Skip to content

赵月辉 / fastgpt-migrated

Go to a project
Commit 87b0bca3 by Archer Committed by GitHub
Options

Doc (#6493) 

* cloud doc

* doc refactor

* doc move

* seo

* remove doc

* yml

* doc

* fix: tsconfig

* fix: tsconfig
parent 6b613595
Showing with 3387 additions and 3494 deletions
README.md
......@@ -24,7 +24,7 @@ FastGPT 是一个 AI Agent 构建平台，提供开箱即用的数据处理、
<a href="https://doc.fastgpt.io/docs/introduction">
<img height="21" src="https://img.shields.io/badge/相关文档-7d09f1?style=flat-square" alt="document">
</a>
<a href="https://doc.fastgpt.io/docs/introduction/development/intro">
<a href="https://doc.fastgpt.io/docs/self-host/dev">
<img height="21" src="https://img.shields.io/badge/本地开发-%23d4eaf7?style=flat-square&logo=xcode&logoColor=7d09f1" alt="development">
</a>
<a href="/#-%E7%9B%B8%E5%85%B3%E9%A1%B9%E7%9B%AE">
......@@ -47,7 +47,7 @@ docker compose up -d
完全启动后，可通过`http://localhost:3000`访问 FastGPT，默认账号为`root`，密码为`1234`。
如果你遇到问题，可以[查看完整 Docker 部署教程](https://doc.fastgpt.io/docs/introduction/development/docker)
如果你遇到问题，可以[查看完整 Docker 部署教程](https://doc.fastgpt.io/docs/self-host/deploy/docker)
## 🛸 使用方式
......@@ -55,7 +55,7 @@ docker compose up -d
如果你不需要私有化部署，可以直接使用我们提供的云服务版本，地址为：[fastgpt.io](https://fastgpt.io/)
- **社区自托管版本**
可以使用[Docker](https://doc.fastgpt.io/docs/introduction/development/docker)快速部署，也可以使用[Sealos Cloud](https://doc.fastgpt.io/docs/introduction/development/sealos) 来一键部署FastGPT。
可以使用[Docker](https://doc.fastgpt.io/docs/self-host/deploy/docker)快速部署，也可以使用[Sealos Cloud](https://doc.fastgpt.io/docs/self-host/deploy/sealos) 来一键部署FastGPT。
- **商业版**
如果你需要更完整的功能，或深度的服务支持，可以选择我们的[商业版](https://doc.fastgpt.io/docs/introduction/commercial)。我们除了提供完整的软件外，还提供相应的场景落地辅导，具体可提交[商业咨询](https://fael3z0zfze.feishu.cn/share/base/form/shrcnjJWtKqjOI9NbQTzhNyzljc)
......@@ -115,7 +115,7 @@ docker compose up -d
## 💪 我们的项目 & 链接
- [快速开始本地开发](https://doc.fastgpt.io/docs/introduction/development/intro/)
- [快速开始本地开发](https://doc.fastgpt.io/docs/self-host/dev/)
- [OpenAPI 文档](https://doc.fastgpt.io/docs/openapi/intro)
- [FastGPT-plugin](https://github.com/labring/fastgpt-plugin)
- [AI Proxy: 模型聚合负载均衡服务](https://github.com/labring/aiproxy)
......
README_en.md
......@@ -24,7 +24,7 @@ FastGPT is an AI Agent building platform that provides out-of-the-box capabiliti
<a href="https://doc.fastgpt.io/docs/introduction">
<img height="21" src="https://img.shields.io/badge/Documentation-7d09f1?style=flat-square" alt="document">
</a>
<a href="https://doc.fastgpt.io/docs/introduction/development/intro">
<a href="https://doc.fastgpt.io/docs/self-host/dev">
<img height="21" src="https://img.shields.io/badge/Local_Development-%23d4eaf7?style=flat-square&logo=xcode&logoColor=7d09f1" alt="development">
</a>
<a href="#-our-projects--links">
......@@ -47,7 +47,7 @@ docker compose up -d
After fully started, you can access FastGPT at `http://localhost:3000`. The default account is `root` and the password is `1234`.
If you encounter any issues, you can [view the complete Docker deployment tutorial](https://doc.fastgpt.io/docs/introduction/development/docker)
If you encounter any issues, you can [view the complete Docker deployment tutorial](https://doc.fastgpt.io/docs/self-host/deploy/docker)
## 🛸 Usage
......@@ -55,7 +55,7 @@ If you encounter any issues, you can [view the complete Docker deployment tutori
If you don't need private deployment, you can directly use our cloud service at: [fastgpt.io](https://fastgpt.io/)
- **Community Self-Hosted Version**
You can quickly deploy using [Docker](https://doc.fastgpt.io/docs/introduction/development/docker) or use [Sealos Cloud](https://doc.fastgpt.io/docs/introduction/development/sealos) to deploy FastGPT with one click.
You can quickly deploy using [Docker](https://doc.fastgpt.io/docs/self-host/deploy/docker) or use [Sealos Cloud](https://doc.fastgpt.io/docs/self-host/deploy/sealos) to deploy FastGPT with one click.
- **Commercial Version**
If you need more complete features or in-depth service support, you can choose our [Commercial Version](https://doc.fastgpt.io/docs/introduction/commercial). In addition to providing complete software, we also offer implementation guidance for specific scenarios. You can submit a [commercial consultation](https://fael3z0zfze.feishu.cn/share/base/form/shrcnjJWtKqjOI9NbQTzhNyzljc).
......@@ -115,7 +115,7 @@ If you encounter any issues, you can [view the complete Docker deployment tutori
## 💪 Our Projects & Links
- [Quick Start Local Development](https://doc.fastgpt.io/docs/introduction/development/intro/)
- [Quick Start Local Development](https://doc.fastgpt.io/docs/self-host/dev/)
- [OpenAPI Documentation](https://doc.fastgpt.io/docs/openapi/intro)
- [FastGPT-plugin](https://github.com/labring/fastgpt-plugin)
- [AI Proxy: Model Aggregation Load Balancing Service](https://github.com/labring/aiproxy)
......
README_id.md
......@@ -24,7 +24,7 @@ FastGPT adalah platform pembangunan AI Agent yang menyediakan kemampuan siap pak
<a href="https://doc.fastgpt.io/docs/introduction">
<img height="21" src="https://img.shields.io/badge/Dokumentasi-7d09f1?style=flat-square" alt="document">
</a>
<a href="https://doc.fastgpt.io/docs/introduction/development/intro">
<a href="https://doc.fastgpt.io/docs/self-host/dev">
<img height="21" src="https://img.shields.io/badge/Pengembangan_Lokal-%23d4eaf7?style=flat-square&logo=xcode&logoColor=7d09f1" alt="development">
</a>
<a href="#-proyek--tautan-kami">
......@@ -47,7 +47,7 @@ docker compose up -d
Setelah sepenuhnya aktif, Anda dapat mengakses FastGPT di `http://localhost:3000`. Akun default adalah `root` dan kata sandinya adalah `1234`.
Jika Anda menghadapi masalah, Anda dapat [melihat tutorial penyebaran Docker lengkap](https://doc.fastgpt.io/docs/introduction/development/docker)
Jika Anda menghadapi masalah, Anda dapat [melihat tutorial penyebaran Docker lengkap](https://doc.fastgpt.io/docs/self-host/deploy/docker)
## 🛸 Cara Penggunaan
......@@ -55,7 +55,7 @@ Jika Anda menghadapi masalah, Anda dapat [melihat tutorial penyebaran Docker len
Jika Anda tidak memerlukan penyebaran privat, Anda dapat langsung menggunakan layanan cloud kami di: [fastgpt.io](https://fastgpt.io/)
- **Versi Self-Hosted Komunitas**
Anda dapat menyebarkan dengan cepat menggunakan [Docker](https://doc.fastgpt.io/docs/introduction/development/docker) atau menggunakan [Sealos Cloud](https://doc.fastgpt.io/docs/introduction/development/sealos) untuk menyebarkan FastGPT dengan satu klik.
Anda dapat menyebarkan dengan cepat menggunakan [Docker](https://doc.fastgpt.io/docs/self-host/deploy/docker) atau menggunakan [Sealos Cloud](https://doc.fastgpt.io/docs/self-host/deploy/sealos) untuk menyebarkan FastGPT dengan satu klik.
- **Versi Komersial**
Jika Anda membutuhkan fitur yang lebih lengkap atau dukungan layanan mendalam, Anda dapat memilih [Versi Komersial](https://doc.fastgpt.io/docs/introduction/commercial). Selain menyediakan perangkat lunak lengkap, kami juga menyediakan panduan implementasi untuk skenario tertentu. Anda dapat mengirimkan [konsultasi komersial](https://fael3z0zfze.feishu.cn/share/base/form/shrcnjJWtKqjOI9NbQTzhNyzljc).
......@@ -115,7 +115,7 @@ Jika Anda menghadapi masalah, Anda dapat [melihat tutorial penyebaran Docker len
## 💪 Proyek & Tautan Kami
- [Mulai Cepat Pengembangan Lokal](https://doc.fastgpt.io/docs/introduction/development/intro/)
- [Mulai Cepat Pengembangan Lokal](https://doc.fastgpt.io/docs/self-host/dev/)
- [Dokumentasi OpenAPI](https://doc.fastgpt.io/docs/openapi/intro)
- [FastGPT-plugin](https://github.com/labring/fastgpt-plugin)
- [AI Proxy: Layanan Load Balancing Agregasi Model](https://github.com/labring/aiproxy)
......
README_ja.md
......@@ -24,7 +24,7 @@ FastGPT 縺ｯ AI Agent 讒狗ｯ峨繝ｩ繝ヨ繝輔か繝ｼ繝縺ｧ縺ゅｊ縲√☆縺舌↓菴ｿ縺医
<a href="https://doc.fastgpt.io/docs/introduction">
<img height="21" src="https://img.shields.io/badge/ドキュメント-7d09f1?style=flat-square" alt="document">
</a>
<a href="https://doc.fastgpt.io/docs/introduction/development/intro">
<a href="https://doc.fastgpt.io/docs/self-host/dev">
<img height="21" src="https://img.shields.io/badge/ローカル開発-%23d4eaf7?style=flat-square&logo=xcode&logoColor=7d09f1" alt="development">
</a>
<a href="#-プロジェクトとリンク">
......@@ -47,7 +47,7 @@ docker compose up -d
完全に起動した後、`http://localhost:3000` で FastGPT にアクセスできます。デフォルトのアカウントは `root`、パスワードは `1234` です。
問題が発生した場合は、[Docker デプロイの完全チュートリアル](https://doc.fastgpt.io/docs/introduction/development/docker)をご覧ください。
問題が発生した場合は、[Docker デプロイの完全チュートリアル](https://doc.fastgpt.io/docs/self-host/deploy/docker)をご覧ください。
## 🛸 利用方法
......@@ -55,7 +55,7 @@ docker compose up -d
プライベートデプロイが不要な場合は、クラウドサービスを直接ご利用いただけます：[fastgpt.io](https://fastgpt.io/)
- **コミュニティセルフホスト版**
[Docker](https://doc.fastgpt.io/docs/introduction/development/docker) で素早くデプロイするか、[Sealos Cloud](https://doc.fastgpt.io/docs/introduction/development/sealos) でワンクリックデプロイが可能です。
[Docker](https://doc.fastgpt.io/docs/self-host/deploy/docker) で素早くデプロイするか、[Sealos Cloud](https://doc.fastgpt.io/docs/self-host/deploy/sealos) でワンクリックデプロイが可能です。
- **商用版**
より完全な機能や深いサービスサポートが必要な場合は、[商用版](https://doc.fastgpt.io/docs/introduction/commercial)をお選びいただけます。完全なソフトウェアの提供に加え、シナリオに応じた導入ガイダンスも提供しています。[商用相談](https://fael3z0zfze.feishu.cn/share/base/form/shrcnjJWtKqjOI9NbQTzhNyzljc)からお問い合わせください。
......@@ -115,7 +115,7 @@ docker compose up -d
## 💪 プロジェクトとリンク
- [クイックスタート ローカル開発](https://doc.fastgpt.io/docs/introduction/development/intro/)
- [クイックスタート ローカル開発](https://doc.fastgpt.io/docs/self-host/dev/)
- [OpenAPI ドキュメント](https://doc.fastgpt.io/docs/openapi/intro)
- [FastGPT-plugin](https://github.com/labring/fastgpt-plugin)
- [AI Proxy: モデル集約ロードバランシングサービス](https://github.com/labring/aiproxy)
......
README_th.md
......@@ -24,7 +24,7 @@ FastGPT เป็นแพลตฟอร์มสำหรับสร้าง
<a href="https://doc.fastgpt.io/docs/introduction">
<img height="21" src="https://img.shields.io/badge/เอกสาร-7d09f1?style=flat-square" alt="document">
</a>
<a href="https://doc.fastgpt.io/docs/introduction/development/intro">
<a href="https://doc.fastgpt.io/docs/self-host/dev">
<img height="21" src="https://img.shields.io/badge/พัฒนาในเครื่อง-%23d4eaf7?style=flat-square&logo=xcode&logoColor=7d09f1" alt="development">
</a>
<a href="#-โปรเจกต์และลิงก์ของเรา">
......@@ -47,7 +47,7 @@ docker compose up -d
เมื่อเริ่มต้นสมบูรณ์แล้ว คุณสามารถเข้าถึง FastGPT ที่ `http://localhost:3000` บัญชีเริ่มต้นคือ `root` และรหัสผ่านคือ `1234`
หากคุณพบปัญหา คุณสามารถ [ดูบทแนะนำการติดตั้ง Docker ฉบับสมบูรณ์](https://doc.fastgpt.io/docs/introduction/development/docker)
หากคุณพบปัญหา คุณสามารถ [ดูบทแนะนำการติดตั้ง Docker ฉบับสมบูรณ์](https://doc.fastgpt.io/docs/self-host/deploy/docker)
## 🛸 วิธีการใช้งาน
......@@ -55,7 +55,7 @@ docker compose up -d
หากคุณไม่ต้องการติดตั้งแบบส่วนตัว คุณสามารถใช้บริการคลาวด์ของเราได้โดยตรงที่: [fastgpt.io](https://fastgpt.io/)
- **เวอร์ชันโฮสต์ตัวเองของชุมชน**
คุณสามารถติดตั้งได้อย่างรวดเร็วโดยใช้ [Docker](https://doc.fastgpt.io/docs/introduction/development/docker) หรือใช้ [Sealos Cloud](https://doc.fastgpt.io/docs/introduction/development/sealos) เพื่อติดตั้ง FastGPT ด้วยคลิกเดียว
คุณสามารถติดตั้งได้อย่างรวดเร็วโดยใช้ [Docker](https://doc.fastgpt.io/docs/self-host/deploy/docker) หรือใช้ [Sealos Cloud](https://doc.fastgpt.io/docs/self-host/deploy/sealos) เพื่อติดตั้ง FastGPT ด้วยคลิกเดียว
- **เวอร์ชันพาณิชย์**
หากคุณต้องการคุณสมบัติที่สมบูรณ์มากขึ้นหรือการสนับสนุนบริการเชิงลึก คุณสามารถเลือก [เวอร์ชันพาณิชย์](https://doc.fastgpt.io/docs/introduction/commercial) นอกจากการให้ซอฟต์แวร์ที่สมบูรณ์ เรายังให้คำแนะนำการนำไปใช้สำหรับสถานการณ์เฉพาะ คุณสามารถส่ง[ปรึกษาธุรกิจ](https://fael3z0zfze.feishu.cn/share/base/form/shrcnjJWtKqjOI9NbQTzhNyzljc)
......@@ -115,7 +115,7 @@ docker compose up -d
## 💪 โปรเจกต์และลิงก์ของเรา
- [เริ่มต้นพัฒนาในเครื่อง](https://doc.fastgpt.io/docs/introduction/development/intro/)
- [เริ่มต้นพัฒนาในเครื่อง](https://doc.fastgpt.io/docs/self-host/dev/)
- [เอกสาร OpenAPI](https://doc.fastgpt.io/docs/openapi/intro)
- [FastGPT-plugin](https://github.com/labring/fastgpt-plugin)
- [AI Proxy: บริการ Load Balancing การรวมโมเดล](https://github.com/labring/aiproxy)
......
README_vi.md
......@@ -24,7 +24,7 @@ FastGPT là nền tảng xây dựng AI Agent cung cấp khả năng sẵn sàng
<a href="https://doc.fastgpt.io/docs/introduction">
<img height="21" src="https://img.shields.io/badge/Tài_Liệu-7d09f1?style=flat-square" alt="document">
</a>
<a href="https://doc.fastgpt.io/docs/introduction/development/intro">
<a href="https://doc.fastgpt.io/docs/self-host/dev">
<img height="21" src="https://img.shields.io/badge/Phát_Triển_Local-%23d4eaf7?style=flat-square&logo=xcode&logoColor=7d09f1" alt="development">
</a>
<a href="#-dự-án--liên-kết-của-chúng-tôi">
......@@ -47,7 +47,7 @@ docker compose up -d
Sau khi khởi động hoàn tất, bạn có thể truy cập FastGPT tại `http://localhost:3000`. Tài khoản mặc định là `root` và mật khẩu là `1234`.
Nếu bạn gặp vấn đề, bạn có thể [xem hướng dẫn triển khai Docker đầy đủ](https://doc.fastgpt.io/docs/introduction/development/docker)
Nếu bạn gặp vấn đề, bạn có thể [xem hướng dẫn triển khai Docker đầy đủ](https://doc.fastgpt.io/docs/self-host/deploy/docker)
## 🛸 Cách Sử Dụng
......@@ -55,7 +55,7 @@ Nếu bạn gặp vấn đề, bạn có thể [xem hướng dẫn triển khai
Nếu bạn không cần triển khai riêng, bạn có thể sử dụng trực tiếp dịch vụ đám mây của chúng tôi tại: [fastgpt.io](https://fastgpt.io/)
- **Phiên Bản Tự Host Cộng Đồng**
Bạn có thể triển khai nhanh chóng bằng [Docker](https://doc.fastgpt.io/docs/introduction/development/docker) hoặc sử dụng [Sealos Cloud](https://doc.fastgpt.io/docs/introduction/development/sealos) để triển khai FastGPT bằng một cú nhấp chuột.
Bạn có thể triển khai nhanh chóng bằng [Docker](https://doc.fastgpt.io/docs/self-host/deploy/docker) hoặc sử dụng [Sealos Cloud](https://doc.fastgpt.io/docs/self-host/deploy/sealos) để triển khai FastGPT bằng một cú nhấp chuột.
- **Phiên Bản Thương Mại**
Nếu bạn cần các tính năng đầy đủ hơn hoặc hỗ trợ dịch vụ chuyên sâu, bạn có thể chọn [Phiên Bản Thương Mại](https://doc.fastgpt.io/docs/introduction/commercial). Ngoài việc cung cấp phần mềm đầy đủ, chúng tôi còn cung cấp hướng dẫn triển khai cho các kịch bản cụ thể. Bạn có thể gửi [tư vấn thương mại](https://fael3z0zfze.feishu.cn/share/base/form/shrcnjJWtKqjOI9NbQTzhNyzljc).
......@@ -115,7 +115,7 @@ Nếu bạn gặp vấn đề, bạn có thể [xem hướng dẫn triển khai
## 💪 Dự Án & Liên Kết Của Chúng Tôi
- [Bắt Đầu Phát Triển Địa Phương](https://doc.fastgpt.io/docs/introduction/development/intro/)
- [Bắt Đầu Phát Triển Địa Phương](https://doc.fastgpt.io/docs/self-host/dev/)
- [Tài Liệu OpenAPI](https://doc.fastgpt.io/docs/openapi/intro)
- [FastGPT-plugin](https://github.com/labring/fastgpt-plugin)
- [AI Proxy: Dịch Vụ Cân Bằng Tải Tổng Hợp Mô Hình](https://github.com/labring/aiproxy)
......
deploy/dev/docker-compose.cn.yml
......@@ -162,7 +162,7 @@ services:
- fastgpt
environment:
- AUTH_TOKEN=token
# @see https://fastgpt.cn/docs/introduction/development/object-storage
# @see https://fastgpt.cn/docs/self-host/config/object-storage
- STORAGE_VENDOR=minio # minio | aws-s3 | cos | oss
- STORAGE_REGION=us-east-1
- STORAGE_ACCESS_KEY_ID=minioadmin
......
deploy/dev/docker-compose.yml
......@@ -162,7 +162,7 @@ services:
- fastgpt
environment:
- AUTH_TOKEN=token
# @see https://fastgpt.cn/docs/introduction/development/object-storage
# @see https://fastgpt.cn/docs/self-host/config/object-storage
- STORAGE_VENDOR=minio # minio | aws-s3 | cos | oss
- STORAGE_REGION=us-east-1
- STORAGE_ACCESS_KEY_ID=minioadmin
......
deploy/docker/cn/docker-compose.milvus.yml
......@@ -12,7 +12,7 @@ x-share-db-config: &x-share-db-config
MONGODB_URI: mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
DB_MAX_LINK: 100
REDIS_URL: redis://default:mypassword@redis:6379
# @see https://doc.fastgpt.cn/docs/introduction/development/object-storage
# @see https://doc.fastgpt.cn/docs/self-host/config/object-storage
STORAGE_VENDOR: minio # minio | aws-s3 | cos | oss
STORAGE_REGION: us-east-1
STORAGE_ACCESS_KEY_ID: minioadmin
......
deploy/docker/cn/docker-compose.oceanbase.yml
......@@ -12,7 +12,7 @@ x-share-db-config: &x-share-db-config
MONGODB_URI: mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
DB_MAX_LINK: 100
REDIS_URL: redis://default:mypassword@redis:6379
# @see https://doc.fastgpt.cn/docs/introduction/development/object-storage
# @see https://doc.fastgpt.cn/docs/self-host/config/object-storage
STORAGE_VENDOR: minio # minio | aws-s3 | cos | oss
STORAGE_REGION: us-east-1
STORAGE_ACCESS_KEY_ID: minioadmin
......
deploy/docker/cn/docker-compose.pg.yml
......@@ -12,7 +12,7 @@ x-share-db-config: &x-share-db-config
MONGODB_URI: mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
DB_MAX_LINK: 100
REDIS_URL: redis://default:mypassword@redis:6379
# @see https://doc.fastgpt.cn/docs/introduction/development/object-storage
# @see https://doc.fastgpt.cn/docs/self-host/config/object-storage
STORAGE_VENDOR: minio # minio | aws-s3 | cos | oss
STORAGE_REGION: us-east-1
STORAGE_ACCESS_KEY_ID: minioadmin
......
