perf: delete dataset (#3949)

* fix: collection list count

* fix: collection list count

* ai proxy ui

* perf: delete dataset

* perf: add dataset text index

* update doc

.github/workflows/fastgpt-preview-image.yml

@@ -68,14 +68,3 @@ jobs:
           SEALOS_TYPE: 'pr_comment'
           SEALOS_FILENAME: 'report.md'
           SEALOS_REPLACE_TAG: 'DEFAULT_REPLACE_DEPLOY'
-
-  helm-check:
-    runs-on: ubuntu-20.04
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-      - name: Helm Check
-        run: |
-          helm dependency update files/helm/fastgpt
-          helm lint files/helm/fastgpt
-          helm package files/helm/fastgpt

.github/workflows/helm-release.yaml

@@ -24,6 +24,6 @@ jobs:
           export APP_VERSION=${{ steps.vars.outputs.tag }}
           export HELM_VERSION=${{ steps.vars.outputs.tag }}
           export HELM_REPO=ghcr.io/${{ github.repository_owner }}
-          helm dependency update files/helm/fastgpt
-          helm package files/helm/fastgpt --version ${HELM_VERSION}-helm --app-version ${APP_VERSION} -d bin
+          helm dependency update deploy/helm/fastgpt
+          helm package deploy/helm/fastgpt --version ${HELM_VERSION}-helm --app-version ${APP_VERSION} -d bin
           helm push bin/fastgpt-${HELM_VERSION}-helm.tgz oci://${HELM_REPO}

.vscode/nextapi.code-snippets

@@ -58,7 +58,7 @@
 		"body": [
 			"import '@/pages/api/__mocks__/base';",
 			"import { root } from '@/pages/api/__mocks__/db/init';",
-			"import { getTestRequest } from '@/test/utils';",
+			"import { getTestRequest } from '@fastgpt/service/test/utils'; ;",
 			"import { AppErrEnum } from '@fastgpt/global/common/error/code/app';",
 			"import handler from './demo';",
 			"",

deploy/docker/docker-compose-milvus.yml

@@ -114,15 +114,15 @@ services:
   # fastgpt
   sandbox:
     container_name: sandbox
-    image: ghcr.io/labring/fastgpt-sandbox:v4.8.22 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.22 # 阿里云
+    image: ghcr.io/labring/fastgpt-sandbox:v4.8.23-fix # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.23-fix # 阿里云
     networks:
       - fastgpt
     restart: always
   fastgpt:
     container_name: fastgpt
-    image: ghcr.io/labring/fastgpt:v4.8.22 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.8.22 # 阿里云
+    image: ghcr.io/labring/fastgpt:v4.8.23-fix # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.8.23-fix # 阿里云
     ports:
       - 3000:3000
     networks:

deploy/docker/docker-compose-pgvector.yml

@@ -72,15 +72,15 @@ services:
   # fastgpt
   sandbox:
     container_name: sandbox
-    image: ghcr.io/labring/fastgpt-sandbox:v4.8.22 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.22 # 阿里云
+    image: ghcr.io/labring/fastgpt-sandbox:v4.8.23-fix # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.23-fix # 阿里云
     networks:
       - fastgpt
     restart: always
   fastgpt:
     container_name: fastgpt
-    image: ghcr.io/labring/fastgpt:v4.8.22 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.8.22 # 阿里云
+    image: ghcr.io/labring/fastgpt:v4.8.23-fix # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.8.23-fix # 阿里云
     ports:
       - 3000:3000
     networks:

deploy/docker/docker-compose-zilliz.yml

@@ -53,15 +53,15 @@ services:
         wait $$!
   sandbox:
     container_name: sandbox
-    image: ghcr.io/labring/fastgpt-sandbox:v4.8.22 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.22 # 阿里云
+    image: ghcr.io/labring/fastgpt-sandbox:v4.8.23-fix # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.23-fix # 阿里云
     networks:
       - fastgpt
     restart: always
   fastgpt:
     container_name: fastgpt
-    image: ghcr.io/labring/fastgpt:v4.8.22 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.8.22 # 阿里云
+    image: ghcr.io/labring/fastgpt:v4.8.23-fix # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.8.23-fix # 阿里云
     ports:
       - 3000:3000
     networks:

docSite/content/zh-cn/docs/development/custom-models/bge-rerank.md

@@ -31,9 +31,9 @@ weight: 920
 
 3 个模型代码分别为：
 
-1. [https://github.com/labring/FastGPT/tree/main/python/bge-rerank/bge-reranker-base](https://github.com/labring/FastGPT/tree/main/python/bge-rerank/bge-reranker-base)
-2. [https://github.com/labring/FastGPT/tree/main/python/bge-rerank/bge-reranker-large](https://github.com/labring/FastGPT/tree/main/python/bge-rerank/bge-reranker-large)
-3. [https://github.com/labring/FastGPT/tree/main/python/bge-rerank/bge-reranker-v2-m3](https://github.com/labring/FastGPT/tree/main/python/bge-rerank/bge-reranker-v2-m3)
+1. [https://github.com/labring/FastGPT/tree/main/plugins/rerank-bge/bge-reranker-base](https://github.com/labring/FastGPT/tree/main/plugins/rerank-bge/bge-reranker-base)
+2. [https://github.com/labring/FastGPT/tree/main/plugins/rerank-bge/bge-reranker-large](https://github.com/labring/FastGPT/tree/main/plugins/rerank-bge/bge-reranker-large)
+3. [https://github.com/labring/FastGPT/tree/main/plugins/rerank-bge/bge-reranker-v2-m3](https://github.com/labring/FastGPT/tree/main/plugins/rerank-bge/bge-reranker-v2-m3)
 
