Perf worker

deploy/templates/docker-compose.prod.yml

@@ -157,6 +157,7 @@ ${{vec.db}}
         condition: service_healthy
     restart: always
     environment:
+      # 完整变量请参考: https://github.com/labring/FastGPT/blob/main/projects/app/.env.template
       <<: [*x-share-db-config, *x-vec-config, *x-log-config]
       HOSTNAME: 0.0.0.0
       # ==================== 基础配置 ====================
@@ -168,8 +169,8 @@ ${{vec.db}}
       DEFAULT_ROOT_PSW: *x-default-root-psw
       # 数据库最大连接数
       DB_MAX_LINK: 5
-      # 自动同步索引（0 表示不同步）
-      SYNC_INDEX: 1
+      # 自动同步索引
+      SYNC_INDEX: true
       TOKEN_KEY: fastgpt
       # 文件阅读时的密钥
       FILE_TOKEN_KEY: filetokenkey
@@ -207,30 +208,6 @@ ${{vec.db}}
       # ==================== 日志与监控 ====================
       # 传递给 OTLP 收集器的服务名称
       LOG_OTEL_SERVICE_NAME: fastgpt-client
-
-      # ==================== 安全与运行限制 ====================
-      # 启动 IP 限流（true）；部分接口启用 IP 限流策略以防止异常请求
-      USE_IP_LIMIT: false
-      # 工作流最大运行次数，避免极端死循环
-      WORKFLOW_MAX_RUN_TIMES: 1000
-      # 循环最大运行次数，避免极端死循环
-      WORKFLOW_MAX_LOOP_TIMES: 100
-      # 服务器接收请求的最大大小（MB）
-      SERVICE_REQUEST_MAX_CONTENT_LENGTH: 10
-      # 启用内网 IP 检查
-      CHECK_INTERNAL_IP: false
-      # ==================== 上传与账号策略 ====================
-      # 最大上传文件大小（MB）
-      UPLOAD_FILE_MAX_SIZE: 1000
-      # 最大上传文件数量
-      UPLOAD_FILE_MAX_AMOUNT: 1000
-      # LLM 请求追踪保留时长（小时）
-      LLM_REQUEST_TRACKING_RETENTION_HOURS: 6
-      # ==================== 功能开关与特殊配置 ====================
-      # 自定义跨域；不配置时默认允许所有跨域（逗号分割）
-      ALLOWED_ORIGINS: 
-      # HTML 转 Markdown 最大字符数（超过后不执行转换）
-      MAX_HTML_TRANSFORM_CHARS: 1000000
     volumes:
       - ./config.json:/app/data/config.json
   fastgpt-code-sandbox:

document/content/self-host/upgrading/4-15/4150.mdx

@@ -3,12 +3,27 @@ title: 'V4.15.0(进行中)'
 description: 'FastGPT V4.15.0 更新说明'
 ---
 
+## 升级指南
+
+### 环境变量变更
+
+```bash
+# fastgpt-app, fastgpt-pro 可增加文件解析并发线程数
+# 线程最大数量
+PARSE_FILE_WORKERS=10
+# 文件解析单任务超时时间（秒）
+PARSE_FILE_TIMEOUT_SECONDS=300
+# 自动同步 mongo 数据库索引, 改成 boolean 字符串值，而不是 0 和 1
+SYNC_INDEX=true
+```
+
 ## 🚀 新增内容
 
 1. 新增循环节点，弃用旧的批量执行。
 2. 全局变量输入框支持输入 object 类型数据。
 3. 工具调用模式下，如果开启了虚拟机功能，用户对话框上传的文件会直接注入到虚拟机中。
 4. 第三方知识库接入钉钉知识库。
+5. 增加文件解析/HTML转Markdown/文本切块 worker pool，避免并发太高导致资源耗尽，可通过环境变量调整其 pool 数量。
 