deploy/docker/cn/docker-compose.seekdb.yml
......@@ -12,7 +12,7 @@ x-share-db-config: &x-share-db-config
MONGODB_URI: mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
DB_MAX_LINK: 100
REDIS_URL: redis://default:mypassword@redis:6379
# @see https://doc.fastgpt.cn/docs/introduction/development/object-storage
# @see https://doc.fastgpt.cn/docs/self-host/config/object-storage
STORAGE_VENDOR: minio # minio | aws-s3 | cos | oss
STORAGE_REGION: us-east-1
STORAGE_ACCESS_KEY_ID: minioadmin
......
deploy/docker/cn/docker-compose.zilliz.yml
......@@ -12,7 +12,7 @@ x-share-db-config: &x-share-db-config
MONGODB_URI: mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
DB_MAX_LINK: 100
REDIS_URL: redis://default:mypassword@redis:6379
# @see https://doc.fastgpt.cn/docs/introduction/development/object-storage
# @see https://doc.fastgpt.cn/docs/self-host/config/object-storage
STORAGE_VENDOR: minio # minio | aws-s3 | cos | oss
STORAGE_REGION: us-east-1
STORAGE_ACCESS_KEY_ID: minioadmin
......
deploy/docker/global/docker-compose.milvus.yml
......@@ -12,7 +12,7 @@ x-share-db-config: &x-share-db-config
MONGODB_URI: mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
DB_MAX_LINK: 100
REDIS_URL: redis://default:mypassword@redis:6379
# @see https://doc.fastgpt.cn/docs/introduction/development/object-storage
# @see https://doc.fastgpt.cn/docs/self-host/config/object-storage
STORAGE_VENDOR: minio # minio | aws-s3 | cos | oss
STORAGE_REGION: us-east-1
STORAGE_ACCESS_KEY_ID: minioadmin
......
deploy/docker/global/docker-compose.oceanbase.yml
......@@ -12,7 +12,7 @@ x-share-db-config: &x-share-db-config
MONGODB_URI: mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
DB_MAX_LINK: 100
REDIS_URL: redis://default:mypassword@redis:6379
# @see https://doc.fastgpt.cn/docs/introduction/development/object-storage
# @see https://doc.fastgpt.cn/docs/self-host/config/object-storage
STORAGE_VENDOR: minio # minio | aws-s3 | cos | oss
STORAGE_REGION: us-east-1
STORAGE_ACCESS_KEY_ID: minioadmin
......
deploy/docker/global/docker-compose.pg.yml
......@@ -12,7 +12,7 @@ x-share-db-config: &x-share-db-config
MONGODB_URI: mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
DB_MAX_LINK: 100
REDIS_URL: redis://default:mypassword@redis:6379
# @see https://doc.fastgpt.cn/docs/introduction/development/object-storage
# @see https://doc.fastgpt.cn/docs/self-host/config/object-storage
STORAGE_VENDOR: minio # minio | aws-s3 | cos | oss
STORAGE_REGION: us-east-1
STORAGE_ACCESS_KEY_ID: minioadmin
......
deploy/docker/global/docker-compose.seekdb.yml
......@@ -12,7 +12,7 @@ x-share-db-config: &x-share-db-config
MONGODB_URI: mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
DB_MAX_LINK: 100
REDIS_URL: redis://default:mypassword@redis:6379
# @see https://doc.fastgpt.cn/docs/introduction/development/object-storage
# @see https://doc.fastgpt.cn/docs/self-host/config/object-storage
STORAGE_VENDOR: minio # minio | aws-s3 | cos | oss
STORAGE_REGION: us-east-1
STORAGE_ACCESS_KEY_ID: minioadmin
......
deploy/docker/global/docker-compose.ziliiz.yml
......@@ -12,7 +12,7 @@ x-share-db-config: &x-share-db-config
MONGODB_URI: mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
DB_MAX_LINK: 100
REDIS_URL: redis://default:mypassword@redis:6379
# @see https://doc.fastgpt.cn/docs/introduction/development/object-storage
# @see https://doc.fastgpt.cn/docs/self-host/config/object-storage
STORAGE_VENDOR: minio # minio | aws-s3 | cos | oss
STORAGE_REGION: us-east-1
STORAGE_ACCESS_KEY_ID: minioadmin
......
deploy/templates/docker-compose.dev.yml
......@@ -162,7 +162,7 @@ services:
- fastgpt
environment:
- AUTH_TOKEN=token
# @see https://fastgpt.cn/docs/introduction/development/object-storage
# @see https://fastgpt.cn/docs/self-host/config/object-storage
- STORAGE_VENDOR=minio # minio | aws-s3 | cos | oss
- STORAGE_REGION=us-east-1
- STORAGE_ACCESS_KEY_ID=minioadmin
......
deploy/templates/docker-compose.prod.yml
......@@ -12,7 +12,7 @@ x-share-db-config: &x-share-db-config
MONGODB_URI: mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
DB_MAX_LINK: 100
REDIS_URL: redis://default:mypassword@redis:6379
# @see https://doc.fastgpt.cn/docs/introduction/development/object-storage
# @see https://doc.fastgpt.cn/docs/self-host/config/object-storage
STORAGE_VENDOR: minio # minio | aws-s3 | cos | oss
STORAGE_REGION: us-east-1
STORAGE_ACCESS_KEY_ID: minioadmin
......
document/README.md
......@@ -38,7 +38,7 @@ import { Alert } from '@/components/docs/Alert'; #高亮块组件
import {Redirect} from '@/components/docs/Redirect' #重定向组件，如果你希望用户点击这个文件跳转到别的文件的话，详情参考 `FAQ`的`Docker 部署问题`文档。
<Redirect to="/docs/introduction/development/docker/#faq" />
<Redirect to="/docs/self-host/deploy/docker/#faq" />
<Tabs items={['Javascript', 'Rust']}> #tabs组件用法，渲染效果参考`introduction`下`development`的`faq`文档
<Tab value="Javascript">Javascript is weird</Tab>
......
document/app/[lang]/docs/[[...slug]]/page.tsx
......@@ -5,6 +5,7 @@ import NotFound from '@/components/docs/not-found';
import { createRelativeLink } from 'fumadocs-ui/mdx';
import { getMDXComponents } from '@/mdx-components';
import { i18n } from '@/lib/i18n';
import { generateArticleSchema, generateBreadcrumbSchema } from '@/lib/schema';
// 在构建时导入静态数据
import docLastModifiedData from '@/data/doc-last-modified.json';
......@@ -36,8 +37,46 @@ export default async function Page({
// @ts-ignore
const lastModified = docLastModifiedData[filePath] || page.data.lastModified;
const homeDomain = process.env.FASTGPT_HOME_DOMAIN ?? 'https://fastgpt.io';
const domain = homeDomain.replace('https://', 'https://doc.');
const url = `${domain}${page.url}`;
// 生成面包屑导航
const breadcrumbItems = [
{ name: 'FastGPT', url: domain },
{ name: 'Docs', url: `${domain}/${lang}/docs` }
];
if (slug && slug.length > 0) {
slug.forEach((segment, index) => {
const segmentUrl = `${domain}/${lang}/docs/${slug.slice(0, index + 1).join('/')}`;
breadcrumbItems.push({ name: segment, url: segmentUrl });
});
}
// 生成结构化数据
const articleSchema = generateArticleSchema({
title: page.data.title,
description: page.data.description || '',
url,
dateModified: lastModified ? new Date(lastModified) : undefined,
lang
});
const breadcrumbSchema = generateBreadcrumbSchema({
items: breadcrumbItems
});
return (
<DocsPage
<>
<script
type="application/ld+json"
dangerouslySetInnerHTML={{ __html: JSON.stringify(articleSchema) }}
/>
<script
type="application/ld+json"
dangerouslySetInnerHTML={{ __html: JSON.stringify(breadcrumbSchema) }}
/>
<DocsPage
toc={page.data.toc}
full={page.data.full}
tableOfContent={{
......@@ -61,6 +100,7 @@ export default async function Page({
/>
</DocsBody>
</DocsPage>
</>
);
}
......@@ -75,8 +115,33 @@ export async function generateMetadata(props: {
const page = source.getPage(slug, lang);
if (!page || !page.data) notFound();
const homeDomain = process.env.FASTGPT_HOME_DOMAIN ?? 'https://fastgpt.io';
const domain = homeDomain.replace('https://', 'https://doc.');
const url = `${domain}${page.url}`;
// 构建多语言 alternates
const languages: Record<string, string> = {};
i18n.languages.forEach((locale) => {
const localePage = source.getPage(slug, locale);
if (localePage) {
languages[locale] = `${domain}/${locale}/docs/${slug?.join('/') || ''}`;
}
});
return {
title: `${page.data.title} | FastGPT`,
description: page.data.description
description: page.data.description,
alternates: {
canonical: url,
languages
},
openGraph: {
title: `${page.data.title} | FastGPT`,
description: page.data.description,
url,
siteName: 'FastGPT',
locale: lang,
type: 'article'
}
};
}
document/app/[lang]/docs/layout.tsx
......@@ -12,7 +12,7 @@ import FeishuLogoLight from '@/components/docs/feishuLogoLIght';
import FeishuLogoDark from '@/components/docs/feishuLogoDark';
import GithubLogoLight from '@/components/docs/githubLogoLight';
import GithubLogoDark from '@/components/docs/githubLogoDark';
import { BookOpen, Code, Lightbulb, CircleHelp, Scale, History } from 'lucide-react';
import { BookOpen, Code, Lightbulb, CircleHelp, Scale, History, Server } from 'lucide-react';
export default async function Layout({
params,
......@@ -31,29 +31,24 @@ export default async function Layout({
url: getLocalizedPath('/docs/introduction', lang)
},
{
icon: <Code className={iconClass} />,
title: t('common:api_reference', lang),
url: getLocalizedPath('/docs/openapi', lang)
},
{
icon: <Lightbulb className={iconClass} />,
title: t('common:use-cases', lang),
url: getLocalizedPath('/docs/use-cases', lang)
},
{
icon: <CircleHelp className={iconClass} />,
title: t('common:faq', lang),
url: getLocalizedPath('/docs/faq', lang)
icon: <Server className={iconClass} />,
title: t('common:selfHost', lang),
url: getLocalizedPath('/docs/self-host', lang)
},
{
icon: <Scale className={iconClass} />,
title: t('common:protocol', lang),
url: getLocalizedPath('/docs/protocol', lang)
icon: <Code className={iconClass} />,
title: t('common:api_reference', lang),
url: getLocalizedPath('/docs/openapi', lang)
},
{
icon: <History className={iconClass} />,
title: t('common:upgrading', lang),
url: getLocalizedPath('/docs/upgrading', lang)
icon: <CircleHelp className={iconClass} />,
title: t('common:faq', lang),
url: getLocalizedPath('/docs/faq', lang)
}
];
......@@ -116,7 +111,7 @@ export default async function Layout({
collapsible: false,
components: CustomSidebarComponents
}}
tabMode="navbar"
tabMode="sidebar"
>
<SidebarKeepOpen tabUrls={tabUrls} />
{children}
......
document/app/[lang]/layout.tsx
......@@ -5,6 +5,7 @@ import type { ReactNode } from 'react';
import type { Translations } from 'fumadocs-ui/i18n';
import CustomSearchDialog from '@/components/CustomSearchDialog';
import Script from 'next/script';
import type { Metadata } from 'next';
const inter = Inter({
subsets: ['latin']
......@@ -14,13 +15,24 @@ const zh_CN: Partial<Translations> = {
search: '搜索',
nextPage: '下一页',
previousPage: '上一页',
lastUpdate: '最后更新于',
lastUpdate: '文件更新时间',
editOnGithub: '在 GitHub 上编辑',
searchNoResult: '没有找到相关内容',
toc: '本页导航',
tocNoHeadings: '本页没有导航',
chooseLanguage: '选择语言'
};
const en: Partial<Translations> = {
search: 'Search',
nextPage: 'Next Page',
previousPage: 'Previous Page',
lastUpdate: 'File Updated',
editOnGithub: 'Edit on GitHub',
searchNoResult: 'No results found',
toc: 'On this page',
tocNoHeadings: 'No headings',
chooseLanguage: 'Choose Language'
};
const locales = [
{
......@@ -33,6 +45,84 @@ const locales = [
}
];
export async function generateMetadata({
params
}: {
params: Promise<{ lang: string }>;
}): Promise<Metadata> {
const { lang } = await params;
const homeDomain = process.env.FASTGPT_HOME_DOMAIN ?? 'https://fastgpt.io';
const domain = homeDomain.replace('https://', 'https://doc.');
const title = lang === 'zh-CN' ? 'FastGPT 文档' : 'FastGPT Documentation';
const description =
lang === 'zh-CN'
? 'FastGPT 是一个 AI Agent 构建平台，通过 Flow 提供开箱即用的数据处理、模型调用能力和可视化工作流编排。'
: 'FastGPT is an AI Agent building platform that provides out-of-the-box data processing, model invocation capabilities, and visual workflow orchestration through Flow.';
return {
title: {
default: title,
template: `%s | FastGPT`
},
description,
keywords: ['FastGPT', 'AI', 'Agent', 'LLM', 'RAG', 'Workflow', 'Documentation'],
authors: [{ name: 'Labring', url: 'https://github.com/labring' }],
creator: 'Labring',
publisher: 'Labring',
metadataBase: new URL(domain),
alternates: {
canonical: '/',
languages: {
en: '/en',
'zh-CN': '/zh-CN'
}
},
openGraph: {
type: 'website',
locale: lang,
url: domain,
title,
description,
siteName: 'FastGPT',
images: [
{
url: '/og-image.png',
width: 1200,
height: 630,
alt: 'FastGPT'
}
]
},
twitter: {
card: 'summary_large_image',
title,
description,
images: ['/twitter-image.png']
},
robots: {
index: true,
follow: true,
googleBot: {
index: true,
follow: true,
'max-video-preview': -1,
'max-image-preview': 'large',
'max-snippet': -1
}
},
icons: {
icon: [
{ url: '/favicon/favicon.ico' },
{ url: '/favicon/favicon.svg', type: 'image/svg+xml' },
{ url: '/favicon/favicon-96x96.png', sizes: '96x96', type: 'image/png' }
],
apple: [{ url: '/favicon/apple-touch-icon.png', sizes: '180x180', type: 'image/png' }]
},
manifest: '/favicon/site.webmanifest'
};
}
export default async function Layout({
children,
params
......@@ -50,12 +140,7 @@ export default async function Layout({
<html lang={lang} className={inter.className} suppressHydrationWarning>
<body className="flex flex-col min-h-screen">
{trackSrc && siteId && (
<Script
src={trackSrc}
data-site-id={siteId}
defer
strategy="afterInteractive"
/>
<Script src={trackSrc} data-site-id={siteId} defer strategy="afterInteractive" />
)}
<RootProvider
i18n={{
......@@ -63,17 +148,7 @@ export default async function Layout({
locales,
translations: {
'zh-CN': zh_CN,
en: {
search: 'Search',
nextPage: 'Next Page',
previousPage: 'Previous Page',
lastUpdate: 'Last Updated',
editOnGithub: 'Edit on GitHub',
searchNoResult: 'No results found',
toc: 'On this page',
tocNoHeadings: 'No headings',
chooseLanguage: 'Choose Language'
}
en
}[lang]
}}
search={{
......
document/app/global.css
......@@ -438,6 +438,11 @@ div[data-rmiz-modal-overlay='visible'] {
border-color: transparent;
}
#nd-page > article,
#nd-toc {
padding-top: 2rem;
}
button[data-search-full] {
background-color: var(--color-fd-background);
}
......@@ -492,8 +497,18 @@ button[role='tab'] {
/* 去掉 viewport 内部的顶部渐变遮罩 */
#nd-sidebar-mobile [data-radix-scroll-area-viewport] > div {
mask-image: linear-gradient(transparent, #fff 0px, #fff calc(100% - 12px), transparent) !important;
-webkit-mask-image: linear-gradient(transparent, #fff 0px, #fff calc(100% - 12px), transparent) !important;
mask-image: linear-gradient(
transparent,
#fff 0px,
#fff calc(100% - 12px),
transparent
) !important;
-webkit-mask-image: linear-gradient(
transparent,
#fff 0px,
#fff calc(100% - 12px),
transparent
) !important;
}
}
......@@ -512,6 +527,12 @@ button[role='tab'] {
justify-content: center;
}
/* RootToggle sidebar tab selector: remove bottom margin */
#nd-sidebar .mb-2,
#nd-sidebar-mobile .mb-2 {
margin-bottom: 0 !important;
}
/* RootToggle 下拉菜单：增加两侧 padding + 选中项浅蓝背景 */
[data-radix-popper-content-wrapper] > div {
padding: 6px 8px !important;
......@@ -528,12 +549,12 @@ button[role='tab'] {
/* 移动端目录下拉框（TOC Popover Trigger）：文本溢出省略号 */
@media (max-width: 767px) {
button[class*="tocnav"] {
button[class*='tocnav'] {
max-width: 100vw;
overflow: hidden;
}
button[class*="tocnav"] > span.grid {
button[class*='tocnav'] > span.grid {
overflow: hidden;
min-width: 0;
}
......
document/app/robots.txt/route.ts 0 → 100644
import { NextResponse } from 'next/server';
export const dynamic = 'force-static';
export function GET() {
const homeDomain = process.env.FASTGPT_HOME_DOMAIN ?? 'https://fastgpt.io';
const domain = homeDomain.replace('https://', 'https://doc.');
const isCN = homeDomain.includes('.cn');
let content: string;
if (isCN) {
content = `User-Agent: Googlebot
Disallow: /
User-Agent: *
Allow: /
Host: ${domain}
Sitemap: ${domain}/sitemap.xml
`;
} else {
content = `User-Agent: bingbot
Disallow: /
User-Agent: *
Allow: /
Sitemap: ${domain}/sitemap.xml
`;
}
return new NextResponse(content, {
headers: { 'Content-Type': 'text/plain; charset=utf-8' }
});
}
document/app/sitemap.xml/route.ts 0 → 100644
import { source } from '@/lib/source';
import { NextResponse } from 'next/server';
import docLastModifiedData from '@/data/doc-last-modified.json';
export const dynamic = 'force-static';
export function GET() {
const homeDomain = process.env.FASTGPT_HOME_DOMAIN ?? 'https://fastgpt.io';
const domain = homeDomain.replace('https://', 'https://doc.');
const pages = source.getPages();
const urlEntries = pages
.map((page) => {
const filePath = `document/content/docs/${page.file.path}`;
// @ts-ignore
const lastModified = docLastModifiedData[filePath] || page.data.lastModified;
return ` <url>
<loc>${domain}${page.url}</loc>${lastModified ? `
<lastmod>${lastModified}</lastmod>` : ''}
</url>`;
})
.join('\n');
const xml = `<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
${urlEntries}
</urlset>`;
return new NextResponse(xml, {
headers: { 'Content-Type': 'application/xml; charset=utf-8' }
});
}
document/components/sideBar.tsx
'use client';
import { usePathname } from 'next/navigation';
import { useEffect, type FC, type ReactNode } from 'react';
import { createContext, useContext, useEffect, type FC, type ReactNode } from 'react';
import {
SidebarItem,
SidebarFolder,
......@@ -11,6 +11,8 @@ import {
import { type SidebarComponents } from 'fumadocs-ui/components/layout/sidebar';
import { type PageTree } from 'fumadocs-core/server';
const NestingLevelContext = createContext(0);
const isInFolder = (folder: PageTree.Folder, pathname: string): boolean => {
const check = (item: PageTree.Item | PageTree.Folder): boolean => {
if ('children' in item) {
......@@ -61,18 +63,27 @@ const CustomFolder: FC<{ item: PageTree.Folder; level: number; children: ReactNo
const shouldExpand = isInFolder(item, pathname);
return (
<SidebarFolder defaultOpen={shouldExpand} className="bg-blue hover:cursor-pointer">
<SidebarFolderTrigger className="hover:cursor-pointer">{item.name}</SidebarFolderTrigger>
<SidebarFolderContent className="bg-blue hover:cursor-pointer">
{children}
</SidebarFolderContent>
</SidebarFolder>
<NestingLevelContext.Provider value={level + 1}>
<SidebarFolder defaultOpen={shouldExpand} className="bg-blue hover:cursor-pointer">
<SidebarFolderTrigger className="hover:cursor-pointer">{item.name}</SidebarFolderTrigger>
<SidebarFolderContent className="bg-blue hover:cursor-pointer">
{children}
</SidebarFolderContent>
</SidebarFolder>
</NestingLevelContext.Provider>
);
};
const CustomSeparator: FC<{ item: PageTree.Separator }> = ({ item }) => (
<div className="text-sm font-semibold px-2 py-1.5 mt-1 mb-1 first:mt-0">{item.name}</div>
);
const CustomSeparator: FC<{ item: PageTree.Separator }> = ({ item }) => {
const level = useContext(NestingLevelContext);
return (
<div
className={`text-sm font-semibold ${level > 0 ? 'pl-6' : 'px-2'} pr-2 py-1.5 mt-1 mb-1 first:mt-0`}
>
{item.name}
</div>
);
};
export const CustomSidebarComponents: SidebarComponents = {
Item: CustomItem,
......
document/content/docs/introduction/cloud/faq.en.mdx 0 → 100644
---
title: FAQ
description: FastGPT Cloud Service FAQ
---
## Does FastGPT Cloud Service support integrating your own models?
Currently, FastGPT Cloud Service does not support integrating your own models, only the unified models provided by the official are supported.