 ### 3. 安装依赖
 

docSite/content/zh-cn/docs/development/custom-models/marker.md

@@ -19,7 +19,7 @@ PDF 是一个相对复杂的文件格式，在 FastGPT 内置的 pdf 解析器
 
 ### 1. 按照 Marker
 
-参考文档 [Marker 安装教程](https://github.com/labring/FastGPT/tree/main/python/pdf-marker)，安装 Marker 模型。封装的 API 已经适配了 FastGPT 自定义解析服务。
+参考文档 [Marker 安装教程](https://github.com/labring/FastGPT/tree/main/plugins/model/pdf-marker)，安装 Marker 模型。封装的 API 已经适配了 FastGPT 自定义解析服务。
 
 这里介绍快速 Docker 安装的方法：
 

docSite/content/zh-cn/docs/development/docker.md

@@ -118,7 +118,7 @@ brew install orbstack
 非 Linux 环境或无法访问外网环境，可手动创建一个目录，并下载配置文件和对应版本的`docker-compose.yml`，在这个文件夹中依据下载的配置文件运行docker，若作为本地开发使用推荐`docker-compose-pgvector`版本，并且自行拉取并运行`sandbox`和`fastgpt`，并在docker配置文件中注释掉`sandbox`和`fastgpt`的部分
 
 - [config.json](https://raw.githubusercontent.com/labring/FastGPT/refs/heads/main/projects/app/data/config.json)
-- [docker-compose.yml](https://github.com/labring/FastGPT/blob/main/files/docker) (注意，不同向量库版本的文件不一样)
+- [docker-compose.yml](https://github.com/labring/FastGPT/blob/main/deploy/docker) (注意，不同向量库版本的文件不一样)
 
 {{% alert icon="🤖" context="success" %}}
 
@@ -134,11 +134,11 @@ cd fastgpt
 curl -O https://raw.githubusercontent.com/labring/FastGPT/main/projects/app/data/config.json
 
