website sync feature

deploy/docker/docker-compose-milvus.yml

@@ -110,6 +110,18 @@ services:
 
         # 等待docker-entrypoint.sh脚本执行的MongoDB服务进程
         wait $$!
+  redis:
+    image: redis:7.2-alpine
+    container_name: redis
+    # ports:
+    # - 6379:6379
+    networks:
+      - fastgpt
+    restart: always
+    command: |
+      redis-server --requirepass mypassword --loglevel warning --maxclients 10000 --appendonly yes --save 60 10 --maxmemory 4gb --maxmemory-policy noeviction
+    volumes:
+      - ./redis/data:/data
 
   # fastgpt
   sandbox:
@@ -157,6 +169,8 @@ services:
       # zilliz 连接参数
       - MILVUS_ADDRESS=http://milvusStandalone:19530
       - MILVUS_TOKEN=none
+      # Redis 地址
+      - REDIS_URL=redis://default:mypassword@redis:6379
       # sandbox 地址
       - SANDBOX_URL=http://sandbox:3000
       # 日志等级: debug, info, warn, error

deploy/docker/docker-compose-pgvector.yml

@@ -69,6 +69,19 @@ services:
         # 等待docker-entrypoint.sh脚本执行的MongoDB服务进程
         wait $$!
 
+  redis:
+    image: redis:7.2-alpine
+    container_name: redis
+    # ports:
+    # - 6379:6379
+    networks:
+      - fastgpt
+    restart: always
+    command: |
+      redis-server --requirepass mypassword --loglevel warning --maxclients 10000 --appendonly yes --save 60 10 --maxmemory 4gb --maxmemory-policy noeviction
+    volumes:
+      - ./redis/data:/data
+
   # fastgpt
   sandbox:
     container_name: sandbox
@@ -114,6 +127,8 @@ services:
       - MONGODB_URI=mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
       # pg 连接参数
       - PG_URL=postgresql://username:password@pg:5432/postgres
+      # Redis 连接参数
+      - REDIS_URL=redis://default:mypassword@redis:6379
       # sandbox 地址
       - SANDBOX_URL=http://sandbox:3000
       # 日志等级: debug, info, warn, error

deploy/docker/docker-compose-zilliz.yml

@@ -51,6 +51,19 @@ services:
 
         # 等待docker-entrypoint.sh脚本执行的MongoDB服务进程
         wait $$!
+  redis:
+    image: redis:7.2-alpine
+    container_name: redis
+    # ports:
+    # - 6379:6379
+    networks:
+      - fastgpt
+    restart: always
+    command: |
+      redis-server --requirepass mypassword --loglevel warning --maxclients 10000 --appendonly yes --save 60 10 --maxmemory 4gb --maxmemory-policy noeviction
+    volumes:
+      - ./redis/data:/data
+
   sandbox:
     container_name: sandbox
     image: ghcr.io/labring/fastgpt-sandbox:v4.9.3 # git
@@ -92,6 +105,8 @@ services:
       - FILE_TOKEN_KEY=filetoken
       # MongoDB 连接参数. 用户名myusername,密码mypassword。
       - MONGODB_URI=mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
+      # Redis 连接参数
+      - REDIS_URI=redis://default:mypassword@redis:6379
       # zilliz 连接参数
       - MILVUS_ADDRESS=zilliz_cloud_address
       - MILVUS_TOKEN=zilliz_cloud_token

docSite/content/zh-cn/docs/development/upgrading/494.md

@@ -7,11 +7,44 @@ toc: true
 weight: 796
 ---
 
+## 升级指南
+
+### 1. 做好数据备份
+
+### 1. 安装 Redis
+
+* docker 部署的用户，参考最新的 `docker-compose.yml` 文件增加 Redis 配置。增加一个 redis 容器，并配置`fastgpt`,`fastgpt-pro`的环境变量，增加 `REDIS_URL` 环境变量。
+* Sealos 部署的用户，在数据库里新建一个`redis`数据库，并复制`内网地址的 connection` 作为 `redis` 的链接串。然后配置`fastgpt`,`fastgpt-pro`的环境变量，增加 `REDIS_URL` 环境变量。
+
+| | | |
+| --- | --- |  --- |
+| ![](/imgs/sealos-redis1.png) | ![](/imgs/sealos-redis2.png) |  ![](/imgs/sealos-redis3.png) |
+
+### 2. 更新镜像 tag
+
+
+### 3. 执行升级脚本
+
+该脚本仅需商业版用户执行。
+
+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/initv494' \
+--header 'rootkey: {{rootkey}}' \
+--header 'Content-Type: application/json'
+```
+
+**脚本功能**
+
+1. 更新站点同步定时器
 