\ No newline at end of file
document/content/docs/introduction/cloud/faq.mdx 0 → 100644
---
title: 常见问题
description: FastGPT 云服务常见问题
---
## 是否支持接入自己的模型
目前 FastGPT 云服务暂不支持接入自己的模型，只能使用官方提供的统一模型。
\ No newline at end of file
document/content/docs/introduction/cloud.mdx → document/content/docs/introduction/cloud/intro.mdx
---
title: FastGPT 云服务
description: FastGPT 云服务
title: 介绍
description: FastGPT 云服务介绍
---
## 服务地址
......
document/content/docs/introduction/cloud/meta.en.json 0 → 100644
{
"title": "FastGPT Cloud",
"description": "FastGPT Cloud Service",
"icon": "🌐",
"pages": ["intro", "faq", "terms", "privacy"]
}
document/content/docs/introduction/cloud/meta.json 0 → 100644
{
"title": "FastGPT 云服务",
"description": "FastGPT 云服务",
"icon": "🌐",
"pages": ["intro", "faq", "terms", "privacy"]
}
document/content/docs/introduction/commercial.en.mdx
......@@ -36,7 +36,7 @@ FastGPT Commercial Edition is an enhanced version built on top of the Community
| Team spaces & permissions | ❌ | ✅ | ✅ |
| Admin dashboard | ❌ | ✅ | Not needed |
| SSO login | ❌ | ✅ | In design |
| Commercial license | [View open source license](/docs/protocol/open-source) | Full | Full |
| Commercial license | [View open source license](/docs/introduction/opensource/license) | Full | Full |
## Pricing
......
document/content/docs/introduction/commercial.mdx
......@@ -36,7 +36,7 @@ FastGPT 商业版是基于 FastGPT 社区版的增强版本，增加了一些独
| 团队空间 & 权限 | ❌ | ✅ | ✅ |
| 管理后台 | ❌ | ✅ | 不需要 |
| SSO 登录 | ❌ | ✅ | 设计中 |
| 商业授权 | [查看开源协议](/docs/protocol/open-source) | 完整 | 完整 |
| 商业授权 | [查看开源协议](/docs/introduction/opensource/license) | 完整 | 完整 |
## 商业版软件价格
......
document/content/docs/introduction/development/custom-models/meta.en.json deleted 100644 → 0
{
"title": "Local Model Usage",
"pages": [
"marker",
"mineru",
"xinference",
"bge-rerank",
"chatglm2",
"m3e",
"chatglm2-m3e",
"ollama"
]
}
document/content/docs/introduction/development/design/meta.en.json deleted 100644 → 0
{
"title": "Design Solutions",
"pages": [
"dataset",
"design_plugin"
]
}
document/content/docs/introduction/development/meta.en.json deleted 100644 → 0
{
"title": "Community Edition",
"description": "FastGPT Community Edition",
"icon": "🔧",
"pages": [
"sealos",
"docker",
"faq",
"intro",
"configuration",
"object-storage",
"signoz",
"modelConfig",
"custom-models",
"proxy",
"migration",
"design"
]
}
document/content/docs/introduction/development/meta.json deleted 100644 → 0
{
"title": "FastGPT 社区版",
"description": "FastGPT 社区版",
"icon": "🔧",
"pages": [
"sealos",
"docker",
"faq",
"intro",
"configuration",
"object-storage",
"signoz",
"modelConfig",
"custom-models",
"proxy",
"migration",
"design"
]
}
document/content/docs/introduction/development/modelConfig/meta.en.json deleted 100644 → 0
{
"title": "Model Configuration Solutions",
"pages": [
"ai-proxy",
"intro",
"one-api",
"siliconCloud",
"ppio"
]
}
document/content/docs/introduction/development/proxy/cloudflare.en.mdx deleted 100644 → 0
---
title: Cloudflare Worker Proxy
description: Use Cloudflare Worker as a Proxy
---
[Reference tutorial by "不做了睡觉"](https://gravel-twister-d32.notion.site/FastGPT-API-ba7bb261d5fd4fd9bbb2f0607dacdc9e)
**Workers configuration file**
```js
const TELEGRAPH_URL = 'https://api.openai.com';
addEventListener('fetch', (event) => {
event.respondWith(handleRequest(event.request));
});
async function handleRequest(request) {
// Security check
if (request.headers.get('auth') !== 'auth_code') {
return new Response('UnAuthorization', { status: 403 });
}
const url = new URL(request.url);
url.host = TELEGRAPH_URL.replace(/^https?:\/\//, '');
const modifiedRequest = new Request(url.toString(), {
headers: request.headers,
method: request.method,
body: request.body,
redirect: 'follow'
});
const response = await fetch(modifiedRequest);
const modifiedResponse = new Response(response.body, response);
// Add CORS headers
modifiedResponse.headers.set('Access-Control-Allow-Origin', '*');
return modifiedResponse;
}
```
**Update FastGPT environment variables**
> Don't forget to include v1!
```bash
OPENAI_BASE_URL=https://xxxxxx/v1
OPENAI_BASE_URL_AUTH=auth_code
```
document/content/docs/introduction/development/proxy/cloudflare.mdx deleted 100644 → 0
---
title: Cloudflare Worker 中转
description: 使用 Cloudflare Worker 实现中转
---
[参考 "不做了睡觉" 的教程](https://gravel-twister-d32.notion.site/FastGPT-API-ba7bb261d5fd4fd9bbb2f0607dacdc9e)
**workers 配置文件**
```js
const TELEGRAPH_URL = 'https://api.openai.com';
addEventListener('fetch', (event) => {
event.respondWith(handleRequest(event.request));
});
async function handleRequest(request) {
// 安全校验
if (request.headers.get('auth') !== 'auth_code') {
return new Response('UnAuthorization', { status: 403 });
}
const url = new URL(request.url);
url.host = TELEGRAPH_URL.replace(/^https?:\/\//, '');
const modifiedRequest = new Request(url.toString(), {
headers: request.headers,
method: request.method,
body: request.body,
redirect: 'follow'
});
const response = await fetch(modifiedRequest);
const modifiedResponse = new Response(response.body, response);
// 添加允许跨域访问的响应头
modifiedResponse.headers.set('Access-Control-Allow-Origin', '*');
return modifiedResponse;
}
```
**修改 FastGPT 的环境变量**
> 务必别忘了填 v1！
```bash
OPENAI_BASE_URL=https://xxxxxx/v1
OPENAI_BASE_URL_AUTH=auth_code
```
document/content/docs/introduction/development/proxy/http_proxy.en.mdx deleted 100644 → 0
---
title: HTTP Proxy
description: Use an HTTP Proxy for Routing
---
If you have a proxy tool (like [Clash](https://github.com/Dreamacro/clash) or [sing-box](https://github.com/SagerNet/sing-box)), you can use an HTTP proxy to access OpenAI. Just add these two environment variables:
```bash
AXIOS_PROXY_HOST=
AXIOS_PROXY_PORT=
```
Using Clash as an example, it's recommended to route only `api.openai.com` through the proxy and direct-connect everything else. Example configuration:
```yaml
mixed-port: 7890
allow-lan: false
bind-address: '*'
mode: rule
log-level: warning
dns:
enable: true
ipv6: false
nameserver:
- 8.8.8.8
- 8.8.4.4
cache-size: 400
proxies:
-
proxy-groups:
- { name: '♻️ Auto Select', type: url-test, proxies: [HK-V01×1.5], url: 'https://api.openai.com', interval: 3600}
rules:
- 'DOMAIN-SUFFIX,api.openai.com,♻️ Auto Select'
- 'MATCH,DIRECT'
```
Then add these two environment variables to FastGPT:
```bash
AXIOS_PROXY_HOST=127.0.0.1
AXIOS_PROXY_PORT=7890
```
document/content/docs/introduction/development/proxy/http_proxy.mdx deleted 100644 → 0
---
title: HTTP 代理中转
description: 使用 HTTP 代理实现中转
---
如果你有代理工具（例如 [Clash](https://github.com/Dreamacro/clash) 或者 [sing-box](https://github.com/SagerNet/sing-box)），也可以使用 HTTP 代理来访问 OpenAI。只需要添加以下两个环境变量即可：
```bash
AXIOS_PROXY_HOST=
AXIOS_PROXY_PORT=
```
以 Clash 为例，建议指定 `api.openai.com` 走代理，其他请求都直连。示例配置如下：
```yaml
mixed-port: 7890
allow-lan: false
bind-address: '*'
mode: rule
log-level: warning
dns:
enable: true
ipv6: false
nameserver:
- 8.8.8.8
- 8.8.4.4
cache-size: 400
proxies:
-
proxy-groups:
- { name: '♻️ 自动选择', type: url-test, proxies: [香港V01×1.5], url: 'https://api.openai.com', interval: 3600}
rules:
- 'DOMAIN-SUFFIX,api.openai.com,♻️ 自动选择'
- 'MATCH,DIRECT'
```
然后给 FastGPT 添加两个环境变量：
```bash
AXIOS_PROXY_HOST=127.0.0.1
AXIOS_PROXY_PORT=7890
```
document/content/docs/introduction/development/proxy/meta.en.json deleted 100644 → 0
{
"title": "Proxy Solutions",
"description": "FastGPT private deployment proxy solutions",
"pages": [
"nginx",
"http_proxy",
"cloudflare"
]
}
document/content/docs/introduction/development/proxy/meta.json deleted 100644 → 0
{
"title": "代理方案",
"description": "FastGPT 私有化部署代理方案",
"pages": ["nginx","http_proxy","cloudflare"]
}
\ No newline at end of file
document/content/docs/introduction/development/proxy/nginx.en.mdx deleted 100644 → 0
---
title: Nginx Proxy
description: Deploy Nginx on Sealos as a Proxy
---
## Log in to Sealos
[Sealos](https://cloud.sealos.io?uid=fnWRt09fZP)
## Create an Application
Open "App Launchpad" and click "New Application":
![](/imgs/sealos3.webp)
![](/imgs/sealos4.png)
### Fill in Basic Configuration
Make sure to enable external access and copy the provided external access address.
![](/imgs/sealos5.png)
### Add Configuration File
1. Copy the configuration below. Replace the content after `server_name` with the external access address from step 2.
```nginx
user nginx;
worker_processes auto;
worker_rlimit_nofile 51200;
events {
worker_connections 1024;
}
http {
resolver 8.8.8.8;
proxy_ssl_server_name on;
access_log off;
server_names_hash_bucket_size 512;
client_header_buffer_size 64k;
large_client_header_buffers 4 64k;
client_max_body_size 50M;
proxy_connect_timeout 240s;
proxy_read_timeout 240s;
proxy_buffer_size 128k;
proxy_buffers 4 256k;
server {
listen 80;
server_name tgohwtdlrmer.cloud.sealos.io; # Replace with the Sealos external address
location ~ /openai/(.*) {
proxy_pass https://api.openai.com/$1$is_args$args;
proxy_set_header Host api.openai.com;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
# For streaming responses
proxy_set_header Connection '';
proxy_http_version 1.1;
chunked_transfer_encoding off;
proxy_buffering off;
proxy_cache off;
# For regular responses
proxy_buffer_size 128k;
proxy_buffers 4 256k;
proxy_busy_buffers_size 256k;
}
}
}
```
2. Open Advanced Configuration.
3. Click "Add Config File".
4. File name: `/etc/nginx/nginx.conf`.
5. File value: the code you just copied.
6. Click Confirm.
![](/imgs/sealos6.png)
### Deploy the Application
After filling everything in, click "Deploy" in the upper right corner to complete deployment.
## Update FastGPT Environment Variables
1. Go to the deployed app's details and copy the external address.
> Note: This is an API address — opening it directly in a browser won't work. To verify, visit: `*.cloud.sealos.io/openai/api`. If you see `Invalid URL (GET /api)`, it's working correctly.
![](/imgs/sealos7.png)
2. Update the environment variable (this is FastGPT's environment variable, not Sealos'):
```bash
OPENAI_BASE_URL=https://tgohwtdlrmer.cloud.sealos.io/openai/v1
```
**Done!**
document/content/docs/introduction/development/proxy/nginx.mdx deleted 100644 → 0
---
title: Nginx 中转
description: 使用 Sealos 部署 Nginx 实现中转
---
## 登录 Sealos
[Sealos](https://cloud.sealos.io?uid=fnWRt09fZP)
## 创建应用
打开 「应用管理」，点击「新建应用」：
![](/imgs/sealos3.webp)
![](/imgs/sealos4.png)
### 填写基本配置
务必开启外网访问，复制外网访问提供的地址。
![](/imgs/sealos5.png)
### 添加配置文件
1. 复制下面这段配置文件，注意 `server_name` 后面的内容替换成第二步的外网访问地址。
```nginx
user nginx;
worker_processes auto;
worker_rlimit_nofile 51200;
events {
worker_connections 1024;
}
http {
resolver 8.8.8.8;
proxy_ssl_server_name on;
access_log off;
server_names_hash_bucket_size 512;
client_header_buffer_size 64k;
large_client_header_buffers 4 64k;
client_max_body_size 50M;
proxy_connect_timeout 240s;
proxy_read_timeout 240s;
proxy_buffer_size 128k;
proxy_buffers 4 256k;
server {
listen 80;
server_name tgohwtdlrmer.cloud.sealos.io; # 这个地方替换成 Sealos 提供的外网地址
location ~ /openai/(.*) {
proxy_pass https://api.openai.com/$1$is_args$args;
proxy_set_header Host api.openai.com;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
# 如果响应是流式的
proxy_set_header Connection '';
proxy_http_version 1.1;
chunked_transfer_encoding off;
proxy_buffering off;
proxy_cache off;
# 如果响应是一般的
proxy_buffer_size 128k;
proxy_buffers 4 256k;
proxy_busy_buffers_size 256k;
}
}
}
```
2. 点开高级配置。
3. 点击「新增配置文件」。
4. 文件名写: `/etc/nginx/nginx.conf`。
5. 文件值为刚刚复制的那段代码。
6. 点击确认。
![](/imgs/sealos6.png)
### 部署应用
填写完毕后，点击右上角的「部署」，即可完成部署。
## 修改 FastGPT 环境变量
1. 进入刚刚部署应用的详情，复制外网地址
> 注意：这是个 API 地址，点击打开是无效的。如需验证，可以访问: `*.cloud.sealos.io/openai/api`，如果提示 `Invalid URL (GET /api)` 则代表成功。
![](/imgs/sealos7.png)
2. 修改环境变量（是 FastGPT 的环境变量，不是 Sealos 的）：
```bash
OPENAI_BASE_URL=https://tgohwtdlrmer.cloud.sealos.io/openai/v1
```
**Done!**
document/content/docs/introduction/guide/dashboard/workflow/ai_chat.en.mdx
......@@ -17,7 +17,7 @@ import { Alert } from '@/components/docs/Alert';
## AI Model
Configure available chat models via [config.json](/docs/introduction/development/configuration/) and connect multiple models through [one-api](/docs/introduction/development/modelConfig/one-api).
Configure available chat models via [config.json](/docs/self-host/config/model/intro)。
Click the AI model to configure its parameters.
......
document/content/docs/introduction/guide/dashboard/workflow/ai_chat.mdx
......@@ -17,7 +17,7 @@ import { Alert } from '@/components/docs/Alert';
## AI模型
可以通过 [config.json](/docs/introduction/development/configuration/) 配置可选的对话模型，通过 [one-api](/docs/introduction/development/modelConfig/one-api) 来实现多模型接入。
可以通过 [config.json](/docs/self-host/config/model/intro) 配置可选的对话模型。
点击AI模型后，可以配置模型的相关参数。
......
document/content/docs/introduction/guide/plugins/dev_system_tool.en.mdx
......@@ -322,7 +322,7 @@ Simple tools may not need E2E testing. For complex tools, the review team may re
### 6.1 Deploy the E2E Test Environment
1. Follow [Quick Start Local Development](/docs/introduction/development/intro) to set up a local FastGPT development environment
1. Follow [Quick Start Local Development](/docs/self-host/dev) to set up a local FastGPT development environment
2. Run `cd runtime && cp .env.template .env.local` to copy the environment variable template, then connect to the Minio, Mongo, and Redis instances from step 1
3. Run `bun run dev` to start the development environment, then update FastGPT's environment variables to connect to your fastgpt-plugin instance
......
document/content/docs/introduction/guide/plugins/dev_system_tool.mdx
......@@ -323,7 +323,7 @@ FastGPT-plugin 使用 Vitest 作为单测框架。
### 6.1 部署 E2E 测试环境
1. 参考 [快速开始本地开发](/docs/introduction/development/intro)，在本地部署一套 FastGPT 开发环境
1. 参考 [快速开始本地开发](/docs/self-host/dev)，在本地部署一套 FastGPT 开发环境
2. `cd runtime && cp .env.template .env.local` 复制环境变量样例文件，连接到上一步部署的 Minio, Mongo, Redis 中
3. `bun run dev` 运行开发环境，修改 FastGPT 的环境变量，连接到你刚刚启动的 fastgpt-plugin
......
document/content/docs/introduction/meta.en.json
{
"title": "Documentation",
"title": "User Guide",
"root": true,
"pages": [
"---Getting Started---",
"---Tutorials---",
"index",
"...guide",
"---Editions---",
"cloud",
"commercial",
"development",
"---Features---",
"...guide"
"opensource"
],
"order": 1
}
document/content/docs/introduction/meta.json
......@@ -2,13 +2,13 @@
"title": "使用文档",
"root": true,
"pages": [
"---入门---",
"---教程---",
"index",
"...guide",
"---版本介绍---",
"cloud",
"commercial",
"development",
"---功能介绍---",
"...guide"
"opensource"
],
"order": 1
}
document/content/docs/introduction/opensource/intro.en.mdx 0 → 100644
---
title: Introduction
description: FastGPT Community Edition Introduction
---
FastGPT Community Edition is the free version of FastGPT, designed for individual developers and small delivery teams. It includes all core FastGPT features: Agent building, workflows, and knowledge bases. Please use it in compliance with the [FastGPT Open Source License](/docs/introduction/opensource/license).
**Related Links**
* [GitHub Repository](https://github.com/labring/FastGPT)
* [Deployment Guide](https://doc.fastgpt.io/docs/self-host/intro/)
* [Local Development Guide](https://doc.fastgpt.io/docs/self-host/intro/)
\ No newline at end of file
document/content/docs/introduction/opensource/intro.mdx 0 → 100644
---
title: 介绍
description: FastGPT 社区版介绍
---
FastGPT 社区版是 FastGPT 的免费版本，适合于个人开发者或小型交付团队使用。包含了 FastGPT 所有核心功能：Agent 构建、工作流、知识库，请在遵守[FastGPT 开源协议](/docs/introduction/opensource/license)的前提下使用。
**相关链接**
* [GitHub 仓库](https://github.com/labring/FastGPT)
* [部署教程](https://doc.fastgpt.io/docs/self-host/intro/)
* [本地开发介绍](https://doc.fastgpt.io/docs/self-host/intro/)
\ No newline at end of file
document/content/docs/introduction/opensource/meta.en.json 0 → 100644
{
"title": "FastGPT Community Edition",
"description": "FastGPT Community Edition",
"icon": "🔧",
"pages": ["intro", "license"]
}
document/content/docs/introduction/opensource/meta.json 0 → 100644
{
"title": "FastGPT 社区版",
"description": "FastGPT 社区版",
"icon": "🔧",
"pages": ["intro", "license"]
}
document/content/docs/protocol/meta.en.json deleted 100644 → 0
{
"title": "Legal",
"root": true,
"description": "Legal",
"pages": [
"open-source",
"terms",
"privacy"
],
"order": 3
}
document/content/docs/protocol/meta.json deleted 100644 → 0
{
"title": "协议",
"root": true,
"description": "协议",
"pages": ["open-source", "terms", "privacy"],
"order": 3
}
document/content/docs/introduction/development/configuration.en.mdx → document/content/docs/self-host/config/json.en.mdx
......@@ -3,7 +3,7 @@ title: Configuration File Guide
description: FastGPT configuration parameters explained
---
Since environment variables aren't ideal for complex configurations, newer versions of FastGPT use ConfigMap-style mounted configuration files. You can find the default config at `projects/app/data/config.json`. See the [Docker Compose deployment guide](/docs/introduction/development/docker/) for how to mount the config file.
Since environment variables aren't ideal for complex configurations, newer versions of FastGPT use ConfigMap-style mounted configuration files. You can find the default config at `projects/app/data/config.json`. See the [Docker Compose deployment guide](/docs/self-host/deploy/docker/) for how to mount the config file.
**In development**, copy the example config `config.json` to `config.local.json` for it to take effect.
......@@ -70,4 +70,4 @@ When importing data to your knowledge base or configuring file uploads in your a
### Using Marker for PDF Parsing
[View the Marker integration tutorial](/docs/introduction/development/custom-models/marker)
[View the Marker integration tutorial](/docs/self-host/custom-models/marker)
document/content/docs/introduction/development/configuration.mdx → document/content/docs/self-host/config/json.mdx
---
title: 配置文件介绍
description: FastGPT 配置参数介绍
title: config.json 文件配置
description: FastGPT config.json 文件配置
---
由于环境变量不利于配置复杂的内容，新版 FastGPT 采用了 ConfigMap 的形式挂载配置文件，你可以在 `projects/app/data/config.json` 看到默认的配置文件。可以参考 [docker-compose 快速部署](/docs/introduction/development/docker/) 来挂载配置文件。
**该配置仅适用于社区版，商业版用户该配置已集成至后台。**
由于环境变量不利于配置复杂的内容，新版 FastGPT 采用了 ConfigMap 的形式挂载配置文件，你可以在 `projects/app/data/config.json` 看到默认的配置文件。可以参考 [docker-compose 快速部署](/docs/self-host/deploy/docker/) 来挂载配置文件。
**开发环境下**，你需要将示例配置文件 `config.json` 复制成 `config.local.json` 文件才会生效。
......@@ -70,4 +72,4 @@ description: FastGPT 配置参数介绍
### 使用 Marker 解析 PDF 文件
[点击查看 Marker 接入教程](/docs/introduction/development/custom-models/marker)
[点击查看 Marker 接入教程](/docs/self-host/custom-models/marker)
document/content/docs/introduction/development/modelConfig/ai-proxy.en.mdx → document/content/docs/self-host/config/model/ai-proxy.en.mdx
......@@ -47,7 +47,7 @@ Using Alibaba Cloud models as an example:
1. Channel Name: The display name for the channel, used for identification only;
2. Provider: The provider corresponding to the model. Different providers have different default addresses and API key formats;
3. Models: The specific models available for this channel. The system includes mainstream models by default. If the desired option is not in the dropdown, click "Add Model" to [add a custom model](/docs/introduction/development/modelconfig/intro/#add-custom-models);
3. Models: The specific models available for this channel. The system includes mainstream models by default. If the desired option is not in the dropdown, click "Add Model" to [add a custom model](/docs/self-host/config/model/intro/#add-custom-models);
4. Model Mapping: Map the model requested by FastGPT to the actual model provided. For example:
```json
......@@ -81,7 +81,7 @@ After the test completes, the results and request duration for each model will b
### 3. Enable Models
Finally, in `Model Configuration`, you can enable the corresponding models to use them on the platform. For more model configuration details, see [Model Configuration](/docs/introduction/development/modelconfig/intro).
Finally, in `Model Configuration`, you can enable the corresponding models to use them on the platform. For more model configuration details, see [Model Configuration](/docs/self-host/config/model/intro).