 # pgvector 版本(测试推荐，简单快捷)
-curl -o docker-compose.yml https://raw.githubusercontent.com/labring/FastGPT/main/files/docker/docker-compose-pgvector.yml
+curl -o docker-compose.yml https://raw.githubusercontent.com/labring/FastGPT/main/deploy/docker/docker-compose-pgvector.yml
 # milvus 版本
-# curl -o docker-compose.yml https://raw.githubusercontent.com/labring/FastGPT/main/files/docker/docker-compose-milvus.yml
+# curl -o docker-compose.yml https://raw.githubusercontent.com/labring/FastGPT/main/deploy/docker/docker-compose-milvus.yml
 # zilliz 版本
-# curl -o docker-compose.yml https://raw.githubusercontent.com/labring/FastGPT/main/files/docker/docker-compose-zilliz.yml
+# curl -o docker-compose.yml https://raw.githubusercontent.com/labring/FastGPT/main/deploy/docker/docker-compose-zilliz.yml
 ```
 
 ### 2. 修改环境变量
@@ -201,6 +201,8 @@ docker restart oneapi
 
 在OneApi中添加合适的AI模型渠道。[点击查看相关教程](/docs/development/modelconfig/one-api/)
 
+只需要添加模型即可，模板已经配置好了oneapi的连接地址和令牌，无需变更。
+
 ### 5. 访问 FastGPT
 
 目前可以通过 `ip:3000` 直接访问(注意防火墙)。登录用户名为 `root`，密码为`docker-compose.yml`环境变量里设置的 `DEFAULT_ROOT_PSW`。
@@ -211,7 +213,7 @@ docker restart oneapi
 
 ### 6. 配置模型
 
-务必先配置至少一组模型，否则系统无法正常使用。
+登录FastGPT后，进入模型配置页面，务必先配置至少一个语言模型和一个向量模型，否则系统无法正常使用。
 
 [点击查看模型配置教程](/docs/development/modelConfig/intro/)
 

docSite/content/zh-cn/docs/development/upgrading/482.md

@@ -20,7 +20,7 @@ SANDBOX_URL=内网地址
 
 ## Docker 部署
 
-可以拉取最新 [docker-compose.yml](https://github.com/labring/FastGPT/blob/main/files/docker/docker-compose.yml) 文件参考
+可以拉取最新 [docker-compose.yml](https://github.com/labring/FastGPT/blob/main/deploy/docker/docker-compose.yml) 文件参考
 
 1. 新增一个容器 `sandbox`
 2. fastgpt 和 fastgpt-pro(商业版) 容器新增环境变量: `SANDBOX_URL`

docSite/content/zh-cn/docs/development/upgrading/4823.md

@@ -1,5 +1,5 @@
 ---
-title: 'V4.8.23(进行中)'
+title: 'V4.8.23'
 description: 'FastGPT V4.8.23 更新说明'
 icon: 'upgrade'
 draft: false
@@ -7,11 +7,33 @@ toc: true
 weight: 802
 ---
 
+## 更新指南
+
+### 1. 做好数据库备份
+
+### 2. 更新镜像：
+
+- 更新 fastgpt 镜像 tag: v4.8.23-fix
+- 更新 fastgpt-pro 商业版镜像 tag: v4.8.23-fix
+- Sandbox 镜像无需更新
+
+### 3. 运行升级脚本
+
+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**FastGPT 域名**。
+
+```bash
+curl --location --request POST 'https://{{host}}/api/admin/initv4823' \
+--header 'rootkey: {{rootkey}}' \
+--header 'Content-Type: application/json'
+```
+
+脚本会清理一些知识库脏数据，主要是多余的全文索引。
 
 ## 🚀 新增内容
 
 1. 增加默认“知识库文本理解模型”配置
 2. AI proxy V1版，可替换 OneAPI使用，同时提供完整模型调用日志，便于排查问题。
+3. 增加工单入口支持。
 
 ## ⚙️ 优化
 
@@ -27,4 +49,6 @@ weight: 802
 1. 标签过滤时，子文件夹未成功过滤。
 2. 暂时移除 md 阅读优化，避免链接分割错误。
 3. 离开团队时，未刷新成员列表。
-4. PPTX 编码错误，导致解析失败。
+4. PPTX 编码错误，导致解析失败。
+5. 删除知识库单条数据时，全文索引未跟随删除。
+6. 修复 Mongo Dataset text 索引在查询数据时未生效。

docSite/content/zh-cn/docs/development/upgrading/483.md

@@ -15,7 +15,7 @@ weight: 821
 
 ## V4.8.3 更新说明
 
-1. 新增 - 支持 Milvus 数据库， 可参考最新的 [docker-compose-milvus.yml](https://github.com/labring/FastGPT/blob/main/files/docker/docker-compose-milvus.yml).
+1. 新增 - 支持 Milvus 数据库， 可参考最新的 [docker-compose-milvus.yml](https://github.com/labring/FastGPT/blob/main/deploy/docker/docker-compose-milvus.yml).
 2. 新增 - 给 chat 接口 empty answer 增加 log，便于排查模型问题。
 3. 新增 - ifelse判断器，字符串支持正则。
 4. 新增 - 代码运行支持 console.log 输出调试。

packages/README.md

@@ -0,0 +1,3 @@
+# 目录说明
+
+该目录为 FastGPT 的依赖包，多端复用。

packages/global/common/error/code/dataset.ts

@@ -4,6 +4,7 @@ import { ErrType } from '../errorCode';
 /* dataset: 501000 */
 export enum DatasetErrEnum {
   unExist = 'unExistDataset',
+  unExistCollection = 'unExistCollection',
   unAuthDataset = 'unAuthDataset',
   unCreateCollection = 'unCreateCollection',
   unAuthDatasetCollection = 'unAuthDatasetCollection',
@@ -28,6 +29,10 @@ const datasetErr = [
     statusText: DatasetErrEnum.unExist,
     message: 'core.dataset.error.unExistDataset'
   },
+  {
+    statusText: DatasetErrEnum.unExistCollection,
+    message: i18nT('common:error_collection_not_exist')
+  },
   {
     statusText: DatasetErrEnum.unAuthDataset,
     message: 'core.dataset.error.unAuthDataset'

packages/global/core/workflow/runtime/utils.ts

@@ -420,137 +420,3 @@ export function rewriteNodeOutputByHistories(
     };
   });
 }
-
-// Parse <think></think> tags to think and answer - unstream response
-export const parseReasoningContent = (text: string): [string, string] => {
-  const regex = /<think>([\s\S]*?)<\/think>/;
-  const match = text.match(regex);
-
-  if (!match) {
-    return ['', text];
-  }
-
-  const thinkContent = match[1].trim();
-
-  // Add answer (remaining text after think tag)
-  const answerContent = text.slice(match.index! + match[0].length);
-
-  return [thinkContent, answerContent];
-};
-
-// Parse <think></think> tags to think and answer - stream response
-export const parseReasoningStreamContent = () => {
-  let isInThinkTag: boolean | undefined;
-
-  const startTag = '<think>';
-  let startTagBuffer = '';
-
-  const endTag = '</think>';
-  let endTagBuffer = '';
-
-  /* 
-    parseReasoning - 只控制是否主动解析 <think></think>，如果接口已经解析了，仍然会返回 think 内容。
-  */
-  const parsePart = (
-    part: {
-      choices: {
-        delta: {
-          content?: string;
-          reasoning_content?: string;
-        };
-      }[];
-    },
-    parseReasoning = false
-  ): [string, string] => {
-    const content = part.choices?.[0]?.delta?.content || '';
-
-    // @ts-ignore
