feat: remove buffer;fix: custom pdf parse (#4914)

c121914yu · web-flow · commit 02b214b3ec74 · 2025-05-28T21:48:10.000+08:00
* fix: doc

* fix: remove buffer

* fix: pdf parse
diff --git a/deploy/docker/docker-compose-milvus.yml b/deploy/docker/docker-compose-milvus.yml
@@ -132,15 +132,15 @@ services:
   # fastgpt
   sandbox:
     container_name: sandbox
-    image: ghcr.io/labring/fastgpt-sandbox:v4.9.10 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.9.10 # 阿里云
+    image: ghcr.io/labring/fastgpt-sandbox:v4.9.10-fix2 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.9.10-fix2 # 阿里云
     networks:
       - fastgpt
     restart: always
   fastgpt-mcp-server:
     container_name: fastgpt-mcp-server
-    image: ghcr.io/labring/fastgpt-mcp_server:v4.9.10 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.9.10 # 阿里云
+    image: ghcr.io/labring/fastgpt-mcp_server:v4.9.10-fix2 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.9.10-fix2 # 阿里云
     ports:
       - 3005:3000
     networks:
@@ -150,8 +150,8 @@ services:
       - FASTGPT_ENDPOINT=http://fastgpt:3000
   fastgpt:
     container_name: fastgpt
-    image: ghcr.io/labring/fastgpt:v4.9.10 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.9.10 # 阿里云
+    image: ghcr.io/labring/fastgpt:v4.9.10-fix2 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.9.10-fix2 # 阿里云
     ports:
       - 3000:3000
     networks:
diff --git a/deploy/docker/docker-compose-oceanbase/docker-compose.yml b/deploy/docker/docker-compose-oceanbase/docker-compose.yml
@@ -109,15 +109,15 @@ services:
   # fastgpt
   sandbox:
     container_name: sandbox
-    image: ghcr.io/labring/fastgpt-sandbox:v4.9.10 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.9.10 # 阿里云
+    image: ghcr.io/labring/fastgpt-sandbox:v4.9.10-fix2 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.9.10-fix2 # 阿里云
     networks:
       - fastgpt
     restart: always
   fastgpt-mcp-server:
     container_name: fastgpt-mcp-server
-    image: ghcr.io/labring/fastgpt-mcp_server:v4.9.10 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.9.10 # 阿里云
+    image: ghcr.io/labring/fastgpt-mcp_server:v4.9.10-fix2 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.9.10-fix2 # 阿里云
     ports:
       - 3005:3000
     networks:
@@ -127,8 +127,8 @@ services:
       - FASTGPT_ENDPOINT=http://fastgpt:3000
   fastgpt:
     container_name: fastgpt
-    image: ghcr.io/labring/fastgpt:v4.9.10 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.9.10 # 阿里云
+    image: ghcr.io/labring/fastgpt:v4.9.10-fix2 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.9.10-fix2 # 阿里云
     ports:
       - 3000:3000
     networks:
diff --git a/deploy/docker/docker-compose-pgvector.yml b/deploy/docker/docker-compose-pgvector.yml
@@ -96,15 +96,15 @@ services:
   # fastgpt
   sandbox:
     container_name: sandbox
-    image: ghcr.io/labring/fastgpt-sandbox:v4.9.10 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.9.10 # 阿里云
+    image: ghcr.io/labring/fastgpt-sandbox:v4.9.10-fix2 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.9.10-fix2 # 阿里云
     networks:
       - fastgpt
     restart: always
   fastgpt-mcp-server:
     container_name: fastgpt-mcp-server
-    image: ghcr.io/labring/fastgpt-mcp_server:v4.9.10 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.9.10 # 阿里云
+    image: ghcr.io/labring/fastgpt-mcp_server:v4.9.10-fix2 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.9.10-fix2 # 阿里云
     ports:
       - 3005:3000
     networks:
@@ -114,8 +114,8 @@ services:
       - FASTGPT_ENDPOINT=http://fastgpt:3000
   fastgpt:
     container_name: fastgpt
-    image: ghcr.io/labring/fastgpt:v4.9.10 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.9.10 # 阿里云
+    image: ghcr.io/labring/fastgpt:v4.9.10-fix2 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.9.10-fix2 # 阿里云
     ports:
       - 3000:3000
     networks:
diff --git a/deploy/docker/docker-compose-zilliz.yml b/deploy/docker/docker-compose-zilliz.yml
@@ -72,15 +72,15 @@ services:
 