![aiproxy8](/imgs/aiproxy-8.png)
......
document/content/docs/introduction/development/modelConfig/ai-proxy.mdx → document/content/docs/self-host/config/model/ai-proxy.mdx
......@@ -47,7 +47,7 @@ AI proxy 相关功能，可以在`账号-模型提供商`页面找到。
1. 渠道名：展示在外部的渠道名称，仅作标识;
2. 厂商：模型对应的厂商，不同厂商对应不同的默认地址和 API 密钥格式;
3. 模型：当前渠道具体可以使用的模型，系统内置了主流的一些模型，如果下拉框中没有想要的选项，可以点击“新增模型”，[增加自定义模型](/docs/introduction/development/modelconfig/intro/#新增自定义模型);
3. 模型：当前渠道具体可以使用的模型，系统内置了主流的一些模型，如果下拉框中没有想要的选项，可以点击“新增模型”，[增加自定义模型](/docs/self-host/config/model/intro/#新增自定义模型);
4. 模型映射：将 FastGPT 请求的模型，映射到具体提供的模型上。例如：
```json
......@@ -81,7 +81,7 @@ FatGPT 中的模型为 `gpt-4o-test`，向 AI Proxy 发起请求时也是 `gpt-4
### 3. 启用模型
最后在`模型配置`中，可以选择启用对应的模型，这样就能在平台中使用了，更多模型配置可以参考[模型配置](/docs/introduction/development/modelconfig/intro)
最后在`模型配置`中，可以选择启用对应的模型，这样就能在平台中使用了，更多模型配置可以参考[模型配置](/docs/self-host/config/model/intro)
![aiproxy8](/imgs/aiproxy-8.png)
......
document/content/docs/introduction/development/modelConfig/intro.en.mdx → document/content/docs/self-host/config/model/intro.en.mdx
......@@ -15,11 +15,11 @@ Starting from version 4.8.20, you can configure models directly in the FastGPT U
#### AI Proxy
Starting from version 4.8.23, FastGPT supports configuring model providers directly in the UI using [AI Proxy](/docs/introduction/development/modelconfig/ai-proxy) for model aggregation, enabling connections to more providers.
Starting from version 4.8.23, FastGPT supports configuring model providers directly in the UI using [AI Proxy](/docs/self-host/config/model/ai-proxy) for model aggregation, enabling connections to more providers.
#### One API
You can also use the [OneAPI Integration Guide](/docs/introduction/development/modelconfig/one-api). You'll need to apply for API access from each provider and add them to OneAPI before using them in FastGPT. Example flow:
You can also use the [OneAPI Integration Guide](/docs/self-host/config/model/one-api). You'll need to apply for API access from each provider and add them to OneAPI before using them in FastGPT. Example flow:
![alt text](/imgs/image-95.png)
......@@ -223,7 +223,7 @@ A free `bge-reranker-v2-m3` model is available.
#### Self-Hosted Rerank Models
[View the ReRank model deployment tutorial](/docs/introduction/development/custom-models/bge-rerank/)
[View the ReRank model deployment tutorial](/docs/self-host/custom-models/bge-rerank/)
### Integrating Speech Recognition Models
......@@ -253,7 +253,7 @@ The custom request key is sent as a request header: `Authorization: Bearer xxx`.
All interfaces follow OpenAI's model format. See the [OpenAI API documentation](https://platform.openai.com/docs/api-reference/introduction) for details.
Since OpenAI doesn't provide a ReRank model, the Cohere format is used instead. [View request examples](/docs/introduction/development/faq/#how-to-check-model-issues)
Since OpenAI doesn't provide a ReRank model, the Cohere format is used instead. [View request examples](/docs/self-host/faq/#how-to-check-model-issues)
### Model Pricing Configuration
......@@ -276,13 +276,13 @@ To add a model provider, modify the following:
### Adding Models
In the `FastGPT-plugin` project, find the corresponding provider's config file under the `modules/model/provider` directory and add the model configuration. Make sure the `model` field is unique across all models. For field descriptions, see [Model Configuration Field Descriptions](/docs/introduction/development/modelconfig/intro/#configuration-via-config-file).
In the `FastGPT-plugin` project, find the corresponding provider's config file under the `modules/model/provider` directory and add the model configuration. Make sure the `model` field is unique across all models. For field descriptions, see [Model Configuration Field Descriptions](/docs/self-host/config/model/intro/#configuration-via-config-file).
## Legacy Model Configuration
After configuring OneAPI, you need to manually add model configuration to the `config.json` file and restart.
Since environment variables aren't ideal for complex configuration, FastGPT uses ConfigMap to mount config files. You can find the default config file at `projects/app/data/config.json`. See [docker-compose Quick Deployment](/docs/introduction/development/docker/) for how to mount config files.
Since environment variables aren't ideal for complex configuration, FastGPT uses ConfigMap to mount config files. You can find the default config file at `projects/app/data/config.json`. See [docker-compose Quick Deployment](/docs/self-host/deploy/docker/) for how to mount config files.
**In development**, copy the example config file `config.json` to `config.local.json` for it to take effect.
**In Docker deployment**, modifying `config.json` requires restarting the container.
......
document/content/docs/introduction/development/modelConfig/intro.mdx → document/content/docs/self-host/config/model/intro.mdx
......@@ -15,11 +15,11 @@ import { Alert } from '@/components/docs/Alert';
#### AI Proxy
从 4.8.23 版本开始， FastGPT 支持在页面上配置模型提供商，即使用 [AI Proxy 接入教程](/docs/introduction/development/modelconfig/ai-proxy) 来进行模型聚合，从而可以对接更多模型提供商。
从 4.8.23 版本开始， FastGPT 支持在页面上配置模型提供商，即使用 [AI Proxy 接入教程](/docs/self-host/config/model/ai-proxy) 来进行模型聚合，从而可以对接更多模型提供商。
#### One API
也可以使用 [OneAPI 接入教程](/docs/introduction/development/modelconfig/one-api)。你需要先在各服务商申请好 API 接入 OneAPI 后，才能在 FastGPT 中使用这些模型。示例流程如下：
也可以使用 [OneAPI 接入教程](/docs/self-host/config/model/one-api)。你需要先在各服务商申请好 API 接入 OneAPI 后，才能在 FastGPT 中使用这些模型。示例流程如下：
![alt text](/imgs/image-95.png)
......@@ -223,7 +223,7 @@ FastGPT 页面上提供了每类模型的简单测试，可以初步检查模型
#### 私有部署模型
[点击查看部署 ReRank 模型教程](/docs/introduction/development/custom-models/bge-rerank/)
[点击查看部署 ReRank 模型教程](/docs/self-host/custom-models/bge-rerank/)
### 接入语音识别模型
......@@ -253,7 +253,7 @@ OneAPI 的语言识别接口，无法正确的识别其他模型（会始终识
所有接口均遵循 OpenAI 提供的模型格式，可参考 [OpenAI API 文档](https://platform.openai.com/docs/api-reference/introduction) 进行配置。
由于 OpenAI 没有提供 ReRank 模型，遵循的是 Cohere 的格式。[点击查看接口请求示例](/docs/introduction/development/faq/#如何检查模型问题)
由于 OpenAI 没有提供 ReRank 模型，遵循的是 Cohere 的格式。[点击查看接口请求示例](/docs/self-host/faq/#如何检查模型问题)
### 模型价格配置
......@@ -276,13 +276,13 @@ OneAPI 的语言识别接口，无法正确的识别其他模型（会始终识
### 添加模型
你可以在`FastGPT-plugin`项目中`modules/model/provider`目录下，找对应模型提供商的配置文件，并追加模型配置。请自行全文检查，`model`字段，必须在所有模型中唯一。具体配置字段说明，参考[模型配置字段说明](/docs/introduction/development/modelconfig/intro/#通过配置文件配置)
你可以在`FastGPT-plugin`项目中`modules/model/provider`目录下，找对应模型提供商的配置文件，并追加模型配置。请自行全文检查，`model`字段，必须在所有模型中唯一。具体配置字段说明，参考[模型配置字段说明](/docs/self-host/config/model/intro/#通过配置文件配置)
## 旧版模型配置说明
配置好 OneAPI 后，需要在`config.json`文件中，手动的增加模型配置，并重启。
由于环境变量不利于配置复杂的内容，FastGPT 采用了 ConfigMap 的形式挂载配置文件，你可以在 `projects/app/data/config.json` 看到默认的配置文件。可以参考 [docker-compose 快速部署](/docs/introduction/development/docker/) 来挂载配置文件。
由于环境变量不利于配置复杂的内容，FastGPT 采用了 ConfigMap 的形式挂载配置文件，你可以在 `projects/app/data/config.json` 看到默认的配置文件。可以参考 [docker-compose 快速部署](/docs/self-host/deploy/docker/) 来挂载配置文件。
**开发环境下**，你需要将示例配置文件 `config.json` 复制成 `config.local.json` 文件才会生效。
**Docker部署**，修改`config.json` 文件，需要重启容器。
......
document/content/docs/self-host/config/model/meta.en.json 0 → 100644
{
"title": "Model Configuration",
"pages": ["intro", "ai-proxy", "one-api", "siliconCloud", "ppio"]
}
document/content/docs/introduction/development/modelConfig/meta.json → document/content/docs/self-host/config/model/meta.json
{
"title": "模型配置方案",
"pages": ["ai-proxy","intro","one-api","siliconCloud","ppio"]
}
\ No newline at end of file
"pages": ["intro", "ai-proxy", "one-api", "siliconCloud", "ppio"]
}
document/content/docs/introduction/development/modelConfig/ppio.en.mdx → document/content/docs/self-host/config/model/ppio.en.mdx
......@@ -65,7 +65,7 @@ For other model IDs, max context, and pricing, see: [Model List](https://ppinfra
## 2. Deploy the Latest FastGPT to Your Local Environment
<Alert context="warning">
Please use version v4.8.22 or above. Deployment reference: [Deploy FastGPT](/docs/introduction/development/intro/)
Please use version v4.8.22 or above. Deployment reference: [Deploy FastGPT](/docs/self-host/dev/)
</Alert>
## 3. Model Configuration (Choose One of the Two Methods Below)
......
document/content/docs/introduction/development/modelConfig/ppio.mdx → document/content/docs/self-host/config/model/ppio.mdx
......@@ -66,7 +66,7 @@ deepseek 系列：
## 2. 部署最新版 FastGPT 到本地环境
<Alert context="warning">
请使用 v4.8.22 以上版本，部署参考: [部署 FastGPT](/docs/introduction/development/intro/)
请使用 v4.8.22 以上版本，部署参考: [部署 FastGPT](/docs/self-host/dev/)
</Alert>
## 3. 模型配置（下面两种方式二选其一）
......
document/content/docs/introduction/development/modelConfig/siliconCloud.en.mdx → document/content/docs/self-host/config/model/siliconCloud.en.mdx
......@@ -5,7 +5,7 @@ description: Try Open Source Models with SiliconCloud
[SiliconCloud](https://cloud.siliconflow.cn/i/TR9Ym0c4) is a platform focused on providing open source model inference, with its own acceleration engine. It helps users test and use open source models quickly at low cost. In our experience, their models offer solid speed and stability, with a wide variety covering language, embedding, reranking, TTS, STT, image generation, and video generation models — meeting all model requirements in FastGPT.
If you want to use SiliconCloud for only some models, see [OneAPI Integration with SiliconCloud](/docs/introduction/development/modelconfig/one-api/#siliconcloud--open-source-model-collection).
If you want to use SiliconCloud for only some models, see [OneAPI Integration with SiliconCloud](/docs/self-host/config/model/one-api/#siliconcloud--open-source-model-collection).
This guide covers deploying FastGPT entirely with SiliconCloud models.
......
document/content/docs/introduction/development/modelConfig/siliconCloud.mdx → document/content/docs/self-host/config/model/siliconCloud.mdx
......@@ -5,7 +5,7 @@ description: 通过 SiliconCloud 体验开源模型
[SiliconCloud(硅基流动)](https://cloud.siliconflow.cn/i/TR9Ym0c4) 是一个以提供开源模型调用为主的平台，并拥有自己的加速引擎。帮助用户低成本、快速的进行开源模型的测试和使用。实际体验下来，他们家模型的速度和稳定性都非常不错，并且种类丰富，覆盖语言、向量、重排、TTS、STT、绘图、视频生成模型，可以满足 FastGPT 中所有模型需求。
如果你想部分模型使用 SiliconCloud 的模型，可额外参考[OneAPI接入硅基流动](/docs/introduction/development/modelconfig/one-api/#硅基流动--开源模型大合集)。
如果你想部分模型使用 SiliconCloud 的模型，可额外参考[OneAPI接入硅基流动](/docs/self-host/config/model/one-api/#硅基流动--开源模型大合集)。
本文会介绍完全使用 SiliconCloud 模型来部署 FastGPT 的方案。
......
document/content/docs/introduction/development/object-storage.en.mdx → document/content/docs/self-host/config/object-storage.en.mdx
---
title: Object Storage Configuration & Common Issues
title: Object Storage Configuration
description: How to configure and connect to various object storage providers via environment variables, and common configuration issues
---
......
document/content/docs/introduction/development/object-storage.mdx → document/content/docs/self-host/config/object-storage.mdx
---
title: 对象存储配置及常见问题
description: 如何通过环境变量配置并连接个各厂商的对象存储，以及常见的配置问题
title: 对象存储配置
description: 如何通过环境变量配置并连接个各厂商的对象存储
---
import { Alert } from '@/components/docs/Alert';
......
document/content/docs/introduction/development/signoz.mdx → document/content/docs/self-host/config/signoz.mdx
---
title: 接入 Signoz 服务监控
description: FastGPT 接入 Signoz 服务监控
title: Signoz 监控服务
description: FastGPT 接入 Signoz 监控服务
---
## 介绍
......
document/content/docs/introduction/development/custom-models/chatglm2-m3e.en.mdx → document/content/docs/self-host/custom-models/chatglm2-m3e.en.mdx
......@@ -21,7 +21,7 @@ You can also set it via the environment variable: sk-key. Refer to Docker docume
## Connect to OneAPI
Documentation: [One API](/docs/introduction/development/modelconfig/one-api/)
Documentation: [One API](/docs/self-host/config/model/one-api/)
Add a channel for chatglm2 and m3e-large respectively, with the following parameters:
......
document/content/docs/introduction/development/custom-models/chatglm2-m3e.mdx → document/content/docs/self-host/custom-models/chatglm2-m3e.mdx
......@@ -21,7 +21,7 @@ FastGPT 默认使用了 OpenAI 的 LLM 模型和向量模型，如果想要私
## 接入 OneAPI
文档链接：[One API](/docs/introduction/development/modelconfig/one-api/)
文档链接：[One API](/docs/self-host/config/model/one-api/)
为 chatglm2 和 m3e-large 各添加一个渠道，参数如下：
......
document/content/docs/self-host/custom-models/meta.en.json 0 → 100644
{
"title": "Local Models",
"pages": ["marker","mineru","xinference","bge-rerank","chatglm2","m3e","chatglm2-m3e","ollama"]
}
document/content/docs/introduction/development/custom-models/ollama.en.mdx → document/content/docs/self-host/custom-models/ollama.en.mdx
......@@ -107,7 +107,7 @@ ollama ls
### 2. AI Proxy Integration
If you're using FastGPT's default configuration from [here](/docs/introduction/development/docker.md), AI Proxy is enabled by default.
If you're using FastGPT's default configuration from [here](/docs/self-host/deploy/docker), AI Proxy is enabled by default.
![](/imgs/Ollama-aiproxy1.png)
......@@ -115,7 +115,7 @@ Make sure your FastGPT can access the Ollama container. If not, refer to the [in
![](/imgs/Ollama-aiproxy2.png)
In FastGPT, go to Account -> Model Providers -> Model Configuration -> Add Model. Make sure the model ID matches the model name in OneAPI. See details [here](/docs/introduction/development/modelConfig/intro.md).
In FastGPT, go to Account -> Model Providers -> Model Configuration -> Add Model. Make sure the model ID matches the model name in OneAPI. See details [here](/docs/self-host/config/model/intro).
![](/imgs/Ollama-models2.png)
......
document/content/docs/introduction/development/custom-models/ollama.mdx → document/content/docs/self-host/custom-models/ollama.mdx
......@@ -107,7 +107,7 @@ ollama ls
### 2. AI Proxy 接入
如果你采用的是 FastGPT 中的默认配置文件部署[这里](/docs/introduction/development/docker.md)，即默认采用 AI Proxy 进行启动。
如果你采用的是 FastGPT 中的默认配置文件部署[这里](/docs/self-host/deploy/docker.md)，即默认采用 AI Proxy 进行启动。
![](/imgs/Ollama-aiproxy1.png)
......@@ -115,7 +115,7 @@ ollama ls
![](/imgs/Ollama-aiproxy2.png)
在 FastGPT 中点击账号->模型提供商->模型配置->新增模型，添加自己的模型即可，添加模型时需要保证模型ID和 OneAPI 中的模型名称一致。详细参考[这里](/docs/introduction/development/modelConfig/intro.md)
在 FastGPT 中点击账号->模型提供商->模型配置->新增模型，添加自己的模型即可，添加模型时需要保证模型ID和 OneAPI 中的模型名称一致。详细参考[这里](/docs/self-host/config/model/intro.md)
![](/imgs/Ollama-models2.png)
......
document/content/docs/introduction/development/custom-models/xinference.en.mdx → document/content/docs/self-host/custom-models/xinference.en.mdx
......@@ -98,7 +98,7 @@ Beyond WebUI and CLI, Xinference also provides Python SDK and RESTful API. For m
## Integrate Local Models with One API
For One API deployment and setup, refer to [here](/docs/introduction/development/modelconfig/one-api/).
For One API deployment and setup, refer to [here](/docs/self-host/config/model/one-api/).
Add a channel for qwen1.5-chat. Set the Base URL to the Xinference service endpoint and register qwen-chat (the model's UID).
......
document/content/docs/introduction/development/custom-models/xinference.mdx → document/content/docs/self-host/custom-models/xinference.mdx
......@@ -98,7 +98,7 @@ xinference launch -n qwen-chat -s 14 -f pytorch
## 将本地模型接入 One API
One API 的部署和接入请参考[这里](/docs/introduction/development/modelconfig/one-api/)。
One API 的部署和接入请参考[这里](/docs/self-host/config/model/one-api/)。
为 qwen1.5-chat 添加一个渠道，这里的 Base URL 需要填 Xinference 服务的端点，并且注册 qwen-chat (模型的 UID) 。
......
document/content/docs/introduction/development/docker.en.mdx → document/content/docs/self-host/deploy/docker.en.mdx
---
title: Deploy with Docker
title: Deploy with Docker-compose
description: Quickly deploy FastGPT using Docker Compose
---
......@@ -74,11 +74,7 @@ SeekDB uses MySQL protocol, fully compatible with OceanBase:
## Preparation
### 1. Ensure Network Access
If using `OpenAI` or other international model APIs, make sure you can access them, or you'll get `Connection error`. See: [Proxy Solutions](/docs/introduction/development/proxy/nginx)
### 2. Prepare Docker Environment
### Prepare Docker Environment
<Tabs items={['Linux','MacOS','Windows']}>
<Tab value="Linux">
......@@ -189,7 +185,7 @@ Each container restart automatically initializes the root user with password `12
### 6. Configure Models
- After first login, the system prompts that `Language Model` and `Index Model` are not configured and automatically redirects to the model configuration page. At least these two model types are required.
- If the redirect doesn't happen, go to `Account - Model Providers` to configure models. [View tutorial](/docs/introduction/development/modelConfig/ai-proxy)
- If the redirect doesn't happen, go to `Account - Model Providers` to configure models. [View tutorial](/docs/self-host/config/model/ai-proxy)
- Known issue: after first entering the system, the browser tab may become unresponsive. Close the tab and reopen it.
### 7. Install System Plugins as Needed
......@@ -219,7 +215,7 @@ Check the `STORAGE_EXTERNAL_ENDPOINT` variable — it must be accessible by both
> Don't use `127.0.0.1` or `localhost` or other loopback addresses. Use the host machine's local IP when deploying with Docker, but set it to a static IP; or use a fixed domain name. This prevents 403 errors caused by URL mismatches when signing object storage URLs.
>
> See [Object Storage Configuration & Common Issues](/docs/introduction/development/object-storage)
> See [Object Storage Configuration & Common Issues](/docs/self-host/config/object-storage)
### Browser Unresponsive After Login
......@@ -306,7 +302,7 @@ docker-compose up -d
### How to Update Versions?
1. Check the [update documentation](/docs/upgrading) to confirm the target version — avoid skipping versions.
1. Check the [update documentation](/docs/self-host/upgrading/upgrade-intruction) to confirm the target version — avoid skipping versions.
2. Change the image tag to the target version
3. Run these commands to pull and restart:
......@@ -319,7 +315,7 @@ docker-compose up -d
### How to Customize Configuration Files?
Modify `config.json`, then run `docker-compose down` followed by `docker-compose up -d` to restart. For details, see [Configuration Guide](/docs/introduction/development/configuration).
Modify `config.json`, then run `docker-compose down` followed by `docker-compose up -d` to restart. For details, see [Configuration Guide](/docs/self-host/config/json).
### How to Check if Custom Config File is Mounted
......
document/content/docs/introduction/development/docker.mdx → document/content/docs/self-host/deploy/docker.mdx
---
title: 通过 Docker 部署
title: Docker-compose 部署
description: 使用 Docker Compose 快速部署 FastGPT
---
......@@ -74,11 +74,7 @@ SeekDB 使用 MySQL 协议，与 OceanBase 完全兼容：
## 前置工作
### 1. 确保网络环境
如果使用`OpenAI`等国外模型接口，请确保可以正常访问，否则会报错：`Connection error` 等。 方案可以参考：[代理方案](/docs/introduction/development/proxy/nginx)
### 2. 准备 Docker 环境
### 准备 Docker-compose 环境
<Tabs items={['Linux','MacOS','Windows']}>
<Tab value="Linux">
......@@ -189,7 +185,7 @@ docker-compose up -d
### 6. 配置模型
- 首次登录FastGPT后，系统会提示未配置`语言模型`和`索引模型`，并自动跳转模型配置页面。系统必须至少有这两类模型才能正常使用。
- 如果系统未正常跳转，可以在`账号-模型提供商`页面，进行模型配置。[点击查看相关教程](/docs/introduction/development/modelConfig/ai-proxy)
- 如果系统未正常跳转，可以在`账号-模型提供商`页面，进行模型配置。[点击查看相关教程](/docs/self-host/config/model/ai-proxy)
- 目前已知可能问题：首次进入系统后，整个浏览器 tab 无法响应。此时需要删除该tab，重新打开一次即可。
### 7. 按需安装系统插件
......@@ -220,7 +216,7 @@ docker-compose up -d
> 填入的地址不可为`127.0.0.1`或者`localhost`等本地回环地址，可填 Docker 部署时的宿主机本地IP，但是需要把宿主机固定为静态 IP；或者统一为一个固定域名；目的是为了避免对象存储签名 URL 时，签发与上传的 URL 不一致导致的 403 错误。
>
> 具体查看 [对象存储配置及常见问题](/docs/introduction/development/object-storage)
> 具体查看 [对象存储配置及常见问题](/docs/self-host/config/object-storage)
### 登录系统后，浏览器无法响应
......@@ -307,7 +303,7 @@ docker-compose up -d
### 如何更新版本？
1. 查看[更新文档](/docs/upgrading)，确认要升级的版本，避免跨版本升级。
1. 查看[更新文档](/docs/self-host/upgrading/upgrade-intruction)，确认要升级的版本，避免跨版本升级。
2. 修改镜像 tag 到指定版本
3. 执行下面命令会自动拉取镜像：
......@@ -320,7 +316,7 @@ docker-compose up -d
### 如何自定义配置文件？
修改`config.json`文件，并执行`docker-compose down`再执行`docker-compose up -d`重起容器。具体配置，参考[配置详解](/docs/introduction/development/configuration)。
修改`config.json`文件，并执行`docker-compose down`再执行`docker-compose up -d`重起容器。具体配置，参考[配置详解](/docs/self-host/config/json)。
### 如何检查自定义配置文件是否挂载
......
document/content/docs/introduction/development/sealos.en.mdx → document/content/docs/self-host/deploy/sealos.en.mdx
......@@ -13,7 +13,7 @@ import { Alert } from '@/components/docs/Alert';
FastGPT uses the one-api project to manage model pools, supporting OpenAI, Azure, mainstream domestic models, and local models.