 ## 🚀 新增内容
 
 1. 集合数据训练状态展示
 2. SMTP 发送邮件插件
+3. BullMQ 消息队列。
+4. 站点同步支持配置训练参数。
 
 ## 🐛 修复
 

packages/global/core/dataset/api.d.ts

@@ -15,7 +15,6 @@ export type DatasetUpdateBody = {
   name?: string;
   avatar?: string;
   intro?: string;
-  status?: DatasetSchemaType['status'];
 
   agentModel?: string;
   vlmModel?: string;
@@ -26,6 +25,7 @@ export type DatasetUpdateBody = {
   apiServer?: DatasetSchemaType['apiServer'];
   yuqueServer?: DatasetSchemaType['yuqueServer'];
   feishuServer?: DatasetSchemaType['feishuServer'];
+  chunkSettings?: DatasetSchemaType['chunkSettings'];
 
   // sync schedule
   autoSync?: boolean;
@@ -141,7 +141,6 @@ export type PushDatasetDataChunkProps = {
 
 export type PostWebsiteSyncParams = {
   datasetId: string;
-  billId: string;
 };
 
 export type PushDatasetDataProps = {

packages/global/core/dataset/constants.ts

@@ -50,14 +50,18 @@ export const DatasetTypeMap = {
 
 export enum DatasetStatusEnum {
   active = 'active',
-  syncing = 'syncing'
+  syncing = 'syncing',
+  waiting = 'waiting'
 }
 export const DatasetStatusMap = {
   [DatasetStatusEnum.active]: {
     label: i18nT('common:core.dataset.status.active')
   },
   [DatasetStatusEnum.syncing]: {
     label: i18nT('common:core.dataset.status.syncing')
+  },
+  [DatasetStatusEnum.waiting]: {
+    label: i18nT('common:core.dataset.status.waiting')
   }
 };
 

packages/global/core/dataset/type.d.ts

@@ -17,6 +17,20 @@ import { SourceMemberType } from 'support/user/type';
 import { DatasetDataIndexTypeEnum } from './data/constants';
 import { ChunkSettingModeEnum } from './constants';
 
+export type ChunkSettingsType = {
+  trainingType: DatasetCollectionDataProcessModeEnum;
+  autoIndexes?: boolean;
+  imageIndex?: boolean;
+
+  chunkSettingMode?: ChunkSettingModeEnum;
+  chunkSplitMode?: DataChunkSplitModeEnum;
+
+  chunkSize?: number;
+  indexSize?: number;
+  chunkSplitter?: string;
+  qaPrompt?: string;
+};
+
 export type DatasetSchemaType = {
   _id: string;
   parentId?: string;
@@ -29,7 +43,6 @@ export type DatasetSchemaType = {
   name: string;
   intro: string;
   type: `${DatasetTypeEnum}`;
-  status: `${DatasetStatusEnum}`;
 
   vectorModel: string;
   agentModel: string;
@@ -39,14 +52,16 @@ export type DatasetSchemaType = {
     url: string;
     selector: string;
   };
+
+  chunkSettings?: ChunkSettingsType;
+
   inheritPermission: boolean;
   apiServer?: APIFileServer;
   feishuServer?: FeishuServer;
   yuqueServer?: YuqueServer;
 
-  autoSync?: boolean;
-
   // abandon
+  autoSync?: boolean;
   externalReadUrl?: string;
   defaultPermission?: number;
 };
@@ -193,6 +208,7 @@ export type DatasetListItemType = {
 };
 
 export type DatasetItemType = Omit<DatasetSchemaType, 'vectorModel' | 'agentModel' | 'vlmModel'> & {
+  status: `${DatasetStatusEnum}`;
   vectorModel: EmbeddingModelItemType;
   agentModel: LLMModelItemType;
   vlmModel?: LLMModelItemType;