-    const reasoningContent = part.choices?.[0]?.delta?.reasoning_content || '';
-    if (reasoningContent || !parseReasoning) {
-      isInThinkTag = false;
-      return [reasoningContent, content];
-    }
-
-    if (!content) {
-      return ['', ''];
-    }
-
-    // 如果不在 think 标签中，或者有 reasoningContent(接口已解析），则返回 reasoningContent 和 content
-    if (isInThinkTag === false) {
-      return ['', content];
-    }
-
-    // 检测是否为 think 标签开头的数据
-    if (isInThinkTag === undefined) {
-      // Parse content think and answer
-      startTagBuffer += content;
-      // 太少内容时候，暂时不解析
-      if (startTagBuffer.length < startTag.length) {
-        return ['', ''];
-      }
-
-      if (startTagBuffer.startsWith(startTag)) {
-        isInThinkTag = true;
-        return [startTagBuffer.slice(startTag.length), ''];
-      }
-
-      // 如果未命中 think 标签，则认为不在 think 标签中，返回 buffer 内容作为 content
-      isInThinkTag = false;
-      return ['', startTagBuffer];
-    }
-
-    // 确认是 think 标签内容，开始返回 think 内容，并实时检测 </think>
-    /* 
-      检测 </think> 方案。
-      存储所有疑似 </think> 的内容，直到检测到完整的 </think> 标签或超出 </think> 长度。
-      content 返回值包含以下几种情况:
-        abc - 完全未命中尾标签
-        abc<th - 命中一部分尾标签
-        abc</think> - 完全命中尾标签
-        abc</think>abc - 完全命中尾标签
-        </think>abc - 完全命中尾标签
-        k>abc - 命中一部分尾标签
-    */
-    // endTagBuffer 专门用来记录疑似尾标签的内容
-    if (endTagBuffer) {
-      endTagBuffer += content;
-      if (endTagBuffer.includes(endTag)) {
-        isInThinkTag = false;
-        const answer = endTagBuffer.slice(endTag.length);
-        return ['', answer];
-      } else if (endTagBuffer.length >= endTag.length) {
-        // 缓存内容超出尾标签长度，且仍未命中 </think>，则认为本次猜测 </think> 失败，仍处于 think 阶段。
-        const tmp = endTagBuffer;
-        endTagBuffer = '';
-        return [tmp, ''];
-      }
-      return ['', ''];
-    } else if (content.includes(endTag)) {
-      // 返回内容，完整命中</think>，直接结束
-      isInThinkTag = false;
-      const [think, answer] = content.split(endTag);
-      return [think, answer];
-    } else {
-      // 无 buffer，且未命中 </think>，开始疑似 </think> 检测。
-      for (let i = 1; i < endTag.length; i++) {
-        const partialEndTag = endTag.slice(0, i);
-        // 命中一部分尾标签
-        if (content.endsWith(partialEndTag)) {
-          const think = content.slice(0, -partialEndTag.length);
-          endTagBuffer += partialEndTag;
-          return [think, ''];
-        }
-      }
-    }
-
-    // 完全未命中尾标签，还是 think 阶段。
-    return [content, ''];
-  };
-
-  const getStartTagBuffer = () => startTagBuffer;
-
-  return {
-    parsePart,
-    getStartTagBuffer
-  };
-};

packages/service/common/file/image/controller.ts

@@ -118,7 +118,7 @@ export async function delImgByRelatedId({
 }: {
   teamId: string;
   relateIds: string[];
-  session: ClientSession;
+  session?: ClientSession;
 }) {
   if (relateIds.length === 0) return;
 

packages/service/common/mongo/index.ts

@@ -38,10 +38,12 @@ const addCommonMiddleware = (schema: mongoose.Schema) => {
     schema.post(op, function (this: any, result: any, next) {
       if (this._startTime) {
         const duration = Date.now() - this._startTime;
-
         const warnLogData = {
-          query: this._query,
-          op,
+          collectionName: this.collection?.name,
+          op: this.op,
+          ...(this._query && { query: this._query }),
+          ...(this._update && { update: this._update }),
+          ...(this._delete && { delete: this._delete }),
           duration
         };
 

packages/service/common/mongo/init.ts

@@ -16,16 +16,30 @@ export async function connectMongo(): Promise<Mongoose> {
 
   console.log('mongo start connect');
   try {
-    connectionMongo.set('strictQuery', true);
+    // Remove existing listeners to prevent duplicates
+    connectionMongo.connection.removeAllListeners('error');
+    connectionMongo.connection.removeAllListeners('disconnected');
+    connectionMongo.set('strictQuery', false);
 
     connectionMongo.connection.on('error', async (error) => {
       console.log('mongo error', error);
-      await connectionMongo.disconnect();
-      await delay(1000);
-      connectMongo();
+      try {
+        if (connectionMongo.connection.readyState !== 0) {
+          await connectionMongo.disconnect();
+          await delay(1000);
+          await connectMongo();
+        }
+      } catch (error) {}
     });
-    connectionMongo.connection.on('disconnected', () => {
+    connectionMongo.connection.on('disconnected', async () => {
       console.log('mongo disconnected');
+      try {
+        if (connectionMongo.connection.readyState !== 0) {
+          await connectionMongo.disconnect();
+          await delay(1000);
+          await connectMongo();
+        }
+      } catch (error) {}
     });
 
     await connectionMongo.connect(process.env.MONGODB_URI as string, {

packages/service/core/ai/config.ts

@@ -35,7 +35,7 @@ export const getAxiosConfig = (props?: { userKey?: OpenaiAccountType }) => {
   const { userKey } = props || {};
 
   const baseUrl = userKey?.baseUrl || global?.systemEnv?.oneapiUrl || openaiBaseUrl;
-  const apiKey = userKey?.key || global?.systemEnv?.chatApiKey || process.env.CHAT_API_KEY || '';
+  const apiKey = userKey?.key || global?.systemEnv?.chatApiKey || openaiBaseKey;
 
   return {
     baseUrl,