See: [Quick OneAPI Deployment on Sealos](/docs/introduction/development/modelconfig/one-api)
See: [Quick OneAPI Deployment on Sealos](/docs/self-host/config/model/one-api)
## One-Click Deployment
......@@ -79,7 +79,7 @@ Password: the `root_password` you set during one-click deployment
You must configure at least one model set, or the system won't work properly.
[View model configuration tutorial](./modelConfig/intro/)
[View model configuration tutorial](/docs/self-host/config/model/intro)
## Pricing
......@@ -109,13 +109,13 @@ In **App Launchpad**, select FastGPT, click **Change**, and you'll see environme
### How to Update/Upgrade FastGPT
[Upgrade script documentation](./upgrading/) — read the docs first to determine which version to upgrade to. Do not skip versions.
[Upgrade script documentation](/docs/self-host/upgrading/upgrade-intruction) — read the docs first to determine which version to upgrade to. Do not skip versions.
For example, if you're on version 4.5 and want to upgrade to 4.5.1: change the image version to v4.5.1, run the upgrade script, wait for completion, then continue upgrading. If the target version doesn't require initialization, skip it.
Upgrade steps:
1. Check the [update documentation](./upgrading/index/) to confirm the target version — avoid skipping versions.
1. Check the [update documentation](/docs/self-host/upgrading/upgrade-intruction) to confirm the target version — avoid skipping versions.
2. Open Sealos app management
3. There are 2 apps: fastgpt, fastgpt-pro
4. Click the 3 dots on the right side of the app, then **Change**. Or click details, then **Change** in the top right.
......@@ -144,7 +144,7 @@ Open Sealos app management -> find the app -> **Change** -> scroll down to advan
![](/imgs/onsealos5.png)
[Config file reference](./configuration/)
[Config file reference](/docs/self-host/config/json)
### Modify Site Name and Favicon
......@@ -184,4 +184,4 @@ Add a mounted file with path: `/app/projects/app/public/icon/logo.svg`, with the
### Using OneAPI
[See OneAPI usage guide](/docs/introduction/development/modelconfig/one-api/)
[See OneAPI usage guide](/docs/self-host/config/model/one-api/)
document/content/docs/introduction/development/sealos.mdx → document/content/docs/self-host/deploy/sealos.mdx
---
title: 通过 Sealos 部署
title: Sealos 部署
description: 使用 Sealos 一键部署 FastGPT
---
......@@ -13,7 +13,7 @@ import { Alert } from '@/components/docs/Alert';
FastGPT 使用了 one-api 项目来管理模型池，其可以兼容 OpenAI 、Azure 、国内主流模型和本地模型等。
可参考：[Sealos 快速部署 OneAPI](/docs/introduction/development/modelconfig/one-api)
可参考：[Sealos 快速部署 OneAPI](/docs/self-host/config/model/one-api)
## 一键部署
......@@ -79,7 +79,7 @@ FastGPT 使用了 one-api 项目来管理模型池，其可以兼容 OpenAI 、A
务必先配置至少一组模型，否则系统无法正常使用。
[点击查看模型配置教程](./modelConfig/intro/)
[点击查看模型配置教程](/docs/self-host/config/model/intro)
## 收费
......@@ -110,13 +110,13 @@ FastGPT 商业版共包含了2个应用（fastgpt, fastgpt-plus）和2个数据
### 如何更新/升级 FastGPT
[升级脚本文档](./upgrading/)先看下文档，看下需要升级哪个版本。注意，不要跨版本升级！！！！！
[升级脚本文档](/docs/self-host/upgrading/upgrade-intruction)先看下文档，看下需要升级哪个版本。注意，不要跨版本升级！！！！！
例如，目前是4.5 版本，要升级到4.5.1，就先把镜像版本改成v4.5.1，执行一下升级脚本，等待完成后再继续升级。如果目标版本不需要执行初始化，则可以跳过。
升级步骤：
1. 查看[更新文档](./upgrading/index/)，确认要升级的版本，避免跨版本升级。
1. 查看[更新文档](/docs/self-host/upgrading/upgrade-intruction)，确认要升级的版本，避免跨版本升级。
2. 打开 sealos 的应用管理
3. 有2个应用 fastgpt ， fastgpt-pro
4. 点击对应应用右边3个点，变更。或者点详情后右上角的变更。
......@@ -145,7 +145,7 @@ FastGPT 商业版共包含了2个应用（fastgpt, fastgpt-plus）和2个数据
![](/imgs/onsealos5.png)
[配置文件参考](./configuration/)
[配置文件参考](/docs/self-host/config/json)
### 修改站点名称以及 favicon
......@@ -184,4 +184,4 @@ SYSTEM_FAVICON 可以是一个网络地址
### One API 使用
[参考 OneAPI 使用步骤](/docs/introduction/development/modelconfig/one-api/)
[参考 OneAPI 使用步骤](/docs/self-host/config/model/one-api/)
document/content/docs/self-host/design/meta.en.json 0 → 100644
{
"title": "Design Documentation",
"pages": ["dataset","design_plugin"]
}
document/content/docs/introduction/development/intro.en.mdx → document/content/docs/self-host/dev.en.mdx
......@@ -72,7 +72,7 @@ cp .env.template .env.local
**2. config.json Configuration File**
Copy `data/config.json` to create `data/config.local.json`. For detailed parameters, see [Configuration Guide](/docs/introduction/development/configuration).
Copy `data/config.json` to create `data/config.local.json`. For detailed parameters, see [Configuration Guide](/docs/self-host/config/model/intro).
```bash
cp data/config.json data/config.local.json
......
document/content/docs/introduction/development/intro.mdx → document/content/docs/self-host/dev.mdx
---
title: 开始本地开发
title: 本地开发
description: 对 FastGPT 进行开发调试
---
......@@ -73,7 +73,7 @@ cp .env.template .env.local
**2. config.json 配置文件**
复制 `data/config.json` 文件，生成一个 `data/config.local.json` 配置文件，具体配置参数说明，可参考 [config 配置说明](/docs/introduction/development/configuration)
复制 `data/config.json` 文件，生成一个 `data/config.local.json` 配置文件，具体配置参数说明，可参考 [config 配置说明](/docs/self-host/config/model/intro)
```bash
cp data/config.json data/config.local.json
......
document/content/docs/introduction/development/faq.en.mdx → document/content/docs/self-host/faq.en.mdx
......@@ -18,7 +18,7 @@ When the frontend crashes, the page will display an error prompting you to check
### OneAPI Errors
Errors with `requestId` are from OneAPI, usually caused by model API issues. See [Common OneAPI Errors](/docs/introduction/development/faq/#3-common-oneapi-errors)
Errors with `requestId` are from OneAPI, usually caused by model API issues. See [Common OneAPI Errors](/docs/self-host/faq/#3-common-oneapi-errors)
## 2. General Issues
......@@ -122,7 +122,7 @@ If OneAPI doesn't have the model configured, don't add it to `config.json` eithe
### Model Test Click Fails
OneAPI only tests the first model in a channel, and only chat models. Vector models can't be auto-tested — send manual requests. [View test command examples](/docs/introduction/development/faq/#how-to-check-model-issues)
OneAPI only tests the first model in a channel, and only chat models. Vector models can't be auto-tested — send manual requests. [View test command examples](/docs/self-host/faq/#how-to-check-model-issues)
### get request url failed: Post `"https://xxx"` dial tcp: xxxx
......
document/content/docs/introduction/development/faq.mdx → document/content/docs/self-host/faq.mdx
......@@ -18,7 +18,7 @@ description: FastGPT 私有部署常见问题
### OneAPI 错误
带有`requestId`的，都是 OneAPI 提示错误，大部分都是因为模型接口报错。可以参考 [OneAPI 常见错误](/docs/introduction/development/faq/#三常见的-oneapi-错误)
带有`requestId`的，都是 OneAPI 提示错误，大部分都是因为模型接口报错。可以参考 [OneAPI 常见错误](/docs/self-host/faq/#三常见的-oneapi-错误)
## 二、通用问题
......@@ -122,7 +122,7 @@ FastGPT 模型配置文件中的 model 必须与 OneAPI 渠道中的模型对应
### 点击模型测试失败
OneAPI 只会测试渠道的第一个模型，并且只会测试对话模型，向量模型无法自动测试，需要手动发起请求进行测试。[查看测试模型命令示例](/docs/introduction/development/faq/#如何检查模型问题)
OneAPI 只会测试渠道的第一个模型，并且只会测试对话模型，向量模型无法自动测试，需要手动发起请求进行测试。[查看测试模型命令示例](/docs/self-host/faq/#如何检查模型问题)
### get request url failed: Post `"https://xxx"` dial tcp: xxxx
......
document/content/docs/protocol/index.en.mdx → document/content/docs/self-host/index.en.mdx
---
title: Protocols
description: FastGPT Protocols
title: Self-Host
description: FastGPT Self-Host
---
import { Redirect } from '@/components/docs/Redirect';
<Redirect to="/docs/protocol/open-source" />
<Redirect to="/docs/self-host/deploy/docker" />
document/content/docs/protocol/index.mdx → document/content/docs/self-host/index.mdx
---
title: 协议
description: FastGPT 协议
title: 自部署
description: FastGPT 自部署
---
import { Redirect } from '@/components/docs/Redirect';
<Redirect to="/docs/protocol/open-source" />
\ No newline at end of file
<Redirect to="/docs/self-host/deploy/docker" />
\ No newline at end of file
document/content/docs/self-host/meta.en.json 0 → 100644
{
"title": "Self-Hosting",
"description": "FastGPT self-hosting guide",
"root": true,
"pages": [
"---Getting Started---",
"deploy/docker",
"deploy/sealos",
"dev",
"---Configuration---",
"config/model",
"config/object-storage",
"config/json",
"config/signoz",
"---Troubleshooting---",
"faq",
"troubleshooting/object-storage",
"---Version Upgrades---",
"upgrading/upgrade-intruction",
"...upgrading",
"---Other---",
"migration",
"custom-models",
"design"
]
}
document/content/docs/self-host/meta.json 0 → 100644
{
"title": "自部署",
"description": "FastGPT 自部署使用案例",
"root": true,
"pages": [
"---开始---",
"deploy/docker",
"deploy/sealos",
"dev",
"---配置说明---",
"config/model",
"config/object-storage",
"config/json",
"config/signoz",
"---故障排查---",
"faq",
"---版本升级---",
"upgrading/upgrade-intruction",
"...upgrading",
"---其他---",
"migration",
"custom-models",
"design"
]
}
document/content/docs/introduction/development/migration/meta.en.json → document/content/docs/self-host/migration/meta.en.json
{
"title": "Migration & Backup",
"pages": [
"docker_db",
"docker_mongo"
]
"pages": ["docker_db","docker_mongo"]
}
document/content/docs/upgrading/4-10/meta.json → document/content/docs/self-host/upgrading/4-12/meta.json
{
"title": "4.10.x",
"title": "4.12.x",
"description": "",
"pages": ["4101", "4100"]
"pages": ["4124", "4123", "4122", "4121", "4120"]
}
document/content/docs/upgrading/4-11/meta.json → document/content/docs/self-host/upgrading/4-13/meta.json
{
"title": "4.11.x",
"title": "4.13.x",
"description": "",
"pages": ["4111", "4110"]
"pages": ["4132", "4131", "4130"]
}
document/content/docs/upgrading/4-14/4145.en.mdx → document/content/docs/self-host/upgrading/4-14/4145.en.mdx
......@@ -7,7 +7,7 @@ description: 'FastGPT V4.14.5 Release Notes'
### 1. Update Storage Bucket Environment Variables
This version adds native support for OSS and COS in addition to MinIO, so the related environment variables need to be renamed. Below is the configuration for MinIO. For other providers, refer to [Object Storage Configuration](/docs/introduction/development/object-storage).
This version adds native support for OSS and COS in addition to MinIO, so the related environment variables need to be renamed. Below is the configuration for MinIO. For other providers, refer to [Object Storage Configuration](/docs/self-host/config/object-storage).
**New Variables**
......
document/content/docs/upgrading/4-14/4145.mdx → document/content/docs/self-host/upgrading/4-14/4145.mdx
......@@ -7,7 +7,7 @@ description: 'FastGPT V4.14.5 更新说明'
### 1. 修改存储桶环境变量
该版本除了支持 minio 以外，还增加支持了原生 OSS 和 COS, 所以需要修改相关环境变量修改成新的命名。下面是 Minio 的配置参数，其他厂商配置，可参考[对象存储配置问题](/docs/introduction/development/object-storage)
该版本除了支持 minio 以外，还增加支持了原生 OSS 和 COS, 所以需要修改相关环境变量修改成新的命名。下面是 Minio 的配置参数，其他厂商配置，可参考[对象存储配置问题](/docs/self-host/config/object-storage)
**新增变量**
......
document/content/docs/self-host/upgrading/meta.en.json 0 → 100644
{
"title": "Version History",
"description": "FastGPT version history",
"pages": ["4-14", "4-13", "4-12", "outdated"]
}
document/content/docs/self-host/upgrading/meta.json 0 → 100644
{
"title": "版本列表",
"description": "FastGPT 版本列表",
"pages": ["4-14", "4-13", "4-12", "outdated"]
}
document/content/docs/upgrading/4-8/45.en.mdx → document/content/docs/self-host/upgrading/outdated/45.en.mdx
......@@ -84,4 +84,4 @@ CREATE INDEX CONCURRENTLY vector_index ON modeldata USING hnsw (vector vector_ip
## Configuration File Changes Required
For the latest configuration, refer to: [V4.5 Latest config.json](/docs/introduction/development/configuration)
For the latest configuration, refer to: [V4.5 Latest config.json](/docs/self-host/config/json)
document/content/docs/upgrading/4-8/45.mdx → document/content/docs/self-host/upgrading/outdated/45.mdx
......@@ -84,4 +84,4 @@ CREATE INDEX CONCURRENTLY vector_index ON modeldata USING hnsw (vector vector_ip
## 该版本需要修改 `config.json` 文件
最新配置可参考: [V45版本最新 config.json](/docs/introduction/development/configuration)
最新配置可参考: [V45版本最新 config.json](/docs/self-host/config/json)
document/content/docs/upgrading/4-8/46.en.mdx → document/content/docs/self-host/upgrading/outdated/46.en.mdx
......@@ -9,7 +9,7 @@ description: FastGPT V4.6 Update
Update the image to the latest or V4.6 version. For the commercial edition, update to V0.2.1.
For the latest configuration, refer to: [V4.6 Latest config.json](/docs/introduction/development/configuration). The commercial edition configuration file has also been updated — refer to the latest Lark documentation.
For the latest configuration, refer to: [V4.6 Latest config.json](/docs/self-host/config/json). The commercial edition configuration file has also been updated — refer to the latest Lark documentation.
## 2. Run the Initialization APIs
......
document/content/docs/upgrading/4-8/46.mdx → document/content/docs/self-host/upgrading/outdated/46.mdx
......@@ -9,7 +9,7 @@ description: FastGPT V4.6 更新
更新镜像至 latest 或者 v4.6 版本。商业版镜像更新至 V0.2.1
最新配置可参考：[V46 版本最新 config.json](/docs/introduction/development/configuration)，商业镜像配置文件也更新，参考最新的飞书文档。
最新配置可参考：[V46 版本最新 config.json](/docs/self-host/config/json)，商业镜像配置文件也更新，参考最新的飞书文档。
## 2。执行初始化 API
......
document/content/docs/upgrading/4-8/465.en.mdx → document/content/docs/self-host/upgrading/outdated/465.en.mdx
......@@ -7,7 +7,7 @@ description: FastGPT V4.6.5
Since OpenAI has begun deprecating function calls in favor of tool choice, FastGPT has updated its configuration and invocation methods accordingly. You'll need to make some changes to your configuration file:
[View the latest configuration file](/docs/introduction/development/configuration/)
[View the latest configuration file](/docs/self-host/config/json/)
1. The main change is renaming the `functionCall` field to `toolChoice` in your model configuration. Models with this set to `true` will use OpenAI's tools mode by default; models without it or with it set to `false` will use prompt-based generation.
......
document/content/docs/upgrading/4-8/465.mdx → document/content/docs/self-host/upgrading/outdated/465.mdx
......@@ -7,7 +7,7 @@ description: FastGPT V4.6.5
由于 openai 已开始弃用 function call，改为 toolChoice。FastGPT 同步的修改了对于的配置和调用方式，需要对配置文件做一些修改：
[点击查看最新的配置文件](/docs/introduction/development/configuration/)
[点击查看最新的配置文件](/docs/self-host/config/json/)
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。
......
document/content/docs/upgrading/4-8/466.en.mdx → document/content/docs/self-host/upgrading/outdated/466.en.mdx
......@@ -5,7 +5,7 @@ description: FastGPT V4.6.6
## Configuration Changes
To reduce code duplication, we've made some changes to the configuration file: [View the latest configuration file](/docs/introduction/development/configuration/)
To reduce code duplication, we've made some changes to the configuration file: [View the latest configuration file](/docs/self-host/config/json/)
## Commercial Edition Changes
......@@ -21,7 +21,7 @@ To reduce code duplication, we've made some changes to the configuration file: [
1. Check out the [FastGPT 2024 RoadMap](https://github.com/labring/FastGPT?tab=readme-ov-file#-%E5%9C%A8%E7%BA%BF%E4%BD%BF%E7%94%A8).
2. New - HTTP node now supports a JSON editor for request headers.
3. New - [ReRank Model Deployment](/docs/introduction/development/custom-models/bge-rerank/)
3. New - [ReRank Model Deployment](/docs/self-host/custom-models/bge-rerank/)
4. New - Search modes: separated vector semantic search, full-text search, and reranking, with RRF (Reciprocal Rank Fusion) for merging results.
5. Improved - Question classifier prompts with ID-guided classification. Tested with Chinese commercial API models (Baidu, Alibaba, Zhipu, iFlytek) — all work correctly in Prompt mode.
6. UI improvements — the interface will be gradually updated with a new design going forward.
......
document/content/docs/upgrading/4-8/466.mdx → document/content/docs/self-host/upgrading/outdated/466.mdx
......@@ -5,7 +5,7 @@ description: FastGPT V4.6.6
## 配置文件变更
为了减少代码重复度，我们对配置文件做了一些修改：[点击查看最新的配置文件](/docs/introduction/development/configuration/)
为了减少代码重复度，我们对配置文件做了一些修改：[点击查看最新的配置文件](/docs/self-host/config/json/)
## 商业版变更
......@@ -21,7 +21,7 @@ description: FastGPT V4.6.6
1. 查看 [FastGPT 2024 RoadMap](https://github.com/labring/FastGPT?tab=readme-ov-file#-%E5%9C%A8%E7%BA%BF%E4%BD%BF%E7%94%A8)
2. 新增 - Http 模块请求头支持 Json 编辑器。
3. 新增 - [ReRank模型部署](/docs/introduction/development/custom-models/bge-rerank/)
3. 新增 - [ReRank模型部署](/docs/self-host/custom-models/bge-rerank/)
4. 新增 - 搜索方式：分离向量语义检索，全文检索和重排，通过 RRF 进行排序合并。
5. 优化 - 问题分类提示词，id引导。测试国产商用 api 模型（百度阿里智谱讯飞）使用 Prompt 模式均可分类。
6. UI 优化，未来将逐步替换新的UI设计。
......
document/content/docs/upgrading/4-8/468.en.mdx → document/content/docs/self-host/upgrading/outdated/468.en.mdx
......@@ -67,7 +67,7 @@ docker-compose up -d
## Update Configuration File
Removed duplicate model configurations. All LLM models are now consolidated into a single property. [View the latest configuration file](/docs/introduction/development/configuration/)
Removed duplicate model configurations. All LLM models are now consolidated into a single property. [View the latest configuration file](/docs/self-host/config/json/)
## Commercial Edition Initialization
......
document/content/docs/upgrading/4-8/468.mdx → document/content/docs/self-host/upgrading/outdated/468.mdx
......@@ -67,7 +67,7 @@ docker-compose up -d
## 修改配置文件
去除了重复的模型配置，LLM模型都合并到一个属性中：[点击查看最新的配置文件](/docs/introduction/development/configuration/)
去除了重复的模型配置，LLM模型都合并到一个属性中：[点击查看最新的配置文件](/docs/self-host/config/json/)
## 商业版初始化
......
document/content/docs/upgrading/4-8/47.en.mdx → document/content/docs/self-host/upgrading/outdated/47.en.mdx
......@@ -5,7 +5,7 @@ description: FastGPT V4.7 Release Notes
## 1. Update Configuration File
Added Boolean values to control which models are available for different feature modules, and added model logos. [View the latest configuration file](/docs/introduction/development/configuration/)
Added Boolean values to control which models are available for different feature modules, and added model logos. [View the latest configuration file](/docs/self-host/config/json/)
## 2. Initialization Script
......
document/content/docs/upgrading/4-8/47.mdx → document/content/docs/self-host/upgrading/outdated/47.mdx
......@@ -5,7 +5,7 @@ description: FastGPT V4.7更新说明
## 1. 修改配置文件
增加一些 Boolean 值，用于决定不同功能块可以使用哪些模型，同时增加了模型的 logo：[点击查看最新的配置文件](/docs/introduction/development/configuration/)
增加一些 Boolean 值，用于决定不同功能块可以使用哪些模型，同时增加了模型的 logo：[点击查看最新的配置文件](/docs/self-host/config/json/)
## 2. 初始化脚本
......
document/content/docs/upgrading/4-8/471.en.mdx → document/content/docs/self-host/upgrading/outdated/471.en.mdx
......@@ -17,7 +17,7 @@ This request runs stale data cleanup (removes invalid files, images, Knowledge B
## Update Configuration File
Added Laf environment configuration. [View the latest configuration file](/docs/introduction/development/configuration/)
Added Laf environment configuration. [View the latest configuration file](/docs/self-host/config/json/)
## V4.7.1 Release Notes
......
document/content/docs/upgrading/4-8/471.mdx → document/content/docs/self-host/upgrading/outdated/471.mdx
......@@ -17,7 +17,7 @@ curl --location --request POST 'https://{{host}}/api/admin/clearInvalidData' \
## 修改配置文件
增加了Laf环境配置：[点击查看最新的配置文件](/docs/introduction/development/configuration/)
增加了Laf环境配置：[点击查看最新的配置文件](/docs/self-host/config/json/)
## V4.7.1 更新说明
......
document/content/docs/upgrading/4-8/4815.en.mdx → document/content/docs/self-host/upgrading/outdated/4815.en.mdx
......@@ -52,7 +52,7 @@ This recalculates free-tier user durations. A previous version upgrade did not r
1. New - API Knowledge Base. See [API Knowledge Base Introduction](/docs/introduction/guide/knowledge_base/api_dataset/). The external file library will be deprecated.