   sandbox:
     container_name: sandbox
-    image: ghcr.io/labring/fastgpt-sandbox:v4.9.10 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.9.10 # 阿里云
+    image: ghcr.io/labring/fastgpt-sandbox:v4.9.10-fix2 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.9.10-fix2 # 阿里云
     networks:
       - fastgpt
     restart: always
   fastgpt-mcp-server:
     container_name: fastgpt-mcp-server
-    image: ghcr.io/labring/fastgpt-mcp_server:v4.9.10 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.9.10 # 阿里云
+    image: ghcr.io/labring/fastgpt-mcp_server:v4.9.10-fix2 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.9.10-fix2 # 阿里云
     ports:
       - 3005:3000
     networks:
@@ -90,8 +90,8 @@ services:
       - FASTGPT_ENDPOINT=http://fastgpt:3000
   fastgpt:
     container_name: fastgpt
-    image: ghcr.io/labring/fastgpt:v4.9.10 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.9.10 # 阿里云
+    image: ghcr.io/labring/fastgpt:v4.9.10-fix2 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.9.10-fix2 # 阿里云
     ports:
       - 3000:3000
     networks:
diff --git a/docSite/content/zh-cn/docs/development/upgrading/4910.md b/docSite/content/zh-cn/docs/development/upgrading/4910.md
@@ -15,8 +15,8 @@ weight: 790
 
 ### 2. 更新镜像 tag
 
-- 更新 FastGPT 镜像 tag: v4.9.10
-- 更新 FastGPT 商业版镜像 tag: v4.9.10
+- 更新 FastGPT 镜像 tag: v4.9.10-fix2
+- 更新 FastGPT 商业版镜像 tag: v4.9.10-fix2
 - mcp_server 无需更新
 - Sandbox 无需更新
 - AIProxy 无需更新
diff --git a/docSite/content/zh-cn/docs/development/upgrading/4911.md b/docSite/content/zh-cn/docs/development/upgrading/4911.md
@@ -20,4 +20,5 @@ weight: 789
 
 1. 工作流中，管理员声明的全局系统工具，无法进行版本管理。
 2. 工具调用节点前，有交互节点时，上下文异常。
-3. 修复备份导入，小于 1000 字时，无法分块问题。
+3. 修复备份导入，小于 1000 字时，无法分块问题。
+4. 自定义 PDF 解析，无法保存 base64 图片。
diff --git a/packages/service/common/buffer/rawText/controller.ts b/packages/service/common/buffer/rawText/controller.ts
@@ -2,6 +2,9 @@ import { retryFn } from '@fastgpt/global/common/system/utils';
 import { connectionMongo } from '../../mongo';
 import { MongoRawTextBufferSchema, bucketName } from './schema';
 import { addLog } from '../../system/log';
+import { setCron } from '../../system/cron';
+import { checkTimerLock } from '../../system/timerLock/utils';
+import { TimerIdEnum } from '../../system/timerLock/constants';
 