packages/service/core/ai/config/provider/AliCloud.json

@@ -1,4 +1,10 @@
 {
   "provider": "AliCloud",
-  "list": []
-}
+  "list": [
+    {
+      "model": "SenseVoiceSmall",
+      "name": "SenseVoiceSmall",
+      "type": "stt"
+    }
+  ]
+}

packages/service/core/ai/utils.ts

@@ -95,11 +95,145 @@ export const llmCompletionsBodyFormat = <T extends CompletionsBodyType>(
   return requestBody as unknown as InferCompletionsBody<T>;
 };
 
-export const llmStreamResponseToText = async (response: StreamChatType) => {
+export const llmStreamResponseToAnswerText = async (response: StreamChatType) => {
   let answer = '';
   for await (const part of response) {
     const content = part.choices?.[0]?.delta?.content || '';
     answer += content;
   }
-  return answer;
+  return parseReasoningContent(answer)[1];
+};
+
+// Parse <think></think> tags to think and answer - unstream response
+export const parseReasoningContent = (text: string): [string, string] => {
+  const regex = /<think>([\s\S]*?)<\/think>/;
+  const match = text.match(regex);
+
+  if (!match) {
+    return ['', text];
+  }
+
+  const thinkContent = match[1].trim();
+
+  // Add answer (remaining text after think tag)
+  const answerContent = text.slice(match.index! + match[0].length);
+
+  return [thinkContent, answerContent];
+};
+
+// Parse <think></think> tags to think and answer - stream response
+export const parseReasoningStreamContent = () => {
+  let isInThinkTag: boolean | undefined;
+
+  const startTag = '<think>';
+  let startTagBuffer = '';
+
+  const endTag = '</think>';
+  let endTagBuffer = '';
+
+  /* 
+    parseReasoning - 只控制是否主动解析 <think></think>，如果接口已经解析了，仍然会返回 think 内容。
+  */
+  const parsePart = (
+    part: {
+      choices: {
+        delta: {
+          content?: string;
+          reasoning_content?: string;
+        };
+      }[];
+    },
+    parseReasoning = false
+  ): [string, string] => {
+    const content = part.choices?.[0]?.delta?.content || '';
+
+    // @ts-ignore
+    const reasoningContent = part.choices?.[0]?.delta?.reasoning_content || '';
+    if (reasoningContent || !parseReasoning) {
+      isInThinkTag = false;
+      return [reasoningContent, content];
+    }
+
+    if (!content) {
+      return ['', ''];
+    }
+
+    // 如果不在 think 标签中，或者有 reasoningContent(接口已解析），则返回 reasoningContent 和 content
+    if (isInThinkTag === false) {
+      return ['', content];
+    }
+
+    // 检测是否为 think 标签开头的数据
+    if (isInThinkTag === undefined) {
+      // Parse content think and answer
+      startTagBuffer += content;
+      // 太少内容时候，暂时不解析
+      if (startTagBuffer.length < startTag.length) {
+        return ['', ''];
+      }
+
+      if (startTagBuffer.startsWith(startTag)) {
+        isInThinkTag = true;
+        return [startTagBuffer.slice(startTag.length), ''];
+      }
+
+      // 如果未命中 think 标签，则认为不在 think 标签中，返回 buffer 内容作为 content
+      isInThinkTag = false;
+      return ['', startTagBuffer];
+    }
+
+    // 确认是 think 标签内容，开始返回 think 内容，并实时检测 </think>
+    /* 
+      检测 </think> 方案。
+      存储所有疑似 </think> 的内容，直到检测到完整的 </think> 标签或超出 </think> 长度。
+      content 返回值包含以下几种情况:
+        abc - 完全未命中尾标签
+        abc<th - 命中一部分尾标签
+        abc</think> - 完全命中尾标签
+        abc</think>abc - 完全命中尾标签
+        </think>abc - 完全命中尾标签
+        k>abc - 命中一部分尾标签
+    */
+    // endTagBuffer 专门用来记录疑似尾标签的内容
+    if (endTagBuffer) {
+      endTagBuffer += content;
+      if (endTagBuffer.includes(endTag)) {
+        isInThinkTag = false;
+        const answer = endTagBuffer.slice(endTag.length);
+        return ['', answer];
+      } else if (endTagBuffer.length >= endTag.length) {
+        // 缓存内容超出尾标签长度，且仍未命中 </think>，则认为本次猜测 </think> 失败，仍处于 think 阶段。
+        const tmp = endTagBuffer;
+        endTagBuffer = '';
+        return [tmp, ''];
+      }
+      return ['', ''];
+    } else if (content.includes(endTag)) {
+      // 返回内容，完整命中</think>，直接结束
+      isInThinkTag = false;
+      const [think, answer] = content.split(endTag);
+      return [think, answer];
+    } else {
+      // 无 buffer，且未命中 </think>，开始疑似 </think> 检测。
+      for (let i = 1; i < endTag.length; i++) {
+        const partialEndTag = endTag.slice(0, i);
+        // 命中一部分尾标签
+        if (content.endsWith(partialEndTag)) {
+          const think = content.slice(0, -partialEndTag.length);
+          endTagBuffer += partialEndTag;
+          return [think, ''];
+        }
+      }
+    }
+
+    // 完全未命中尾标签，还是 think 阶段。
+    return [content, ''];
+  };
+
+  const getStartTagBuffer = () => startTagBuffer;
+
+  return {
+    parsePart,
+    getStartTagBuffer
+  };
 };

packages/service/core/dataset/collection/controller.ts

@@ -25,6 +25,7 @@ import { MongoImage } from '../../../common/file/image/schema';
 import { hashStr } from '@fastgpt/global/common/string/tools';
 import { addDays } from 'date-fns';
 import { MongoDatasetDataText } from '../data/dataTextSchema';
+import { delay, retryFn } from '@fastgpt/global/common/system/utils';
 
 export const createCollectionAndInsertData = async ({
   dataset,
@@ -216,7 +217,7 @@ export async function createOneCollection({
         nextSyncTime
       }
     ],
-    { session }
+    { session, ordered: true }
   );
 
   return collection;
@@ -227,8 +228,14 @@ export const delCollectionRelatedSource = async ({
   collections,