2. New - Toolbox page displaying all available system resources. The commercial edition admin panel now offers easier configuration of system plugins and custom categories.
3. New - HTML code in Markdown is now rendered separately. You can choose preview mode, which blocks all scripts and only displays content.
4. New - Custom system-level file parsing service. See [Integrating Marker PDF Document Parsing](/docs/introduction/development/custom-models/marker/).
4. New - Custom system-level file parsing service. See [Integrating Marker PDF Document Parsing](/docs/self-host/custom-models/marker/).
5. New - Collections can be reconfigured directly without deleting and re-importing.
6. New - Commercial edition admin panel supports configuring sidebar navigation links.
7. Improved - Base64 image truncation detection.
......
document/content/docs/upgrading/4-8/4815.mdx → document/content/docs/self-host/upgrading/outdated/4815.mdx
......@@ -52,7 +52,7 @@ curl --location --request POST 'https://{{host}}/api/admin/init/refreshFreeUser'
1. 新增 - API 知识库, 见 [API 知识库介绍](/docs/introduction/guide/knowledge_base/api_dataset/)，外部文件库会被弃用。
2. 新增 - 工具箱页面，展示所有可用的系统资源。商业版后台可更便捷的配置系统插件和自定义分类。
3. 新增 - Markdown 中，HTML代码会被额外渲染，可以选择预览模式，会限制所有 script 脚本，仅做展示。
4. 新增 - 自定义系统级文件解析服务, 见 [接入 Marker PDF 文档解析](/docs/introduction/development/custom-models/marker/)
4. 新增 - 自定义系统级文件解析服务, 见 [接入 Marker PDF 文档解析](/docs/self-host/custom-models/marker/)
5. 新增 - 集合直接重新调整参数，无需删除再导入。
6. 新增 - 商业版后台支持配置侧边栏跳转链接。
7. 优化 - base64 图片截取判断。
......
document/content/docs/upgrading/4-8/4816.en.mdx → document/content/docs/self-host/upgrading/outdated/4816.en.mdx
......@@ -13,7 +13,7 @@ description: FastGPT V4.8.16 Release Notes
### 2. Update configuration file
Refer to the latest [configuration file documentation](/docs/introduction/development/configuration/) and update your `config.json` or admin model configuration. Add the `provider` field to LLMModel and VectorModel for model categorization. For example:
Refer to the latest [configuration file documentation](/docs/self-host/config/json/) and update your `config.json` or admin model configuration. Add the `provider` field to LLMModel and VectorModel for model categorization. For example:
```json
{
......
document/content/docs/upgrading/4-8/4816.mdx → document/content/docs/self-host/upgrading/outdated/4816.mdx
......@@ -13,7 +13,7 @@ description: FastGPT V4.8.16 更新说明
### 2. 更新配置文件
参考最新的[配置文件](/docs/introduction/development/configuration/)，更新 `config.json` 或 admin 中模型文件配置。给 LLMModel 和 VectorModel 增加 `provider` 字段，以便进行模型分类。例如：
参考最新的[配置文件](/docs/self-host/config/json/)，更新 `config.json` 或 admin 中模型文件配置。给 LLMModel 和 VectorModel 增加 `provider` 字段，以便进行模型分类。例如：
```json
{
......
document/content/docs/upgrading/4-8/4820.en.mdx → document/content/docs/self-host/upgrading/outdated/4820.en.mdx
......@@ -31,7 +31,7 @@ The script automatically loads models from the old configuration file into the n
## Full Release Notes
1. New - Visual model parameter configuration, replacing the old config file approach. Over 100 model presets included, with one-click testing for all model types. (Full in-page channel configuration is planned for the next version.) [View model configuration guide](/docs/introduction/development/modelconfig/intro/)
1. New - Visual model parameter configuration, replacing the old config file approach. Over 100 model presets included, with one-click testing for all model types. (Full in-page channel configuration is planned for the next version.) [View model configuration guide](/docs/self-host/config/model/intro/)
2. New - DeepSeek Reasoner model supports outputting the thinking process.
3. New - Usage record export and dashboard.
4. New - Markdown syntax extension supporting audio and video (via `audio` and `video` code blocks).
......
document/content/docs/upgrading/4-8/4820.mdx → document/content/docs/self-host/upgrading/outdated/4820.mdx
......@@ -31,7 +31,7 @@ curl --location --request POST 'https://{{host}}/api/admin/initv4820' \
## 完整更新内容
1. 新增 - 可视化模型参数配置，取代原配置文件配置模型。预设超过 100 个模型配置。同时支持所有类型模型的一键测试。（预计下个版本会完全支持在页面上配置渠道）。[点击查看模型配置方案](/docs/introduction/development/modelconfig/intro/)
1. 新增 - 可视化模型参数配置，取代原配置文件配置模型。预设超过 100 个模型配置。同时支持所有类型模型的一键测试。（预计下个版本会完全支持在页面上配置渠道）。[点击查看模型配置方案](/docs/self-host/config/model/intro/)
2. 新增 - DeepSeek resoner 模型支持输出思考过程。
3. 新增 - 使用记录导出和仪表盘。
4. 新增 - markdown 语法扩展，支持音视频（代码块 audio 和 video）。
......
document/content/docs/self-host/upgrading/outdated/484.en.mdx 0 → 100644
---
title: V4.8.4 (Includes Upgrade Script)
description: FastGPT V4.8.4 Release Notes
---
## Upgrade Guide
### 1. Update Images
- Update the fastgpt image tag to v4.8.4
- Update the fastgpt-sandbox image tag to v4.8.4 (optional, no changes)
- Update the commercial edition image tag to v4.8.4
### 2. Commercial Edition Initialization
From any terminal, send 1 HTTP request. Replace `{{rootkey}}` with the `rootkey` from your environment variables, and `{{host}}` with your **FastGPT commercial edition domain**.
```bash
curl --location --request POST 'https://{{host}}/api/admin/init/484' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
## V4.8.4 Release Notes
1. New - Apps now use the new permission system.
2. New - Apps now support folders.
3. Improved - Text splitting now removes consecutive line breaks and tabs to avoid performance issues with large text.
4. Critical Fix - Fixed system plugin runtime pool data pollution. Since data was loaded from memory, it caused global state contamination.
5. Fixed - Debug mode showing abnormal connections when source and target content are identical.
6. Fixed - Scheduled execution initialization error.
7. Fixed - App invocation parameter passing error.
8. Fixed - Incorrect nodeId when copying complex nodes with Ctrl+C/V.
9. Adjusted global theme for the component library.
document/content/docs/self-host/upgrading/outdated/484.mdx 0 → 100644
---
title: V4.8.4(包含升级脚本)
description: FastGPT V4.8.4 更新说明
---
## 升级指南
### 1. 修改镜像
- fastgpt 镜像 tag 修改成 v4.8.4
- fastgpt-sandbox 镜像 tag 修改成 v4.8.4 (选择性，无变更)
- 商业版镜像 tag 修改成 v4.8.4
### 2. 商业版用户执行初始化
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 商业版的域名**。
```bash
curl --location --request POST 'https://{{host}}/api/admin/init/484' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
## V4.8.4 更新说明
1. 新增 - 应用使用新权限系统。
2. 新增 - 应用支持文件夹。
3. 优化 - 文本分割增加连续换行、制表符清除，避免大文本性能问题。
4. 重要修复 - 修复系统插件运行池数据污染问题，由于从内存获取，会导致全局污染。
5. 修复 - Debug 模式下，相同 source 和 target 内容，导致连线显示异常。
6. 修复 - 定时执行初始化错误。
7. 修复 - 应用调用传参异常。
8. 修复 - ctrl + cv 复杂节点时，nodeId错误。
9. 调整组件库全局theme。
document/content/docs/self-host/upgrading/outdated/485.en.mdx 0 → 100644
---
title: V4.8.5 (Includes Upgrade Script)
description: FastGPT V4.8.5 Release Notes
---
## Upgrade Guide
### 1. Back Up Your Database
### 2. Update Images
- Update the fastgpt image tag to v4.8.5
- Update the commercial edition image tag to v4.8.5
### 3. Run Initialization
From any terminal, send 1 HTTP request. Replace `{{rootkey}}` with the `rootkey` from your environment variables, and `{{host}}` with your **FastGPT domain**.
```bash
curl --location --request POST 'https://{{host}}/api/admin/initv485' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
This will merge the plugin data table into the app table. The plugin table will not be deleted.
------
**Commercial edition users: run the additional initialization below**
From any terminal, send 1 HTTP request. Replace `{{rootkey}}` with the `rootkey` from your environment variables, and `{{host}}` with your **FastGPT domain**:
```bash
curl --location --request POST 'https://{{host}}/api/admin/init/485' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
This will reset the Knowledge Base permission system.
## V4.8.5 Release Notes
1. New - Merged plugins and apps into a unified workspace.
2. New - App duplication feature.
3. New - App template creation.
4. New - Code execution results can now be used as tool output.
5. New - Markdown image output supports pinch-to-zoom on mobile.
6. Improved - Raw file encoding for storage and retrieval.
7. Improved - Simple mode now filters out deleted Knowledge Bases to avoid false error states.
8. Improved - Folder reading now supports more than 100 files per folder.
9. Improved - QA splitting / manual entry: when an `a` field is present, the `q` field is automatically used as a supplementary index.
10. Improved - Chat dialog page code.
11. Improved - New workflow nodes are now auto-numbered.
12. Fixed - Scheduled tasks could not actually be disabled.
13. Fixed - Input guide special characters causing regex errors.
14. Fixed - Files containing unescaped `%` characters causing page crashes.
15. Fixed - Page crash when selecting Knowledge Base references in custom input.
document/content/docs/self-host/upgrading/outdated/485.mdx 0 → 100644
---
title: V4.8.5(包含升级脚本)
description: FastGPT V4.8.5 更新说明
---
## 升级指南
### 1. 做好数据库备份
### 2. 修改镜像
- fastgpt 镜像 tag 修改成 v4.8.5
- 商业版镜像 tag 修改成 v4.8.5
### 3. 执行初始化
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/initv485' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
会把插件的数据表合并到应用中，插件表不会删除。
------
**商业版用户执行额外的初始化**
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/init/485' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
会重置知识库权限系统。
## V4.8.5 更新说明
1. 新增 - 合并插件和应用，统一成工作台
2. 新增 - 应用创建副本功能
3. 新增 - 应用创建模板
4. 新增 - 支持代码运行结果作为工具输出。
5. 新增 - Markdown 图片输出，支持移动端放大缩放。
6. 优化 - 原文件编码存取
7. 优化 - 知识库删除后，简易模式会过滤掉删除的知识库，避免错误判断。
8. 优化 - 文件夹读取，支持单个文件夹超出 100 个文件
9. 优化 - 问答拆分/手动录入，当有`a`字段时，自动将`q`作为补充索引。
10. 优化 - 对话框页面代码
11. 优化 - 工作流新节点自动增加序号名
12. 修复 - 定时任务无法实际关闭
13. 修复 - 输入引导特殊字符导致正则报错
14. 修复 - 文件包含特殊字符`%`，且为转义时会导致页面崩溃
15. 修复 - 自定义输入选择知识库引用时页面崩溃
document/content/docs/self-host/upgrading/outdated/486.en.mdx 0 → 100644
---
title: V4.8.6 (Includes Upgrade Script)
description: FastGPT V4.8.6 Release Notes
---
## Upgrade Guide
### 1. Back Up Your Database
### 2. Update Images
- Update the fastgpt image tag to v4.8.6
- Update the fastgpt-sandbox image tag to v4.8.6
- Update the commercial edition image tag to v4.8.6
### 3. Run Initialization
From any terminal, send 1 HTTP request. Replace `{{rootkey}}` with the `rootkey` from your environment variables, and `{{host}}` with your **FastGPT domain**.
```bash
curl --location --request POST 'https://{{host}}/api/admin/initv486' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
This will initialize inherited permissions for apps.
-------
## V4.8.6 Release Notes
1. New - App permission inheritance.
2. New - Knowledge Base now supports disabling individual collections.
3. New - System plugin architecture change. Added link reader and math calculator plugins. The official release will include documentation on creating custom system plugins.
4. New - Code sandbox runtime parameters.
5. New - Option to hide the header during AI conversations, primarily for mobile optimization.
6. Improved - File reading now defaults to MongoDB secondary nodes to reduce primary node load.
7. Improved - Prompt templates.
8. Improved - Fixed duplicate Mongo model loading.
9. Fixed - Creating a link collection not returning the ID.
10. Fixed - API documentation descriptions.
11. Fixed - API system prompt merging.
12. Fixed - Content inside team plugin folders failing to load.
13. Fixed - Knowledge Base collection folder breadcrumbs failing to load.
14. Fixed - Markdown export conversation error.
15. Fixed - Prompt template closing tag error.
16. Fixed - Documentation descriptions.
document/content/docs/self-host/upgrading/outdated/486.mdx 0 → 100644
---
title: V4.8.6(包含升级脚本)
description: FastGPT V4.8.6 更新说明
---
## 升级指南
### 1. 做好数据库备份
### 2. 修改镜像
- fastgpt 镜像 tag 修改成 v4.8.6
- fastgpt-sandbox 镜像 tag 修改成 v4.8.6
- 商业版镜像 tag 修改成 v4.8.6
### 3. 执行初始化
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/initv486' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
会初始化应用的继承权限
-------
## V4.8.6 更新说明
1. 新增 - 应用权限继承
2. 新增 - 知识库支持单个集合禁用功能
3. 新增 - 系统插件模式变更，新增链接读取和数学计算器插件，正式版会更新如何自定义系统插件
4. 新增 - 代码沙盒运行参数
5. 新增 - AI对话时隐藏头部的功能，主要是适配移动端
6. 优化 - 文件读取，Mongo 默认使用从节点，减轻主节点压力
7. 优化 - 提示词模板
8. 优化 - Mongo model 重复加载
9. 修复 - 创建链接集合未返回 id
10. 修复 - 文档接口说明
11. 修复 - api system 提示合并
12. 修复 - 团队插件目录内的内容无法加载
13. 修复 - 知识库集合目录面包屑无法加载
14. 修复 - Markdown 导出对话异常
15. 修复 - 提示模板结束标签错误
16. 修复 - 文档描述
document/content/docs/self-host/upgrading/outdated/487.en.mdx 0 → 100644
---
title: V4.8.7
description: FastGPT V4.8.7 Release Notes
---
## Upgrade Guide
### 1. Back up your database
### 2. Update images
- Update the fastgpt image tag to v4.8.7
- Update the commercial edition image tag to v4.8.7
-------
## V4.8.7 Release Notes
1. New - Plugins now support standalone execution, publishing, and log viewing.
2. New - App search.
3. Improved - Chat dialog code.
4. Improved - Upgraded Dockerfile Node and pnpm versions.
5. Improved - Vision mode now works properly with local domain deployments.
6. Fixed - Unable to modify global variables in Simple Mode.
7. Fixed - GPT-4o unable to use tools and images simultaneously.
document/content/docs/self-host/upgrading/outdated/488.en.mdx 0 → 100644
---
title: V4.8.8 (Includes Migration Script)
description: FastGPT V4.8.8 Release Notes
---
## Upgrade Guide
### 1. Back up your database
### 2. Update images
- Update the fastgpt image tag to v4.8.8-fix2
- Update the commercial edition image tag to v4.8.8
### 3. Run initialization
From any terminal, send an HTTP request. Replace `{{rootkey}}` with the `rootkey` from your environment variables, and `{{host}}` with your **FastGPT domain**.
```bash
curl --location --request POST 'https://{{host}}/api/admin/initv488' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
This will initialize inherited permissions for Knowledge Bases.
-------
## V4.8.8 Release Notes
[View full release notes](https://github.com/labring/FastGPT/releases/tag/v4.8.8)
1. New - Restructured system plugin architecture. Community members can now submit system plugins via PR. See: [How to Submit System Plugins to the FastGPT Community](https://fael3z0zfze.feishu.cn/wiki/ERZnw9R26iRRG0kXZRec6WL9nwh).
2. New - DuckDuckGo system plugin.
3. New - Lark webhook system plugin.
4. New - Revamped variable input method. Prompt input fields and all Textarea inputs in workflows now support typing `/` to trigger variable selection, allowing you to directly pick any upstream output value without dynamic imports.
5. Commercial - Knowledge Base permission inheritance.
6. Improved - Mobile quick app switching interaction.
7. Improved - Node icons.
8. Improved - Added a dedicated copy button to chat references for easier copying. Added collapsible reference content.
9. Improved - Upgraded OpenAI SDK with a custom Whisper model interface (the SDK's built-in Whisper interface doesn't seem to work well with standard FastAPI endpoints).
10. Fixed - Permission table declaration issue.
11. Fixed - Parallel execution nodes not recording run time correctly.
12. Fixed - Run details not displaying nested node information correctly.
13. Fixed - Simple Mode failing to load Knowledge Base configuration on first entry.
14. Fixed - Log debug level configuration not taking effect.
15. Fixed - When running plugins standalone, plugin input values were being variable-substituted, potentially causing downstream node variable issues.
document/content/docs/self-host/upgrading/outdated/488.mdx 0 → 100644
---
title: V4.8.8(包含升级脚本)
description: FastGPT V4.8.8 更新说明
---
## 升级指南
### 1. 做好数据库备份
### 2. 修改镜像
- fastgpt 镜像 tag 修改成 v4.8.8-fix2
- 商业版镜像 tag 修改成 v4.8.8
### 3. 执行初始化
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/initv488' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
会初始化知识库的继承权限
-------
## V4.8.8 更新说明
[点击查看完整更新](https://github.com/labring/FastGPT/releases/tag/v4.8.8)
1. 新增 - 重构系统插件的结构。允许向开源社区 PR 系统插件，具体可见: [如何向 FastGPT 社区提交系统插件](https://fael3z0zfze.feishu.cn/wiki/ERZnw9R26iRRG0kXZRec6WL9nwh)。
2. 新增 - DuckDuckGo 系统插件。
3. 新增 - 飞书 webhook 系统插件。
4. 新增 - 修改变量填写方式。提示词输入框以以及工作流中所有 Textarea 输入框，支持输入 / 唤起变量选择，可直接选择所有上游输出值，无需动态引入。
5. 商业版新增 - 知识库权限继承。
6. 优化 - 移动端快速切换应用交互。
7. 优化 - 节点图标。
8. 优化 - 对话框引用增加额外复制案件，便于复制。增加引用内容折叠。
9. 优化 - OpenAI sdk 升级，并自定义了 whisper 模型接口（未仔细查看 sdk 实现，但 sdk 中 whisper 接口，似乎无法适配一般 fastapi 接口）
10. 修复 - Permission 表声明问题。
11. 修复 - 并行执行节点，运行时间未正确记录。
12. 修复 - 运行详情未正确展示嵌套节点信息。
13. 修复 - 简易模式，首次进入，无法正确获取知识库配置。
14. 修复 - Log debug level 配置无效。
15. 修复 - 插件独立运行时，会将插件输入的值进行变量替换，可能导致后续节点变量异常。
document/content/docs/self-host/upgrading/outdated/489.en.mdx 0 → 100644
---
title: V4.8.9 (Requires Initialization)
description: FastGPT V4.8.9 Release Notes
---
## Upgrade Guide
### 1. Back up your database
### 2. Update images
- Update the FastGPT image tag to v4.8.9
- Update the FastGPT commercial edition image tag to v4.8.9
- Sandbox image update is optional
### 3. Run initialization (Commercial Edition)
From any terminal, send an HTTP request. Replace `{{rootkey}}` with the `rootkey` from your environment variables, and `{{host}}` with your **FastGPT domain**:
```bash
curl --location --request POST 'https://{{host}}/api/admin/init/489' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
This initializes notification methods for multi-tenancy (internal use only, no action needed).
-------
## V4.8.9 Release Notes
1. New - File upload configuration. Image upload capability is now determined by system configuration rather than relying on vision model availability.
2. New - AI chat node and tool calls support toggling "Enable image recognition". When enabled, it automatically retrieves images uploaded in the chat and image URLs from "User question".
3. New - Document parsing node.
4. Commercial - Team notification account binding for receiving important messages.
5. Commercial - Knowledge Base collection tagging for tag-based management.
6. Commercial - Knowledge Base search node supports tag filtering and creation date filtering.
7. Commercial - Transfer app owner permissions.
8. New - Delete all conversation starters.
9. New - QA splitting supports custom chunk sizes, and optimized the issue where GPT-4o-mini produced very little content with large chunks.
10. Improved - Lazy loading for chat messages to reduce network transfer.
11. Improved - Clear file selection cache to allow re-selecting the same file.
12. Fixed - Knowledge Base file upload progress not reaching 100% under unstable network or with many files.
13. Fixed - After deleting an app, returning to chat and selecting the last conversation from the deleted app showed an error.
14. Fixed - Plugin dynamic variable default values not displaying correctly.
15. Fixed - Tool call temperature and max response values not taking effect.
16. Fixed - In function call mode, GPT models require the `content` parameter in assistant role messages (doesn't affect most models since nearly all have switched to ToolChoice mode; FC mode is deprecated).