 const getGridBucket = () => {
   return new connectionMongo.mongo.GridFSBucket(connectionMongo.connection.db!, {
@@ -137,3 +140,40 @@ export const updateRawTextBufferExpiredTime = async ({
     );
   });
 };
+
+export const clearExpiredRawTextBufferCron = async () => {
+  const clearExpiredRawTextBuffer = async () => {
+    addLog.debug('Clear expired raw text buffer start');
+    const gridBucket = getGridBucket();
+
+    return retryFn(async () => {
+      const data = await MongoRawTextBufferSchema.find(
+        {
+          'metadata.expiredTime': { $lt: new Date() }
+        },
+        '_id'
+      ).lean();
+
+      for (const item of data) {
+        await gridBucket.delete(item._id);
+      }
+      addLog.debug('Clear expired raw text buffer end');
+    });
+  };
+
+  setCron('*/10 * * * *', async () => {
+    if (
+      await checkTimerLock({
+        timerId: TimerIdEnum.clearExpiredRawTextBuffer,
+        lockMinuted: 9
+      })
+    ) {
+      try {
+        await clearExpiredRawTextBuffer();
+      } catch (error) {
+        addLog.error('clearExpiredRawTextBufferCron error', error);
+      }
+    }
+  });
+  clearExpiredRawTextBuffer();
+};
diff --git a/packages/service/common/file/read/utils.ts b/packages/service/common/file/read/utils.ts
@@ -110,7 +110,7 @@ export const readRawContentByFileBuffer = async ({
 
     return {
       rawText: text,
-      formatText: rawText,
+      formatText: text,
       imageList
     };
   };
diff --git a/packages/service/common/system/timerLock/constants.ts b/packages/service/common/system/timerLock/constants.ts
@@ -5,7 +5,8 @@ export enum TimerIdEnum {
   clearExpiredSubPlan = 'clearExpiredSubPlan',
   updateStandardPlan = 'updateStandardPlan',
   scheduleTriggerApp = 'scheduleTriggerApp',
-  notification = 'notification'
+  notification = 'notification',
+  clearExpiredRawTextBuffer = 'clearExpiredRawTextBuffer'
 }
 
 export enum LockNotificationEnum {
diff --git a/projects/app/src/instrumentation.ts b/projects/app/src/instrumentation.ts
@@ -39,6 +39,12 @@ export async function register() {
       systemStartCb();
       initGlobalVariables();
 
+      try {
+        await preLoadWorker();
+      } catch (error) {
+        console.error('Preload worker error', error);
+      }
+
       // Connect to MongoDB
       await connectMongo(connectionMongo, MONGO_URL);
       connectMongo(connectionLogMongo, MONGO_LOG_URL);
@@ -54,12 +60,6 @@ export async function register() {
       startCron();
       startTrainingQueue(true);
 
-      try {
-        await preLoadWorker();
-      } catch (error) {
-        console.error('Preload worker error', error);
-      }
-
       console.log('Init system success');
     }
   } catch (error) {
diff --git a/projects/app/src/service/common/system/cron.ts b/projects/app/src/service/common/system/cron.ts
@@ -11,6 +11,7 @@ import { checkTimerLock } from '@fastgpt/service/common/system/timerLock/utils';
 import { TimerIdEnum } from '@fastgpt/service/common/system/timerLock/constants';
 import { addHours } from 'date-fns';
 import { getScheduleTriggerApp } from '@/service/core/app/utils';
+import { clearExpiredRawTextBufferCron } from '@fastgpt/service/common/buffer/rawText/controller';
 
 // Try to run train every minute
 const setTrainingQueueCron = () => {
@@ -83,4 +84,5 @@ export const startCron = () => {
   setClearTmpUploadFilesCron();
   clearInvalidDataCron();
   scheduleTriggerAppCron();
+  clearExpiredRawTextBufferCron();
 };

Original file line number	Diff line number	Diff line change
`@@ -5,7 +5,8 @@ export enum TimerIdEnum {`
`5`	`5`	`clearExpiredSubPlan = 'clearExpiredSubPlan',`
`6`	`6`	`updateStandardPlan = 'updateStandardPlan',`
`7`	`7`	`scheduleTriggerApp = 'scheduleTriggerApp',`
`8`		`- notification = 'notification'`
	`8`	`+ notification = 'notification',`
	`9`	`+ clearExpiredRawTextBuffer = 'clearExpiredRawTextBuffer'`
`9`	`10`	`}`
`10`	`11`
`11`	`12`	`export enum LockNotificationEnum {`