   session
 }: {
-  collections: DatasetCollectionSchemaType[];
-  session: ClientSession;
+  collections: {
+    teamId: string;
+    fileId?: string;
+    metadata?: {
+      relatedImgId?: string;
+    };
+  }[];
+  session?: ClientSession;
 }) => {
   if (collections.length === 0) return;
 
@@ -259,11 +266,13 @@ export const delCollectionRelatedSource = async ({
 export async function delCollection({
   collections,
   session,
-  delRelatedSource
+  delImg = true,
+  delFile = true
 }: {
   collections: DatasetCollectionSchemaType[];
   session: ClientSession;
-  delRelatedSource: boolean;
+  delImg: boolean;
+  delFile: boolean;
 }) {
   if (collections.length === 0) return;
 
@@ -274,83 +283,55 @@ export async function delCollection({
   const datasetIds = Array.from(new Set(collections.map((item) => String(item.datasetId))));
   const collectionIds = collections.map((item) => String(item._id));
 
-  // Delete training data
-  await MongoDatasetTraining.deleteMany({
-    teamId,
-    datasetIds: { $in: datasetIds },
-    collectionId: { $in: collectionIds }
+  await retryFn(async () => {
+    await Promise.all([
+      // Delete training data
+      MongoDatasetTraining.deleteMany({
+        teamId,
+        datasetId: { $in: datasetIds },
+        collectionId: { $in: collectionIds }
+      }),
+      // Delete dataset_data_texts
+      MongoDatasetDataText.deleteMany({
+        teamId,
+        datasetId: { $in: datasetIds },
+        collectionId: { $in: collectionIds }
+      }),
+      // Delete dataset_datas
+      MongoDatasetData.deleteMany({
+        teamId,
+        datasetId: { $in: datasetIds },
+        collectionId: { $in: collectionIds }
+      }),
+      ...(delImg
+        ? [
+            delImgByRelatedId({
+              teamId,
+              relateIds: collections
+                .map((item) => item?.metadata?.relatedImgId || '')
+                .filter(Boolean)
+            })
+          ]
+        : []),
+      ...(delFile
+        ? [
+            delFileByFileIdList({
+              bucketName: BucketNameEnum.dataset,
+              fileIdList: collections.map((item) => item?.fileId || '').filter(Boolean)
+            })
+          ]
+        : []),
+      // Delete vector data
+      deleteDatasetDataVector({ teamId, datasetIds, collectionIds })
+    ]);
+
+    // delete collections
+    await MongoDatasetCollection.deleteMany(
+      {
+        teamId,
+        _id: { $in: collectionIds }
+      },
+      { session }
+    );
   });
-
-  /* file and imgs */
-  if (delRelatedSource) {
-    await delCollectionRelatedSource({ collections, session });
-  }
-
-  // Delete dataset_datas
-  await MongoDatasetData.deleteMany(
-    { teamId, datasetIds: { $in: datasetIds }, collectionId: { $in: collectionIds } },
-    { session }
-  );
-  // Delete dataset_data_texts
-  await MongoDatasetDataText.deleteMany(
-    { teamId, datasetIds: { $in: datasetIds }, collectionId: { $in: collectionIds } },
-    { session }
-  );
-
-  // delete collections
-  await MongoDatasetCollection.deleteMany(
-    {
-      teamId,
-      _id: { $in: collectionIds }
-    },
-    { session }
-  );
-
-  // no session delete: delete files, vector data
-  await deleteDatasetDataVector({ teamId, datasetIds, collectionIds });
-}
-
-/**
- * delete delOnlyCollection
- */
-export async function delOnlyCollection({
-  collections,
-  session
-}: {
-  collections: DatasetCollectionSchemaType[];
-  session: ClientSession;
-}) {
-  if (collections.length === 0) return;
-
-  const teamId = collections[0].teamId;
-
-  if (!teamId) return Promise.reject('teamId is not exist');
-
-  const datasetIds = Array.from(new Set(collections.map((item) => String(item.datasetId))));
-  const collectionIds = collections.map((item) => String(item._id));
-
-  // delete training data
-  await MongoDatasetTraining.deleteMany({
-    teamId,
-    datasetIds: { $in: datasetIds },
-    collectionId: { $in: collectionIds }
-  });
-
-  // delete dataset.datas
-  await MongoDatasetData.deleteMany(
-    { teamId, datasetIds: { $in: datasetIds }, collectionId: { $in: collectionIds } },
-    { session }
-  );
-
-  // delete collections
-  await MongoDatasetCollection.deleteMany(
-    {
-      teamId,
-      _id: { $in: collectionIds }
-    },
-    { session }
-  );
-
-  // no session delete: delete files, vector data
-  await deleteDatasetDataVector({ teamId, datasetIds, collectionIds });
 }

packages/service/core/dataset/collection/utils.ts

@@ -97,7 +97,7 @@ export const createOrGetCollectionTags = async ({
       datasetId,
       tag: tagContent
     })),
-    { session }
+    { session, ordered: true }
   );
 
   return [...existingTags.map((tag) => tag._id), ...newTags.map((tag) => tag._id)];
@@ -174,6 +174,14 @@ export const syncCollection = async (collection: CollectionWithDatasetType) => {
   }
 
   await mongoSessionRun(async (session) => {
+    // Delete old collection
+    await delCollection({
+      collections: [collection],
+      delImg: false,
+      delFile: false,
+      session
+    });
+
     // Create new collection
     await createCollectionAndInsertData({
       session,
@@ -208,13 +216,6 @@ export const syncCollection = async (collection: CollectionWithDatasetType) => {
         updateTime: new Date()
       }
     });