 ## ⚙️ 优化
 
@@ -27,4 +42,4 @@ description: 'FastGPT V4.15.0 更新说明'
 
 1. 重新调整代码结构，升级 nextjs 最新版，切换至 turbopack 构建，提高构建速度；升级容器默认 node 至 24。
 2. 优化 Agent tool 声明和运行，统一所有 tool 的声明和运行方式。
-3. 文件上传内容从 system prompt 中放到 user message 中，提高 cache 命中率
+3. 文件上传内容从 system prompt 中放到 user message 中，提高 cache 命中率。

document/data/doc-last-modified.json

@@ -95,6 +95,8 @@
   "content/introduction/guide/knowledge_base/collection_tags.mdx": "2026-04-26T21:08:47+08:00",
   "content/introduction/guide/knowledge_base/dataset_engine.en.mdx": "2026-04-26T21:08:47+08:00",
   "content/introduction/guide/knowledge_base/dataset_engine.mdx": "2026-04-26T21:08:47+08:00",
+  "content/introduction/guide/knowledge_base/dingtalk_dataset.en.mdx": "2026-04-29T20:39:24+08:00",
+  "content/introduction/guide/knowledge_base/dingtalk_dataset.mdx": "2026-04-29T20:39:24+08:00",
   "content/introduction/guide/knowledge_base/lark_dataset.en.mdx": "2026-04-26T21:08:47+08:00",
   "content/introduction/guide/knowledge_base/lark_dataset.mdx": "2026-04-26T21:08:47+08:00",
   "content/introduction/guide/knowledge_base/rag.en.mdx": "2026-04-26T21:08:47+08:00",
@@ -252,7 +254,7 @@
   "content/self-host/upgrading/4-14/41481.mdx": "2026-04-26T21:08:47+08:00",
   "content/self-host/upgrading/4-14/4149.en.mdx": "2026-04-26T21:08:47+08:00",
   "content/self-host/upgrading/4-14/4149.mdx": "2026-04-26T21:08:47+08:00",
-  "content/self-host/upgrading/4-15/4150.mdx": "2026-04-29T14:53:45+08:00",
+  "content/self-host/upgrading/4-15/4150.mdx": "2026-04-29T21:00:20+08:00",
   "content/self-host/upgrading/outdated/40.en.mdx": "2026-04-26T21:08:47+08:00",
   "content/self-host/upgrading/outdated/40.mdx": "2026-04-26T21:08:47+08:00",
   "content/self-host/upgrading/outdated/41.en.mdx": "2026-04-26T21:08:47+08:00",
@@ -393,8 +395,8 @@
   "content/self-host/upgrading/outdated/499.mdx": "2026-04-26T21:08:47+08:00",
   "content/self-host/upgrading/upgrade-intruction.en.mdx": "2026-04-26T21:08:47+08:00",
   "content/self-host/upgrading/upgrade-intruction.mdx": "2026-04-26T21:08:47+08:00",
-  "content/toc.en.mdx": "2026-04-26T21:28:27+08:00",
-  "content/toc.mdx": "2026-04-28T18:03:38+08:00",
+  "content/toc.en.mdx": "2026-04-29T20:39:24+08:00",
+  "content/toc.mdx": "2026-04-29T20:39:24+08:00",
   "content/use-cases/app-cases/dalle3.en.mdx": "2026-04-26T21:08:47+08:00",
   "content/use-cases/app-cases/dalle3.mdx": "2026-04-26T21:08:47+08:00",
   "content/use-cases/app-cases/english_essay_correction_bot.en.mdx": "2026-04-26T21:08:47+08:00",

packages/global/common/system/constants.ts

@@ -9,3 +9,4 @@ export const DEFAULT_USER_AVATAR = '/imgs/avatar/BlueAvatar.svg';
 export const isDevEnv = process.env.NODE_ENV === 'development';
 export const isProduction = process.env.NODE_ENV === 'production';
 export const isTestEnv = process.env.NODE_ENV === 'test';
+export const isPhaseProductionBuild = process.env.NEXT_PHASE === 'phase-production-build';