packages/service/common/bullmq/index.ts

@@ -0,0 +1,74 @@
+import { ConnectionOptions, Processor, Queue, QueueOptions, Worker, WorkerOptions } from 'bullmq';
+import { addLog } from '../system/log';
+import { newQueueRedisConnection, newWorkerRedisConnection } from '../redis';
+
+const defaultWorkerOpts: Omit<ConnectionOptions, 'connection'> = {
+  removeOnComplete: {
+    count: 0 // Delete jobs immediately on completion
+  },
+  removeOnFail: {
+    count: 0 // Delete jobs immediately on failure
+  }
+};
+
+export enum QueueNames {
+  websiteSync = 'websiteSync'
+}
+
+export const queues = (() => {
+  if (!global.queues) {
+    global.queues = new Map<QueueNames, Queue>();
+  }
+  return global.queues;
+})();
+export const workers = (() => {
+  if (!global.workers) {
+    global.workers = new Map<QueueNames, Worker>();
+  }
+  return global.workers;
+})();
+
+export function getQueue<DataType, ReturnType = void>(
+  name: QueueNames,
+  opts?: Omit<QueueOptions, 'connection'>
+): Queue<DataType, ReturnType> {
+  // check if global.queues has the queue
+  const queue = queues.get(name);
+  if (queue) {
+    return queue as Queue<DataType, ReturnType>;
+  }
+  const newQueue = new Queue<DataType, ReturnType>(name.toString(), {
+    connection: newQueueRedisConnection(),
+    ...opts
+  });
+
+  // default error handler, to avoid unhandled exceptions
+  newQueue.on('error', (error) => {
+    addLog.error(`MQ Queue [${name}]: ${error.message}`, error);
+  });
+  queues.set(name, newQueue);
+  return newQueue;
+}
+
+export function getWorker<DataType, ReturnType = void>(
+  name: QueueNames,
+  processor: Processor<DataType, ReturnType>,
+  opts?: Omit<WorkerOptions, 'connection'>
+): Worker<DataType, ReturnType> {
+  const worker = workers.get(name);
+  if (worker) {
+    return worker as Worker<DataType, ReturnType>;
+  }
+
+  const newWorker = new Worker<DataType, ReturnType>(name.toString(), processor, {
+    connection: newWorkerRedisConnection(),
+    ...defaultWorkerOpts,
+    ...opts
+  });
+  // default error handler, to avoid unhandled exceptions
+  newWorker.on('error', (error) => {
+    addLog.error(`MQ Worker [${name}]: ${error.message}`, error);
+  });
+  workers.set(name, newWorker);
+  return newWorker;
+}

packages/service/common/bullmq/type.d.ts

@@ -0,0 +1,7 @@
+import { Queue, Worker } from 'bullmq';
+import { QueueNames } from './index';
+
+declare global {
+  var queues: Map<QueueNames, Queue> | undefined;
+  var workers: Map<QueueNames, Worker> | undefined;
+}

packages/service/common/redis/index.ts

@@ -0,0 +1,27 @@
+import Redis from 'ioredis';
+
+const REDIS_URL = process.env.REDIS_URL ?? 'redis://localhost:6379';
+
+export function newQueueRedisConnection() {
+  const redis = new Redis(REDIS_URL);
+  redis.on('connect', () => {
+    console.log('Redis connected');
+  });
+  redis.on('error', (error) => {
+    console.error('Redis connection error', error);
+  });
+  return redis;
+}
+
+export function newWorkerRedisConnection() {
+  const redis = new Redis(REDIS_URL, {
+    maxRetriesPerRequest: null
+  });
+  redis.on('connect', () => {
+    console.log('Redis connected');
+  });
+  redis.on('error', (error) => {
+    console.error('Redis connection error', error);
+  });
+  return redis;
+}

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

@@ -1,6 +1,7 @@
 import {
   DatasetCollectionTypeEnum,
-  DatasetCollectionDataProcessModeEnum
+  DatasetCollectionDataProcessModeEnum,
+  DatasetTypeEnum
 } from '@fastgpt/global/core/dataset/constants';
 import type { CreateDatasetCollectionParams } from '@fastgpt/global/core/dataset/api.d';
 import { MongoDatasetCollection } from './schema';
@@ -104,7 +105,8 @@ export const createCollectionAndInsertData = async ({
       hashRawText: hashStr(rawText),
       rawTextLength: rawText.length,
       nextSyncTime: (() => {
-        if (!dataset.autoSync) return undefined;
+        // ignore auto collections sync for website datasets
+        if (!dataset.autoSync && dataset.type === DatasetTypeEnum.websiteDataset) return undefined;
         if (
           [DatasetCollectionTypeEnum.link, DatasetCollectionTypeEnum.apiFile].includes(
             createCollectionParams.type