-
-    // Delete old collection
-    await delCollection({
-      collections: [collection],
-      delRelatedSource: false,
-      session
-    });
   });
 
   return DatasetCollectionSyncResultEnum.success;

packages/service/core/dataset/controller.ts

@@ -7,6 +7,8 @@ import { MongoDatasetTraining } from './training/schema';
 import { MongoDatasetData } from './data/schema';
 import { deleteDatasetDataVector } from '../../common/vectorStore/controller';
 import { MongoDatasetDataText } from './data/dataTextSchema';
+import { DatasetErrEnum } from '@fastgpt/global/common/error/code/dataset';
+import { retryFn } from '@fastgpt/global/common/system/utils';
 
 /* ============= dataset ========== */
 /* find all datasetId by top datasetId */
@@ -54,7 +56,7 @@ export async function getCollectionWithDataset(collectionId: string) {
     .populate<{ dataset: DatasetSchemaType }>('dataset')
     .lean();
   if (!data) {
-    return Promise.reject('Collection is not exist');
+    return Promise.reject(DatasetErrEnum.unExistCollection);
   }
   return data;
 }
@@ -77,40 +79,39 @@ export async function delDatasetRelevantData({
 
   const datasetIds = datasets.map((item) => item._id);
 
-  // delete training data
-  await MongoDatasetTraining.deleteMany({
-    teamId,
-    datasetId: { $in: datasetIds }
-  });
-
   // Get _id, teamId, fileId, metadata.relatedImgId for all collections
   const collections = await MongoDatasetCollection.find(
     {
       teamId,
       datasetId: { $in: datasetIds }
     },
-    '_id teamId datasetId fileId metadata',
-    { session }
+    '_id teamId datasetId fileId metadata'
   ).lean();
 
-  // Delete Image and file
-  await delCollectionRelatedSource({ collections, session });
+  await retryFn(async () => {
+    await Promise.all([
+      // delete training data
+      MongoDatasetTraining.deleteMany({
+        teamId,
+        datasetId: { $in: datasetIds }
+      }),
+      //Delete dataset_data_texts
+      MongoDatasetDataText.deleteMany({
+        teamId,
+        datasetId: { $in: datasetIds }
+      }),
+      //delete dataset_datas
+      MongoDatasetData.deleteMany({ teamId, datasetId: { $in: datasetIds } }),
+      // Delete Image and file
+      delCollectionRelatedSource({ collections }),
+      // Delete vector data
+      deleteDatasetDataVector({ teamId, datasetIds })
+    ]);
+  });
 
   // delete collections
   await MongoDatasetCollection.deleteMany({
     teamId,
     datasetId: { $in: datasetIds }
   }).session(session);
-
-  // No session delete:
-  // Delete dataset_data_texts
-  await MongoDatasetDataText.deleteMany({
-    teamId,
-    datasetId: { $in: datasetIds }
-  });
-  // delete dataset_datas
-  await MongoDatasetData.deleteMany({ teamId, datasetId: { $in: datasetIds } });
-
-  // Delete vector data
-  await deleteDatasetDataVector({ teamId, datasetIds });
 }

packages/service/core/dataset/data/dataTextSchema.ts

@@ -1,6 +1,6 @@
 import { connectionMongo, getMongoModel } from '../../../common/mongo';
 const { Schema } = connectionMongo;
-import { DatasetDataSchemaType } from '@fastgpt/global/core/dataset/type.d';
+import { DatasetDataTextSchemaType } from '@fastgpt/global/core/dataset/type.d';
 import { TeamCollectionName } from '@fastgpt/global/support/user/team/constant';
 import { DatasetCollectionName } from '../schema';
 import { DatasetColCollectionName } from '../collection/schema';
@@ -40,12 +40,13 @@ try {
       default_language: 'none'
     }
   );
+  DatasetDataTextSchema.index({ teamId: 1, datasetId: 1, collectionId: 1 });
   DatasetDataTextSchema.index({ dataId: 1 }, { unique: true });
 } catch (error) {
   console.log(error);
 }
 
-export const MongoDatasetDataText = getMongoModel<DatasetDataSchemaType>(
+export const MongoDatasetDataText = getMongoModel<DatasetDataTextSchemaType>(
   DatasetDataTextCollectionName,
   DatasetDataTextSchema
 );

packages/service/core/workflow/dispatch/chat/oneapi.ts

@@ -3,11 +3,8 @@ import { filterGPTMessageByMaxContext, loadRequestMessages } from '../../../chat
 import type { ChatItemType, UserChatItemValueItemType } from '@fastgpt/global/core/chat/type.d';
 import { ChatRoleEnum } from '@fastgpt/global/core/chat/constants';
 import { SseResponseEventEnum } from '@fastgpt/global/core/workflow/runtime/constants';
-import {
-  parseReasoningContent,
-  parseReasoningStreamContent,
-  textAdaptGptResponse
-} from '@fastgpt/global/core/workflow/runtime/utils';
+import { textAdaptGptResponse } from '@fastgpt/global/core/workflow/runtime/utils';
+import { parseReasoningContent, parseReasoningStreamContent } from '../../../ai/utils';
 import { createChatCompletion } from '../../../ai/config';
 import type { ChatCompletionMessageParam, StreamChatType } from '@fastgpt/global/core/ai/type.d';
 import { formatModelChars2Points } from '../../../../support/wallet/usage/utils';

packages/service/support/permission/inheritPermission.ts

@@ -196,7 +196,8 @@ export async function syncCollaborators({
       permission: item.permission
     })),
     {
-      session
+      session,
+      ordered: true
     }
   );
 }

packages/service/support/permission/publish/authLink.ts

@@ -1,5 +1,5 @@
 import { AppDetailType } from '@fastgpt/global/core/app/type';
-import { OutLinkSchema } from '@fastgpt/global/support/outLink/type';