17. Fixed - Knowledge Base file upload progress updates could be incorrect.
18. Fixed - Knowledge Base page always resetting to the first page during rebuilding.
19. Fixed - Knowledge Base list OpenAPI authentication issue.
20. Fixed - Unable to provide feedback on new conversations via share links.
document/content/docs/self-host/upgrading/outdated/489.mdx 0 → 100644
---
title: V4.8.9（需要初始化）
description: FastGPT V4.8.9 更新说明
---
## 升级指南
### 1. 做好数据库备份
### 2. 修改镜像
- 更新 FastGPT 镜像 tag: v4.8.9
- 更新 FastGPT 商业版镜像 tag: v4.8.9
- Sandbox 镜像，可以不更新
### 3. 商业版执行初始化
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/init/489' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
会初始化多租户的通知方式，仅内部使用的，无需执行。
-------
## V4.8.9 更新说明
1. 新增 - 文件上传配置，不再依赖视觉模型决定是否可上传图片，而是通过系统配置决定。
2. 新增 - AI 对话节点和工具调用支持选择“是否开启图片识别”，开启后会自动获取对话框上传的图片和“用户问题”中的图片链接。
3. 新增 - 文档解析节点。
4. 商业版新增 - 团队通知账号绑定，用于接收重要信息。
5. 商业版新增 - 知识库集合标签功能，可以对知识库进行标签管理。
6. 商业版新增 - 知识库搜索节点支持标签过滤和创建时间过滤。
7. 商业版新增 - 转移 App owner 权限。
8. 新增 - 删除所有对话引导内容。
9. 新增 - QA 拆分支持自定义 chunk 大小，并优化 gpt4o-mini 拆分时，chunk 太大导致生成内容很少的问题。
10. 优化 - 对话框信息懒加载，减少网络传输。
11. 优化 - 清除选文件缓存，支持重复选择同一个文件。
12. 修复 - 知识库上传文件，网络不稳定或文件较多情况下，进度无法到 100%。
13. 修复 - 删除应用后回到聊天选择最后一次对话的应用为删除的应用时提示无该应用问题。
14. 修复 - 插件动态变量配置默认值时，无法正常显示默认值。
15. 修复 - 工具调用温度和最大回复值未生效。
16. 修复 - 函数调用模式，assistant role 中，GPT 模型必须传入 content 参数。（不影响大部分模型，目前基本都改用用 ToolChoice 模式，FC 模式已弃用）。
17. 修复 - 知识库文件上传进度更新可能异常。
18. 修复 - 知识库 rebuilding 时候，页面总是刷新到第一页。
19. 修复 - 知识库 list openapi 鉴权问题。
20. 修复 - 分享链接，新对话无法反馈。
document/content/docs/upgrading/4-9/490.en.mdx → document/content/docs/self-host/upgrading/outdated/490.en.mdx
......@@ -160,7 +160,7 @@ curl --location --request POST 'https://{{host}}/api/admin/initv490' \
## Compatibility & Deprecations
1. Deprecated — The previous custom file parsing solution for private deployments. Please update to the latest configuration. [See PDF Enhanced Parsing Configuration](/docs/introduction/development/configuration/#使用-doc2x-解析-pdf-文件)
1. Deprecated — The previous custom file parsing solution for private deployments. Please update to the latest configuration. [See PDF Enhanced Parsing Configuration](/docs/self-host/config/json/#使用-doc2x-解析-pdf-文件)
2. Deprecated — The legacy local file upload API: `/api/core/dataset/collection/create/file` (previously available only in the Pro edition). This endpoint has been replaced by: `/api/core/dataset/collection/create/localFile`
3. Maintenance ending, deprecation upcoming — External file library APIs. Use the API File Library as a replacement.
4. API Update — For endpoints that include a `trainingType` field (file upload to knowledge base, link collection creation, API file library, push chunk data, etc.), `trainingType` will only support `chunk` and `QA` modes going forward. Enhanced indexing mode will use a separate field: `autoIndexes`. Legacy `trainingType=auto` code is still supported for now, but please migrate to the new API format as soon as possible. See: [Knowledge Base OpenAPI Documentation](/docs/openapi/dataset.md)
......
document/content/docs/upgrading/4-9/490.mdx → document/content/docs/self-host/upgrading/outdated/490.mdx
......@@ -160,7 +160,7 @@ curl --location --request POST 'https://{{host}}/api/admin/initv490' \
## 兼容 & 弃用
1. 弃用 - 之前私有化部署的自定义文件解析方案，请同步更新到最新的配置方案。[点击查看 PDF 增强解析配置](/docs/introduction/development/configuration/#使用-doc2x-解析-pdf-文件)
1. 弃用 - 之前私有化部署的自定义文件解析方案，请同步更新到最新的配置方案。[点击查看 PDF 增强解析配置](/docs/self-host/config/json/#使用-doc2x-解析-pdf-文件)
2. 弃用 - 弃用旧版本地文件上传 API：/api/core/dataset/collection/create/file（以前仅商业版可用的 API，该接口已放切换成：/api/core/dataset/collection/create/localFile）
3. 停止维护，即将弃用 - 外部文件库相关 API，可通过 API 文件库替代。
4. API更新 - 上传文件至知识库、创建连接集合、API 文件库、推送分块数据等带有 `trainingType` 字段的接口，`trainingType`字段未来仅支持`chunk`和`QA`两种模式。增强索引模式将设置单独字段：`autoIndexes`，目前仍有适配旧版`trainingType=auto`代码，但请尽快变更成新接口类型。具体可见：[知识库 OpenAPI 文档](/docs/openapi/dataset.md)
......
document/content/docs/self-host/upgrading/outdated/491.en.mdx 0 → 100644
---
title: V4.9.1
description: FastGPT V4.9.1 Release Notes
---
## Upgrade Guide
### 1. Back Up Your Database
### 2. Update Images
- Update FastGPT image tag: v4.9.1-fix2
- Update FastGPT Pro image tag: v4.9.1-fix2
- Sandbox image: no update required
- AIProxy image changed to: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.1.3
### 3. Run the Upgrade Script
From any terminal, send an HTTP request. Replace `{{rootkey}}` with the `rootkey` from your environment variables, and `{{host}}` with your **FastGPT domain**.
```bash
curl --location --request POST 'https://{{host}}/api/admin/initv491' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
**Script Functions**
Re-processes tokenization using the latest jieba dictionary. This takes a while — you can monitor progress in the logs.
## New Features
1. Pro edition supports single-team mode for better internal member management.
2. Knowledge base chunk reader.
3. API knowledge base supports PDF enhanced parsing.
4. Team member invitations now use an invite link model.
5. Hybrid search weight configuration support.
6. Rerank model selection and weight configuration support. The knowledge base search weight calculation has been adjusted from `vector search weight + full-text search weight + rerank weight` to `search weight + rerank weight`. This may affect search results — you can adjust the relevant weights to adapt your data.
## Improvements
1. Knowledge base data input UI improvements.
2. App-bound knowledge base data fetching moved to backend processing.
3. Added dependency package security version checks and upgraded some dependencies.
4. Model testing code improvements.
5. Optimized reasoning output parsing: as long as a model is configured to support reasoning, `<think>` tags will always be parsed, even when reasoning is disabled during a conversation.
6. Loaded the latest jieba dictionary for improved full-text search tokenization.
## Bug Fixes
1. Max response tokens tooltip showing incorrect values.
2. HTTP Node failing to parse strings containing newline characters.
3. Knowledge base question optimization not passing conversation history.
4. Missing error message translations.
5. Content extraction node: incorrect schema for array types.
6. Model channel testing not actually targeting the specified channel.
7. Adding a custom model would also save default model fields, causing incorrect default model detection.
8. Prompt-mode tool calls not null-checking the reasoning chain, causing UI rendering errors.
9. Editing app info causing avatar loss.
10. Share link titles being reset on refresh.
11. Authentication failure when calculating parentPath, causing it to be cleared.
document/content/docs/self-host/upgrading/outdated/491.mdx 0 → 100644
---
title: V4.9.1
description: FastGPT V4.9.1 更新说明
---
## 更新指南
### 1. 做好数据库备份
### 2. 更新镜像
- 更新 FastGPT 镜像 tag: v4.9.1-fix2
- 更新 FastGPT 商业版镜像 tag: v4.9.1-fix2
- Sandbox 镜像，可以不更新
- AIProxy 镜像修改为: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.1.3
### 3. 执行升级脚本
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/initv491' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
**脚本功能**
重新使用最新的 jieba 分词库进行分词处理。时间较长，可以从日志里查看进度。
## 🚀 新增内容
1. 商业版支持单团队模式，更好的管理内部成员。
2. 知识库分块阅读器。
3. API 知识库支持 PDF 增强解析。
4. 邀请团队成员，改为邀请链接模式。
5. 支持混合检索权重设置。
6. 支持重排模型选择和权重设置，同时调整了知识库搜索权重计算方式，改成 搜索权重 + 重排权重，而不是向量检索权重+全文检索权重+重排权重。会对检索结果有一定影响，可以通过调整相关权重来进行数据适配。
## ⚙️ 优化
1. 知识库数据输入框交互
2. 应用拉取绑定知识库数据交由后端处理。
3. 增加依赖包安全版本检测，并升级部分依赖包。
4. 模型测试代码。
5. 优化思考过程解析逻辑：只要配置了模型支持思考，均会解析 `<think>` 标签，不会因为对话时，关闭思考而不解析。
6. 载入最新 jieba 分词库，增强全文检索分词效果。
## 🐛 修复
1. 最大响应 tokens 提示显示错误的问题。
2. HTTP Node 中，字符串包含换行符时，会解析失败。
3. 知识库问题优化中，未传递历史记录。
4. 错误提示翻译缺失。
5. 内容提取节点，array 类型 schema 错误。
6. 模型渠道测试时，实际未指定渠道测试。
7. 新增自定义模型时，会把默认模型字段也保存，导致默认模型误判。
8. 修复 promp 模式工具调用，未判空思考链，导致 UI 错误展示。
9. 编辑应用信息导致头像丢失。
10. 分享链接标题会被刷新掉。
11. 计算 parentPath 时，存在鉴权失败清空。
document/content/docs/self-host/upgrading/outdated/4910.en.mdx 0 → 100644
---
title: V4.9.10
description: FastGPT V4.9.10 Release Notes
---
## Upgrade Guide
Important: This update rebuilds the full-text index. During the rebuild, full-text search results will be empty. On a 4c16g instance, rebuilding approximately 7 million full-text indexes takes about 25 minutes. For a seamless upgrade, you'll need to handle table synchronization yourself.
### 1. Back Up Your Data
### 2. Update Image Tags
- Update FastGPT image tag: v4.9.10-fix2
- Update FastGPT Pro image tag: v4.9.10-fix2
- mcp_server: no update required
- Sandbox: no update required
- AIProxy: no update required
## New Features
1. Support for setting the `systemEnv.hnswMaxScanTuples` parameter in PG to increase the total data volume for iterative search.
2. Knowledge base preprocessing now includes a "Chunk Conditions" parameter to control when chunking should be skipped.
3. Knowledge base preprocessing now includes a "Paragraph Priority" mode with configurable maximum paragraph depth. The previous "Length Priority" mode no longer includes embedded paragraph priority logic.
4. Workflow adjusted to single-direction input/output connections, with quick "add next node" support.
5. Lark and Yuque knowledge bases are now available in the Community Edition.
6. Latest Gemini and Claude model presets.
## Improvements
1. Increased default timeout for LLM stream calls.
2. Various confirmation dialog UI improvements.
3. Renamed the knowledge base "Table Dataset" to "Backup Import". Also added support for exporting and importing knowledge base indexes.
4. Knowledge base citation limit in workflows: if no related AI nodes exist in the workflow, the interaction mode switches to manual input only, with a limit of 10 million.
5. Mobile voice input now accurately detects whether the device is a phone rather than just a small screen.
6. Optimized context truncation algorithm to always preserve at least one Human message.
## Bug Fixes
1. Incorrect score sorting during full-text search across multiple knowledge bases.
2. Stream response potentially capturing incorrect `finish_reason` values.
3. Tool call mode not saving reasoning output.
4. Knowledge base `indexSize` parameter not taking effect.
5. Incorrect preview citations and context after 2 levels of workflow nesting.
6. Extra leading space when converting xlsx to Markdown.
7. Base64 images in Markdown files not being extracted and saved during file reading.
document/content/docs/self-host/upgrading/outdated/4910.mdx 0 → 100644
---
title: V4.9.10
description: FastGPT V4.9.10 更新说明
---
## 升级指南
重要提示：本次更新会重新构建全文索引，构建期间，全文检索结果会为空，4c16g 700 万组全文索引大致消耗 25 分钟。如需无缝升级，需自行做表同步工程。
### 1. 做好数据备份
### 2. 更新镜像 tag
- 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
## 🚀 新增内容
1. 支持 PG 设置`systemEnv.hnswMaxScanTuples`参数，提高迭代搜索的数据总量。
2. 知识库预处理参数增加 “分块条件”，可控制某些情况下不进行分块处理。
3. 知识库预处理参数增加 “段落优先” 模式，可控制最大段落深度。原“长度优先”模式，不再内嵌段落优先逻辑。
4. 工作流调整为单向接入和接出，支持快速的添加下一步节点。
5. 开放飞书和语雀知识库到社区版。
6. gemini 和 claude 最新模型预设。
## ⚙️ 优化
1. LLM stream调用，默认超时调大。
2. 部分确认交互优化。
3. 纠正原先知识库的“表格数据集”名称，改成“备份导入”。同时支持知识库索引的导出和导入。
4. 工作流知识库引用上限，如果工作流中没有相关 AI 节点，则交互模式改成纯手动输入，并且上限为 1000万。
5. 语音输入，移动端判断逻辑，准确判断是否为手机，而不是小屏。
6. 优化上下文截取算法，至少保证留下一组 Human 信息。
## 🐛 修复
1. 全文检索多知识库时排序得分排序不正确。
2. 流响应捕获 finish_reason 可能不正确。
3. 工具调用模式，未保存思考输出。
4. 知识库 indexSize 参数未生效。
5. 工作流嵌套 2 层后，获取预览引用、上下文不正确。
6. xlsx 转成 Markdown 时候，前面会多出一个空格。
7. 读取 Markdown 文件时，Base64 图片未进行额外抓换保存。
document/content/docs/self-host/upgrading/outdated/4911.en.mdx 0 → 100644
---
title: V4.9.11 (Includes Upgrade Script)
description: FastGPT V4.9.11 Release Notes
---
## Upgrade Guide
### 1. Update Images:
- Update FastGPT image tag: v4.9.11
- Update FastGPT Pro image tag: v4.9.11
- mcp_server: no update required
- Update Sandbox image tag: v4.9.11
- AIProxy: no update required
### 2. Run the Upgrade Script
This script only needs to be run by Pro edition users.
From any terminal, send an HTTP request. Replace `{{rootkey}}` with the `rootkey` from your environment variables, and `{{host}}` with your **FastGPT domain**.
```bash
curl --location --request POST 'https://{{host}}/api/admin/initv4911' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
**Script Functions**
1. Migrates third-party knowledge base API configurations.
## New Features
1. Pro edition supports image knowledge bases.
2. Added node search functionality in the workflow editor.
3. Sub-workflow version control in workflows now supports a "Keep Latest Version" option — no manual updates needed.
4. Additional audit operation logs.
5. Knowledge base now has an async document parsing queue — documents can be imported without waiting for parsing to complete.
6. Third-party knowledge base development documentation. [View here](/docs/introduction/guide/knowledge_base/third_dataset/)
## Improvements
1. Raw text cache now uses GridFS storage for higher capacity.
2. Added knowledge base template import option.
## Bug Fixes
1. Admin-declared global system tools in workflows unable to be version-managed.
2. Context errors when an interactive node precedes a tool call node.
3. Backup import failing to chunk content under 1,000 characters.
4. Custom PDF parsing unable to save Base64 images.
5. Non-stream requests not performing CITE marker replacement.
6. Hidden security vulnerability in the Python sandbox.
7. Missing confirm button when importing plugins via curl.
document/content/docs/self-host/upgrading/outdated/4911.mdx 0 → 100644
---
title: V4.9.11(包含升级脚本)
description: FastGPT V4.9.11 更新说明
---
## 更新指南
### 1. 更新镜像：
- 更新 FastGPT 镜像 tag: v4.9.11
- 更新 FastGPT 商业版镜像 tag: v4.9.11
- mcp_server 无需更新
- 更新 Sandbox 镜像 tag: v4.9.11
- AIProxy 无需更新
### 2. 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/initv4911' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
**脚本功能**
1. 移动第三方知识库 API 配置。
## 🚀 新增内容
1. 商业版支持图片知识库。
2. 工作流中增加节点搜索功能。
3. 工作流中，子流程版本控制，可选择“保持最新版本”，无需手动更新。
4. 增加更多审计操作日志。
5. 知识库增加文档解析异步队列，导入文档时，无需等待文档解析完毕才进行导入。
6. 第三方知识库开发文档, [点击查看](/docs/introduction/guide/knowledge_base/third_dataset/)
## ⚙️ 优化
1. 原文缓存改用 gridfs 存储，提高上限。
2. 增加知识库模板导入选项。
## 🐛 修复
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。
4. 自定义 PDF 解析，无法保存 base64 图片。
5. 非流请求，未进行 CITE 标记替换。
6. Python 沙盒存在隐藏风险。
7. curl 导入插件缺失确认按键
document/content/docs/self-host/upgrading/outdated/4912.en.mdx 0 → 100644
---
title: V4.9.12
description: FastGPT V4.9.12 Release Notes
---
## Upgrade Guide
### 1. Update Environment Variables
Add the following environment variable to both the `fastgpt` and `fastgpt-pro` image configurations: `AES256_SECRET_KEY=` — used for secret key encryption.
### 2. Update Images:
- Update FastGPT image tag: v4.9.12
- Update FastGPT Pro image tag: v4.9.12
- mcp_server: no update required
- Sandbox: no update required
- Update AIProxy image tag: v0.2.2
## New Features
1. Enhanced AI Proxy monitoring with chart and table views for model call and performance metrics.
2. HTTP nodes and MCP now support separate "Auth Configuration" — plaintext credentials are never sent back to the client, ensuring data security.
3. Question classification and content extraction now automatically include the previous round's results in the prompt for additional guidance.
4. Conditional node now supports variable references.
5. Pro edition supports LLM-based automatic segment detection during knowledge base chunking.
6. Admin dashboard with data analytics.
7. Doubao 1.6 series models and updated Qwen model configurations.
## Improvements
1. Password validation now accepts more special characters.
2. Backend now fully computes knowledge base chunk parameters to prevent default values from being incorrectly applied in auto mode.
3. Text chunking moved to a worker thread to avoid blocking.
4. More subscription plan usage information displayed.
5. Input box styling improvements, with updated voice input UI for both desktop and mobile.
6. MCP tool calls now use raw schema for invocation to ensure completeness.
7. Deleting knowledge base files no longer fails if the file doesn't exist.
8. Upgraded MCP SDK with compatibility for the latest HTTP Streamable protocol.
9. Yuque document library now recursively fetches data from document-type directories.
## Bug Fixes
1. Custom QA extraction prompts being overwritten.
2. Template import failing when empty indexes exist in the data.
3. Potential XSS vulnerability on the login page.
4. Voice input in the text box causing the file list to be lost.
5. Image TTL field not being cleared in knowledge base documents, causing images to expire.
6. MCP tool storage not escaping integer type data.
document/content/docs/self-host/upgrading/outdated/4912.mdx 0 → 100644
---
title: V4.9.12
description: FastGPT V4.9.12 更新说明
---
## 更新指南
### 1. 更新环境变量
在 `fastgpt`和`fastgpt-pro`镜像环境变量中加入: `AES256_SECRET_KEY=` 变量，用于密钥加密。
### 2. 更新镜像：
- 更新 FastGPT 镜像 tag: v4.9.12
- 更新 FastGPT 商业版镜像 tag: v4.9.12
- mcp_server 无需更新
- Sandbox 无需更新
- 更新 AIProxy 镜像 tag: v0.2.2
## 🚀 新增内容
1. AI proxy 监控完善，支持以图表/表格形式查看模型调用和性能情况。
2. HTTP 节点和 MCP 支持单独“鉴权配置”，鉴权配置明文不会二次返回客户端，以保障数据安全。
3. 问题分类和内容提取，提示词中自动加入上一轮结果进行额外引导。
4. 判断器支持变量引用。
5. 商业版支持知识库分块时，LLM 进行自动分段识别。
6. Admin 管理员数据看板。
7. 豆包 1.6 系列模型，更新 qwen 模型配置。
## ⚙️ 优化
1. 密码校验时，增加更多的特殊字符
2. 后端全量计算知识库 chunk 参数，避免自动模式下部分参数未正确使用默认值。
3. 将文本分块移至 worker 线程，避免阻塞。
4. 展示更多套餐用量信息。
5. 优化输入框样式，桌面和移动端的语音输入样式更新。
6. MCP 工具调用，使用 Raw schema 进行工具调用，保障完整性。
7. 删除知识库文件时，如果文件不存在，不会阻断删除。
8. 升级 MCP SDK，兼容最新的 HTTPStreamable。
9. 语雀文档库，递归获取文档类型目录下的数据。
## 🐛 修复
1. 自定义问答提取提示词被覆盖。
2. 模板导入时，存在空 indexes 时，导致数据插入失败。
3. 登录页可能存在的 XSS 攻击。
4. 输入框语音输入时候会丢失文件列表的问题。
5. 知识库文档中图片 TTL 字段未清除，导致图片过期。
6. MCP 工具存储时，未转义 int 类型数据。
document/content/docs/self-host/upgrading/outdated/4913.en.mdx 0 → 100644
---
title: V4.9.13
description: FastGPT V4.9.13 Release Notes
---
## Upgrade Guide
### 1. Update Images:
- Update FastGPT image tag: v4.9.13
- Update FastGPT Pro image tag: v4.9.13
- mcp_server: no update required
- Sandbox: no update required
- AIProxy: no update required
## New Features
1. Subscription plan caching to reduce MongoDB query frequency.
## Improvements
1. All NodeId random value generation adjusted to avoid starting with a digit.
2. Knowledge base collection search now supports nested search.
## Bug Fixes
1. Chat log date range selection issues.
2. System prompt potentially being duplicated when passed via API calls.
3. AI chat/tool calls reading files from history even when no file link was selected.
4. Manually updating knowledge base indexes incorrectly deleting old indexes, causing manual indexes to become ineffective.
document/content/docs/self-host/upgrading/outdated/4913.mdx 0 → 100644
---
title: V4.9.13
description: FastGPT V4.9.13 更新说明
---
## 更新指南
### 1. 更新镜像：
- 更新 FastGPT 镜像 tag: v4.9.13
- 更新 FastGPT 商业版镜像 tag: v4.9.13
- mcp_server 无需更新
- Sandbox 无需更新
- AIProxy 无需更新
## 🚀 新增内容
1. 套餐缓存，减少 MongoDB 查询次数。
## ⚙️ 优化
1. 所有 NodeId 调整随机值生成，避免首字母数字开头。
2. 知识库集合搜索，支持嵌套搜索。
## 🐛 修复
1. 对话日志，日期范围选择问题。
2. API 调用时，传入的 system 提示词可能会重复。
3. AI 对话/工具调用，未选择文件链接时，也会从历史记录读取文件。
4. 手动更新知识库索引时，错误的删除旧索引，导致手动索引无效。
document/content/docs/self-host/upgrading/outdated/4914.en.mdx 0 → 100644
---
title: V4.9.14
description: FastGPT V4.9.14 Release Notes
---
## Upgrade Guide
### 1. Update Images:
- Update FastGPT image tag: v4.9.14
- Update FastGPT Pro image tag: v4.9.14
- mcp_server: no update required
- Sandbox: no update required
- AIProxy: no update required
## New Features
1. Knowledge base import now supports automatically adding the filename to the system index.
2. Admin-side audit logs.
## Improvements
1. Unified knowledge base training queue code logic.
2. Input box UX improvements.
3. Image knowledge base now automatically removes line breaks from descriptions to prevent model output line breaks from breaking image display.