packages/global/common/system/types/index.ts

@@ -1,13 +1,11 @@
 import type { SubPlanType } from '../../../support/wallet/sub/type';
-import { StandSubPlanLevelMapType } from '../../../support/wallet/sub/type';
 import type {
   LLMModelItemType,
   EmbeddingModelItemType,
   TTSModelType,
   STTModelType,
   RerankModelItemType
 } from '../../../core/ai/model.schema';
-import { SubTypeEnum } from '../../../support/wallet/sub/constants';
 
 export type NavbarItemType = {
   id: string;
@@ -153,7 +151,7 @@ export type FastGPTFeConfigsType = {
 
 export type SystemEnvType = {
   openapiPrefix?: string;
-  tokenWorkers: number; // token count max worker
+  tokenWorkers: number; // token count max worker (min 10, max 1000)
 
   datasetParseMaxProcess: number;
   vectorMaxProcess: number;

packages/service/common/mongo/index.ts

@@ -8,6 +8,7 @@ import type {
   PipelineStage
 } from 'mongoose';
 import mongoose, { Mongoose } from 'mongoose';
+import { env } from '../../env';
 
 const logger = getLogger(LogCategories.INFRA.MONGO);
 
@@ -21,8 +22,8 @@ export type {
   PipelineStage
 };
 
-export const MONGO_URL = process.env.MONGODB_URI as string;
-export const MONGO_LOG_URL = (process.env.MONGODB_LOG_URI ?? process.env.MONGODB_URI) as string;
+export const MONGO_URL = env.MONGODB_URI;
+export const MONGO_LOG_URL = env.MONGODB_LOG_URI ?? env.MONGODB_URI;
 
 export const connectionMongo = (() => {
   if (!global.mongodb) {
@@ -156,8 +157,8 @@ export const getMongoLogModel = <T>(name: string, schema: mongoose.Schema): Mode
 const syncMongoIndex = async (model: Model<any>) => {
   if (
     process.env.NODE_ENV === 'test' ||
-    process.env.SYNC_INDEX === '0' ||
     process.env.NEXT_PHASE === 'phase-production-build' ||
+    !env.SYNC_INDEX ||
     !MONGO_URL
   ) {
     return;

packages/service/common/secret/aes256gcm.ts

@@ -1,6 +1,7 @@
 import crypto from 'crypto';
-import { AES256_SECRET_KEY } from './constants';
+import { env } from '../../env';
 
+const AES256_SECRET_KEY = env.AES256_SECRET_KEY;
 export const encryptSecret = (text: string) => {
   const iv = crypto.randomBytes(16);
   const key = crypto.scryptSync(AES256_SECRET_KEY, 'salt', 32);

packages/service/common/string/utils.ts

@@ -1,11 +1,22 @@
-import { WorkerNameEnum, runWorker } from '../../worker/utils';
+import { env } from '../../env';
+import { WorkerNameEnum, getWorkerController } from '../../worker/utils';
 import { type ImageType } from '../../worker/readFile/type';
 
 export const htmlToMarkdown = async (html?: string | null) => {
-  const md = await runWorker<{
-    rawText: string;
-    imageList: ImageType[];
-  }>(WorkerNameEnum.htmlStr2Md, { html: html || '' });
+  const workerController = getWorkerController<
+    { html: string },
+    {
+      rawText: string;
+      imageList: ImageType[];
+    }
+  >({
+    name: WorkerNameEnum.htmlStr2Md,
+    maxReservedThreads: env.HTML_TO_MARKDOWN_WORKERS,
+    taskTimeoutMs: 300000,
+    maxTasksPerWorker: 100
+  });
+
+  const md = await workerController.run({ html: html || '' });
 
   return md.rawText;
 };