+import { OutlinkAppType, OutLinkSchema } from '@fastgpt/global/support/outLink/type';
 import { parseHeaderCert } from '../controller';
 import { MongoOutLink } from '../../outLink/schema';
 import { OutLinkErrEnum } from '@fastgpt/global/common/error/code/outLink';
@@ -54,11 +54,15 @@ export async function authOutLinkCrud({
 }
 
 /* outLink exist and it app exist */
-export async function authOutLinkValid({ shareId }: { shareId?: string }) {
+export async function authOutLinkValid<T extends OutlinkAppType = any>({
+  shareId
+}: {
+  shareId?: string;
+}) {
   if (!shareId) {
     return Promise.reject(OutLinkErrEnum.linkUnInvalid);
   }
-  const outLinkConfig = await MongoOutLink.findOne({ shareId }).lean();
+  const outLinkConfig = await MongoOutLink.findOne({ shareId }).lean<OutLinkSchema<T>>();
 
   if (!outLinkConfig) {
     return Promise.reject(OutLinkErrEnum.linkUnInvalid);
@@ -66,6 +70,6 @@ export async function authOutLinkValid({ shareId }: { shareId?: string }) {
 
   return {
     appId: outLinkConfig.appId,
-    outLinkConfig
+    outLinkConfig: outLinkConfig
   };
 }

packages/service/support/wallet/sub/utils.ts

@@ -100,7 +100,7 @@ export const initTeamFreePlan = async ({
         surplusPoints: freePoints
       }
     ],
-    { session }
+    { session, ordered: true }
   );
 };
 

packages/service/support/wallet/usage/controller.ts

@@ -160,7 +160,7 @@ export const createTrainingUsage = async ({
         ]
       }
     ],
-    { session }
+    { session, ordered: true }
   );
 
   return { billId: String(_id) };

packages/web/components/common/Icon/index.tsx

@@ -1,4 +1,4 @@
-import React, { useEffect } from 'react';
+import React, { useEffect, useState } from 'react';
 import type { IconProps } from '@chakra-ui/react';
 import { Box, Icon } from '@chakra-ui/react';
 import { iconPaths } from './constants';
@@ -8,7 +8,7 @@ import { useRefresh } from '../../../hooks/useRefresh';
 const iconCache: Record<string, any> = {};
 
 const MyIcon = ({ name, w = 'auto', h = 'auto', ...props }: { name: IconNameType } & IconProps) => {
-  const { refresh } = useRefresh();
+  const [, setUpdate] = useState(0);
 
   useEffect(() => {
     if (iconCache[name]) {
@@ -20,7 +20,7 @@ const MyIcon = ({ name, w = 'auto', h = 'auto', ...props }: { name: IconNameType
         const component = { as: icon.default };
         // Store in cache
         iconCache[name] = component;
-        refresh();
+        setUpdate((prev) => prev + 1); // force update
       })
       .catch((error) => console.log(error));
   }, [name]);

packages/web/hooks/useScrollPagination.tsx

@@ -217,7 +217,7 @@ export function useScrollPagination<
       const offset = init ? 0 : data.length;
 
       setTrue();
-      console.log(offset);
+
       try {
         const res = await api({
           offset,

packages/web/i18n/en/account_model.json

@@ -24,6 +24,7 @@
   "key_type": "API key format:",
   "log": "Call log",
   "log_detail": "Log details",
+  "log_request_id_search": "Search by requestId",
   "log_status": "Status",
   "mapping": "Model Mapping",
   "mapping_tip": "A valid Json is required. \nThe model can be mapped when sending a request to the actual address. \nFor example:\n{\n  \n  \"gpt-4o\": \"gpt-4o-test\"\n\n}\n\nWhen FastGPT requests the gpt-4o model, the gpt-4o-test model is sent to the actual address, instead of gpt-4o.",

packages/web/i18n/en/common.json

@@ -888,6 +888,7 @@
   "error.upload_file_error_filename": "{{name}} Upload Failed",
   "error.upload_image_error": "File upload failed",
   "error.username_empty": "Account cannot be empty",
+  "error_collection_not_exist": "The collection does not exist",
   "extraction_results": "Extraction Results",
   "field_name": "Field Name",
   "free": "Free",

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

@@ -24,6 +24,7 @@
   "key_type": "API key 格式: ",
   "log": "调用日志",
   "log_detail": "日志详情",
+  "log_request_id_search": "根据 requestId 搜索",
   "log_status": "状态",
   "mapping": "模型映射",
   "mapping_tip": "需填写一个有效 Json。可在向实际地址发送请求时，对模型进行映射。例如：\n{\n  \"gpt-4o\": \"gpt-4o-test\"\n}\n当 FastGPT 请求 gpt-4o 模型时，会向实际地址发送 gpt-4o-test 的模型，而不是 gpt-4o。",

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

@@ -891,6 +891,7 @@
   "error.upload_file_error_filename": "{{name}} 上传失败",
   "error.upload_image_error": "上传文件失败",
   "error.username_empty": "账号不能为空",
+  "error_collection_not_exist": "集合不存在",
   "extraction_results": "提取结果",
   "field_name": "字段名",
   "free": "免费",

packages/web/i18n/zh-Hant/account_model.json

@@ -22,6 +22,7 @@
   "key_type": "API key 格式:",
   "log": "調用日誌",
   "log_detail": "日誌詳情",
+  "log_request_id_search": "根據 requestId 搜索",
   "log_status": "狀態",
   "mapping": "模型映射",
   "mapping_tip": "需填寫一個有效 Json。\n可在向實際地址發送請求時，對模型進行映射。\n例如：\n{\n  \n  \"gpt-4o\": \"gpt-4o-test\"\n\n}\n\n當 FastGPT 請求 gpt-4o 模型時，會向實際地址發送 gpt-4o-test 的模型，而不是 gpt-4o。",

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

@@ -888,6 +888,7 @@
   "error.upload_file_error_filename": "{{name}} 上傳失敗",
   "error.upload_image_error": "上傳文件失敗",
   "error.username_empty": "帳號不能為空",
+  "error_collection_not_exist": "集合不存在",
   "extraction_results": "提取結果",
   "field_name": "欄位名稱",
   "free": "免費",

plugins/README.md

@@ -0,0 +1,5 @@
+# 目录说明
+
+该目录为 FastGPT 辅助子项目，非必须。
+
+- model 私有化模型