoints.reduce((acc, cur) => acc + (cur.surplusPoints || 0), 0);

  const standardMaxDatasetSize =
    standard?.currentSubLevel && standardPlans
      ? standardPlans[standard.currentSubLevel]?.maxDatasetSize || Infinity
      : Infinity;
  const totalDatasetSize =
-    standardMaxDatasetSize + (extraDatasetSize?.currentExtraDatasetSize || 0);
-
-  const standardMaxPoints =
-    standard?.currentSubLevel && standardPlans
-      ? standardPlans[standard.currentSubLevel]?.totalPoints || Infinity
-      : Infinity;
-  const totalPoints = standardMaxPoints + (extraPoints?.currentExtraPoints || 0);
-
-  const surplusPoints = (standard?.surplusPoints || 0) + (extraPoints?.surplusPoints || 0);
+    standardMaxDatasetSize +
+    extraDatasetSize.reduce((acc, cur) => acc + (cur.currentExtraDatasetSize || 0), 0);

  return {
    [SubTypeEnum.standard]: standard,
-    [SubTypeEnum.extraDatasetSize]: extraDatasetSize,
-    [SubTypeEnum.extraPoints]: extraPoints,
+    standardConstants:
+      standard?.currentSubLevel && standardPlans
+        ? standardPlans[standard.currentSubLevel]
+        : undefined,

-    standardMaxDatasetSize,
-    datasetMaxSize: totalDatasetSize,
-    usedDatasetSize,
-
-    standardMaxPoints,
    totalPoints,
-    usedPoints: totalPoints - surplusPoints
+    usedPoints: totalPoints - surplusPoints,
+
+    datasetMaxSize: totalDatasetSize,
+    usedDatasetSize
  };
 };
--- a/packages/service/support/wallet/usage/controller.ts
+++ b/packages/service/support/wallet/usage/controller.ts
@@ -1,8 +1,8 @@
-import { BillSourceEnum } from '@fastgpt/global/support/wallet/bill/constants';
-import { MongoBill } from './schema';
+import { UsageSourceEnum } from '@fastgpt/global/support/wallet/usage/constants';
+import { MongoUsage } from './schema';
 import { ClientSession } from '../../../common/mongo';

-export const createTrainingBill = async ({
+export const createTrainingUsage = async ({
  teamId,
  tmbId,
  appName,
@@ -14,33 +14,33 @@ export const createTrainingBill = async ({
  teamId: string;
  tmbId: string;
  appName: string;
-  billSource: `${BillSourceEnum}`;
+  billSource: `${UsageSourceEnum}`;
  vectorModel: string;
  agentModel: string;
  session?: ClientSession;
 }) => {
-  const [{ _id }] = await MongoBill.create(
+  const [{ _id }] = await MongoUsage.create(
    [
      {
        teamId,
        tmbId,
        appName,
        source: billSource,
+        totalPoints: 0,
        list: [
          {
-            moduleName: 'wallet.moduleName.index',
+            moduleName: 'support.wallet.moduleName.index',
            model: vectorModel,
            charsLength: 0,
            amount: 0
          },
          {
-            moduleName: 'wallet.moduleName.qa',
+            moduleName: 'support.wallet.moduleName.qa',
            model: agentModel,
            charsLength: 0,
            amount: 0
          }
-        ],
-        total: 0
+        ]
      }
    ],
    { session }
--- a/Show More
+++ b/Show More