4. Image indexing now generates separate image content descriptions, and attaches them to search results after retrieval — enabling LLMs to understand image content.
5. Auto-completion for MCP Schema entries missing the `properties` field to prevent errors with certain models.
6. Error handling for potential JSON import template failures.
7. Dangerous characters filtered during CSV export.
8. Added security request headers.
9. Changing password now invalidates all other active sessions.
10. Citation display optimization: detects preceding URLs and automatically adds spacing.
## Bug Fixes
1. Knowledge base data input incorrectly detecting QA mode.
2. Knowledge base tag condition conflicts.
3. Chat log like/dislike statistics.
document/content/docs/self-host/upgrading/outdated/4914.mdx 0 → 100644
---
title: V4.9.14
description: FastGPT V4.9.14 更新说明
---
## 更新指南
### 1. 更新镜像：
- 更新 FastGPT 镜像 tag: v4.9.14
- 更新 FastGPT 商业版镜像 tag: v4.9.14
- mcp_server 无需更新
- Sandbox 无需更新
- AIProxy 无需更新
## 🚀 新增内容
1. 知识库导入，支持配置：自动将文件名加入系统索引中。
2. Admin 端审计日志。
## ⚙️ 优化
1. 统一知识库训练队列代码逻辑。
2. 输入框 UX。
3. 图片知识库自动去除介绍中的换行，避免模型输出换行导致无法显示图片。
4. 图片索引过程会单独描述图片内容，并在检索后会将图片描述赋予检索结果，使语言模型也可以对图片进行理解。
5. 对于 MCP Schema 中，缺少`properties`属性的值，进行自动补全，避免部分模型报错。
6. 对 JSON 导入模板可能的报错进行捕获。
7. 过滤 CSV 导出时可能存在的危险字符串。
8. 添加安全请求头。
9. 修改密码，强制其他登录端失效。
10. Cite 引用展示优化，识别前置的 url 并自动加空格。
## 🐛 修复
1. 知识库数据输入，识别 QA 模式错误。
2. 知识库标签条件冲突。
3. 对话日志点赞点踩统计。
document/content/docs/self-host/upgrading/outdated/492.en.mdx 0 → 100644
---
title: V4.9.2
description: FastGPT V4.9.2 Release Notes
---
## Upgrade Guide
You can skip directly to v4.9.3 — v4.9.2 has a workflow data type conversion bug.
### 1. Back Up Your Database
### 2. SSO Migration
Pro edition users using SSO or member sync with DingTalk or WeCom need to migrate their existing SSO configuration:
Refer to [SSO & External Member Sync](/docs/introduction/guide/admin/sso) for deploying and configuring the `sso-service`.
1. Before upgrading images, copy and back up the existing configuration from the Pro admin panel (e.g., for WeCom, copy the AppId, Secret, etc.).
2. Follow the documentation above to deploy the SSO service and configure the relevant environment variables.
3. If you were previously using WeCom org structure sync, after upgrading, switch the team mode to "Sync Mode" in the Pro admin panel.
### 3. Configuration Parameter Changes
Rename the `systemEnv.pgHNSWEfSearch` parameter in your `config.json` file to `hnswEfSearch`.
Pro edition users can make this change in the admin panel under `System Configuration - Basic Settings` after upgrading.
### 4. Update Images
- Update FastGPT image tag: v4.9.2
- Update FastGPT Pro image tag: v4.9.2
- Sandbox image: no update required
- AIProxy image changed to: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.1.4
## Important Updates
- Knowledge base data import API changes: added optional parameters `chunkSettingMode`, `chunkSplitMode`, and `indexSize`. See the [Knowledge Base Data Import API](/docs/openapi/dataset) documentation for details.
## New Features
1. Knowledge base chunking optimization: supports separate configuration for chunk size and index size, allowing extra-large chunks that trade higher input tokens for complete chunks.
2. Knowledge base chunking now includes custom separator presets and supports custom newline-based splitting.
3. External variables renamed to Custom Variables. Now supports debugging during testing, and the variable is hidden in share links.
4. Collection sync now supports syncing title changes.
5. Team member management overhaul: extracted mainstream IM SSO (WeCom, Lark, DingTalk) and added support for connecting to FastGPT via custom SSO. Also improved member sync with external systems.
6. Support for `oceanbase` vector database. Set the `OCEANBASE_URL` environment variable to enable.
7. PDF parsing example based on mistral-ocr.
8. PDF parsing example based on miner-u.
## Improvements
1. Chat log export now includes member names.
2. Invite link UI improvements.
3. When SSL certificate is unavailable and copy fails, a dialog is shown for manual copying.
4. FastGPT now properly displays AI Proxy channel names even when channels are not built in.
5. Upgraded Next.js to version 14.2.25.
6. Workflow node array-string type now auto-adapts to string input.
7. Workflow node array type now automatically JSON-parses string input.
8. AI Proxy log optimization: removed retry failure logs, keeping only the final error log.
9. Personal info and notification display improvements.
10. Model testing loading animation improvements.
11. Minor chunking algorithm adjustments:
- Stronger continuity between cross-processing symbols.
- Code blocks now use the LLM model context as chunk size to better preserve code block integrity.
- Tables now use the LLM model context as chunk size to better preserve table integrity.
## Bug Fixes
1. Lark and Yuque knowledge bases unable to sync.
2. Channel testing using the custom request URL instead of the channel request URL when a custom URL was configured.
3. Speech recognition model testing unable to test disabled models.
4. Admin-configured system plugins failing authentication when the plugin contains other system apps.
5. Removing TTS custom request URL requiring the requestAuth field to be filled.
document/content/docs/self-host/upgrading/outdated/492.mdx 0 → 100644
---
title: V4.9.2
description: FastGPT V4.9.2 更新说明
---
## 更新指南
可直接升级v4.9.3，v4.9.2存在一个工作流数据类型转化错误。
### 1. 做好数据库备份
### 2. SSO 迁移
使用了 SSO 或成员同步的商业版用户，并且是对接`钉钉`、`企微`的，需要迁移已有的 SSO 相关配置:
参考：[SSO & 外部成员同步](/docs/introduction/guide/admin/sso)中的配置进行`sso-service`的部署和配置。
1. 先将原商业版后台中的相关配置项复制备份出来（以企微为例，将 AppId, Secret 等复制出来）再进行镜像升级。
2. 参考上述文档，部署 SSO 服务，配置相关的环境变量
3. 如果原先使用企微组织架构同步的用户，升级完镜像后，需要在商业版后台切换团队模式为“同步模式”
### 3. 配置参数变更
修改`config.json`文件中`systemEnv.pgHNSWEfSearch`参数名，改成`hnswEfSearch`。
商业版用户升级镜像后，直接在后台`系统配置-基础配置`中进行变更。
### 4. 更新镜像
- 更新 FastGPT 镜像 tag: v4.9.2
- 更新 FastGPT 商业版镜像 tag: v4.9.2
- Sandbox 镜像，可以不更新
- AIProxy 镜像修改为: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.1.4
## 重要更新
- 知识库导入数据 API 变更，增加`chunkSettingMode`,`chunkSplitMode`,`indexSize`可选参数，具体可参考 [知识库导入数据 API](/docs/openapi/dataset) 文档。
## 🚀 新增内容
1. 知识库分块优化：支持单独配置分块大小和索引大小，允许进行超大分块，以更大的输入 Tokens 换取完整分块。
2. 知识库分块增加自定义分隔符预设值，同时支持自定义换行符分割。
3. 外部变量改名：自定义变量。 并且支持在测试时调试，在分享链接中，该变量直接隐藏。
4. 集合同步时，支持同步修改标题。
5. 团队成员管理重构，抽离主流 IM SSO（企微、飞书、钉钉），并支持通过自定义 SSO 接入 FastGPT。同时完善与外部系统的成员同步。
6. 支持 `oceanbase` 向量数据库。填写环境变量`OCEANBASE_URL`即可。
7. 基于 mistral-ocr 的 PDF 解析示例。
8. 基于 miner-u 的 PDF 解析示例。
## ⚙️ 优化
1. 导出对话日志时，支持导出成员名。
2. 邀请链接交互。
3. 无 SSL 证书时复制失败，会提示弹窗用于手动复制。
4. FastGPT 未内置 ai proxy 渠道时，也能正常展示其名称。
5. 升级 nextjs 版本至 14.2.25。
6. 工作流节点数组字符串类型，自动适配 string 输入。
7. 工作流节点数组类型，自动进行 JSON parse 解析 string 输入。
8. AI proxy 日志优化，去除重试失败的日志，仅保留最后一份错误日志。
9. 个人信息和通知展示优化。
10. 模型测试 loading 动画优化。
11. 分块算法小调整：
- 跨处理符号之间连续性更强。
- 代码块分割时，用 LLM 模型上下文作为分块大小，尽可能保证代码块完整性。
- 表格分割时，用 LLM 模型上下文作为分块大小，尽可能保证表格完整性。
## 🐛 修复
1. 飞书和语雀知识库无法同步。
2. 渠道测试时，如果配置了模型自定义请求地址，会走自定义请求地址，而不是渠道请求地址。
3. 语音识别模型测试未启用的模型时，无法正常测试。
4. 管理员配置系统插件时，如果插件包含其他系统应用，无法正常鉴权。
5. 移除 TTS 自定义请求地址时，必须需要填 requestAuth 字段。
document/content/docs/self-host/upgrading/outdated/494.en.mdx 0 → 100644
---
title: V4.9.4
description: FastGPT V4.9.4 Release Notes
---
## Upgrade Guide
### 1. Back Up Your Data
### 2. Install Redis
* For Docker deployments, refer to the latest `docker-compose.yml` file to add Redis configuration. Add a Redis container and configure the `REDIS_URL` environment variable for both `fastgpt` and `fastgpt-pro`.
* For Sealos deployments, create a new `redis` database in the Database section, copy the `internal connection` URL as the Redis connection string, then configure the `REDIS_URL` environment variable for both `fastgpt` and `fastgpt-pro`.
| | | |
| --- | --- | --- |
| ![](/imgs/sealos-redis1.png) | ![](/imgs/sealos-redis2.png) | ![](/imgs/sealos-redis3.png) |
### 3. Update Image Tags
- Update FastGPT image tag: v4.9.4
- Update FastGPT Pro image tag: v4.9.4
- Sandbox: no update required
- AIProxy: no update required
### 4. Run the Upgrade Script
This script only needs to be run by Pro edition users.
From any terminal, send an HTTP request. Replace `{{rootkey}}` with the `rootkey` from your environment variables, and `{{host}}` with your **FastGPT domain**:
```bash
curl --location --request POST 'https://{{host}}/api/admin/initv494' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
**Script Functions**
1. Updates the site sync scheduler.
## New Features
1. Collection data training status display.
2. SMTP email sending plugin.
3. BullMQ message queue.
4. Partial data caching via Redis.
5. Site sync now supports configuring training parameters and incremental sync.
6. AI chat/tool calls now return the model's `finish_reason` field for easier tracking of output interruption causes.
7. Mobile voice input UI adjustments.
## Improvements
1. Admin template rendering adjustments.
2. Chat file expiration time now configurable via environment variable.
3. MongoDB log database can now be deployed independently.
## Bug Fixes
1. Unable to click into subdirectories when searching apps/knowledge bases.
2. Retraining parameters not properly initialized.
3. Inconsistent requests in package/service across multiple apps.
document/content/docs/self-host/upgrading/outdated/494.mdx 0 → 100644
---
title: V4.9.4
description: FastGPT V4.9.4 更新说明
---
## 升级指南
### 1. 做好数据备份
### 2. 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) |
### 3. 更新镜像 tag
- 更新 FastGPT 镜像 tag: v4.9.4
- 更新 FastGPT 商业版镜像 tag: v4.9.4
- Sandbox 无需更新
- AIProxy 无需更新
### 4. 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. 利用 redis 进行部分数据缓存。
5. 站点同步支持配置训练参数和增量同步。
6. AI 对话/工具调用，增加返回模型 finish_reason 字段，便于追踪模型输出中断原因。
7. 移动端语音输入交互调整
## ⚙️ 优化
1. Admin 模板渲染调整。
2. 支持环境变量配置对话文件过期时间。
3. MongoDB log 库可独立部署。
## 🐛 修复
1. 搜索应用/知识库时，无法点击目录进入下一层。
2. 重新训练时，参数未成功初始化。
3. package/service 部分请求在多 app 中不一致。
document/content/docs/self-host/upgrading/outdated/495.en.mdx 0 → 100644
---
title: V4.9.5
description: FastGPT V4.9.5 Release Notes
---
## Upgrade Guide
### 1. Back Up Your Data
### 2. Update Image Tags
- Update FastGPT image tag: v4.9.5
- Update FastGPT Pro image tag: v4.9.5
- Sandbox: no update required
- AIProxy: no update required
## New Features
1. Granular team member permissions: separately control whether members can create root-level apps/knowledge bases and API keys.
2. Interactive nodes now work inside nested workflows.
3. Team member operation audit logs.
4. User input node now supports checkboxes.
## Improvements
1. Traditional Chinese translation updates.
2. ARM image builds.
## Bug Fixes
1. Incorrect password validation rules.
2. Share links unable to hide knowledge base search results.
3. Regex compatibility issues on older iOS versions.
4. QA extraction queue counter not resetting after errors, causing the queue to stop working.
5. Debug mode interactive nodes potentially causing infinite loops on next step.
document/content/docs/self-host/upgrading/outdated/495.mdx 0 → 100644
---
title: V4.9.5
description: FastGPT V4.9.5 更新说明
---
## 升级指南
### 1. 做好数据备份
### 2. 更新镜像 tag
- 更新 FastGPT 镜像 tag: v4.9.5
- 更新 FastGPT 商业版镜像 tag: v4.9.5
- Sandbox 无需更新
- AIProxy 无需更新
## 🚀 新增内容
1. 团队成员权限细分，可分别控制是否可创建在根目录应用/知识库以及 API Key
2. 支持交互节点在嵌套工作流中使用。
3. 团队成员操作日志。
4. 用户输入节点支持多选框。
## ⚙️ 优化
1. 繁体中文翻译。
2. Arm 镜像打包
## 🐛 修复
1. password 检测规则错误。
2. 分享链接无法隐藏知识库检索结果。
3. IOS 低版本正则兼容问题。
4. 修复问答提取队列错误后，计数器未清零问题，导致问答提取队列失效。
5. Debug 模式交互节点下一步可能造成死循环。
document/content/docs/self-host/upgrading/outdated/496.en.mdx 0 → 100644
---
title: V4.9.6
description: FastGPT V4.9.6 Release Notes
---
## New Features
1. Apps can now be called externally via MCP.
2. Support for creating tools using the MCP SSE protocol.
3. Batch execution node now supports interactive nodes, enabling human participation in each loop iteration.
4. Added workspace secondary menu with merged toolbox.
5. Added system configurations for grok3, GPT4.1, o-series, and Gemini 2.5 models.
## Improvements
1. Enhanced workflow data type conversion robustness and compatibility.
2. Python sandbox code now supports large data inputs.
3. Breadcrumb component now supports configuring whether the last step is clickable.
4. Knowledge base tool call results now automatically prepend image domain names.
5. GitHub Action runner upgraded to Ubuntu 24.
6. Removed extra leading/trailing newlines when replying via Lark, WeChat Official Account, and other third-party channels.
7. Adjusted chunking strategy: large tables are now split into independent chunks instead of being merged into oversized blocks.
8. Iframe embed component now includes built-in microphone permission declaration.
## Bug Fixes
1. Sub-workflows with interactive nodes not fully restoring all sub-workflow data.
2. Completion v1 API not accepting the `interactive` parameter, causing API call failures.
3. Consecutive tool calls causing abnormal context truncation.
## Upgrade Guide
### 1. Back Up Your Data
### 2. Deploy the MCP Server Service
#### Docker Deployment
Add the `fastgpt-mcp-server` service to your `docker-compose.yml` file:
```yml
fastgpt-mcp-server:
container_name: fastgpt-mcp-server
image: ghcr.io/labring/fastgpt-mcp_server:v4.9.6
ports:
- 3005:3000
networks:
- fastgpt
restart: always
environment:
- FASTGPT_ENDPOINT=http://fastgpt:3000
```
#### Sealos Deployment
In `App Management`, add a new `fastgpt-mcp-server` app with the image `ghcr.io/labring/fastgpt-mcp_server:v4.9.6` and set the environment variable `FASTGPT_ENDPOINT=<your FastGPT access URL>`.
### 3. Update FastGPT Container Environment Variables
#### Community Edition
Add the following to your `config.json` configuration file: `"feconfigs.mcpServerProxyEndpoint": "<fastgpt-mcp-server access URL>"` (no trailing slash). For example:
```json
{
"feConfigs": {
"lafEnv": "https://laf.dev",
"mcpServerProxyEndpoint": "https://mcp.fastgpt.cn"
}
}
```
#### Pro Edition
In the Admin panel, go to `System Configuration - Basic Settings - System Parameters` and set the `MCP Proxy Server URL` to the public access URL of your `fastgpt-mcp-server`.
### 4. Update Image Tags
- Update FastGPT image tag: v4.9.6
- Update FastGPT Pro image tag: v4.9.6
- Update Sandbox image tag: v4.9.6
- Add FastGPT MCP Server image tag: v4.9.6
- AIProxy: no update required
document/content/docs/self-host/upgrading/outdated/496.mdx 0 → 100644
---
title: V4.9.6
description: FastGPT V4.9.6 更新说明
---
## 🚀 新增内容
1. 以 MCP 方式对外提供应用调用。
2. 支持以 MCP SSE 协议创建工具。
3. 批量执行节点支持交互节点，可实现每一轮循环都人工参与。
4. 增加工作台二级菜单，合并工具箱。
5. 增加 grok3、GPT4.1、o系列、Gemini2.5 模型系统配置。
## ⚙️ 优化
1. 工作流数据类型转化鲁棒性和兼容性增强。
2. Python sandbox 代码，支持大数据输入。
3. 路径组件支持配置最后一步是否可点击。
4. 知识库工具调用结果，自动补充图片域名。
5. Github action runner 升级成 unbuntu24
6. 去除飞书、公众号等三方渠道，回复时，可能前后多一个换行的问题。
7. 调整分块策略，大表格时，不进行超大块合并，而是独立拆块。
8. Iframe 嵌套组件，内置允许麦克风声明。
## 🐛 修复
1. 修复子工作流包含交互节点时，未成功恢复子工作流所有数据。
2. completion v1 接口，未接受 interactive 参数，导致 API 调用失败。
3. 连续工具调用，上下文截断异常
## 升级指南
### 1. 做好数据备份
### 2. 部署 MCP server 服务
#### Docker 部署
在`docker-compose.yml`文件中，加入`fastgpt-mcp-server`服务:
```yml
fastgpt-mcp-server:
container_name: fastgpt-mcp-server
image: ghcr.io/labring/fastgpt-mcp_server:v4.9.6
ports:
- 3005:3000
networks:
- fastgpt
restart: always
environment:
- FASTGPT_ENDPOINT=http://fastgpt:3000
```
#### Sealos 部署
直接在`应用管理`中，增加一个`fastgpt-mcp-server`应用，镜像为`ghcr.io/labring/fastgpt-mcp_server:v4.9.6`，并设置环境变量`FASTGPT_ENDPOINT=fastgpt 的访问地址`。
### 3. 修改 FastGPT 容器环境变量
#### 社区版
修改`config.json`配置文件，增加: `"feconfigs.mcpServerProxyEndpoint": "fastgpt-mcp-server 的访问地址"`， 末尾不要携带/，例如:
```json
{
"feConfigs": {
"lafEnv": "https://laf.dev",
"mcpServerProxyEndpoint": "https://mcp.fastgpt.cn"
}
}
```
#### 商业版
在 Admin 后台，`系统配置-基础配置-系统参数`中的`MCP 转发服务地址`中，设置`fastgpt-mcp-server`的公网访问地址。
### 4. 更新镜像 tag
- 更新 FastGPT 镜像 tag: v4.9.6
- 更新 FastGPT 商业版镜像 tag: v4.9.6
- 更新 Sandbox 镜像 tag: v4.9.6
- 增加 FastGPT mcp server 镜像 tag: v4.9.6
- AIProxy 无需更新
document/content/docs/self-host/upgrading/outdated/497.en.mdx 0 → 100644
---
title: V4.9.7
description: FastGPT V4.9.7 Release Notes
---
## Upgrade Guide
### 1. Back Up Your Data
### 2. Update Image Tags
- Update FastGPT image tag: v4.9.7-fix2
- Update FastGPT Pro image tag: v4.9.7
- mcp_server: no update required
- Sandbox: no update required
- Update AIProxy image tag: v0.1.8
## New Features
1. Knowledge base answers now include citations at the end of each referenced paragraph.
2. MCP tools support the HTTP Streamable protocol.
3. MCP Server supports editing tool names to accommodate clients that don't support Chinese characters.
4. Right-click in the workflow editor to auto-align nodes.
5. Support for custom `config.json` path in production environments.
6. API calls support passing a special chatId (`NO_RECORD_HISTORIES`) to prevent the system from storing conversation history.
7. Rerank model usage-based billing support.
8. Subscription plan redemption codes.
9. Alipay payment support.
10. Short link analytics tracking.
11. Added Jina AI model system configuration.
## Improvements
1. Doc2x document parsing: added error message capture and increased timeout duration.
2. Adjusted PG vector query to force vector index usage.
3. Conversation time statistics now accurately return the overall workflow execution time.
4. Audio parsing duration now retrieved from ai_proxy.
5. AI model token counts now prioritize the API usage values for accuracy. If unavailable, falls back to GPT-3.5 estimation.
6. Optimized the chat log list API to handle scenarios with large numbers of messages in a single conversation.
## Bug Fixes
1. File upload chunk size limit to prevent exceeding MongoDB limits.
2. Usage dashboard unable to retrieve statistics for specific members.
3. Dashboard API returning incorrect statistics due to timezone handling issues.
4. LLM model test API unable to test disabled models. Also fixed the issue where model testing would strip custom request URLs.
5. Copy app permission issues.
6. Chat record export now limits individual conversations to 1,000 message pairs to prevent export failures.
7. Workflow variables followed by another workflow variable not triggering rendering.
8. Debugging the knowledge base search module showing "no permission" errors.
9. Text content extraction node default value assignment logic.
10. Share links forcibly returning citation content from nested apps.
11. Knowledge base collection metadata filtering: same-named tags across different knowledge bases returning no results when using `$and` filters.
12. App list permission configuration potentially causing index refresh issues.
document/content/docs/self-host/upgrading/outdated/497.mdx 0 → 100644
---
title: V4.9.7
description: FastGPT V4.9.7 更新说明
---
## 升级指南
### 1. 做好数据备份
### 2. 更新镜像 tag
- 更新 FastGPT 镜像 tag: v4.9.7-fix2
- 更新 FastGPT 商业版镜像 tag: v4.9.7
- mcp_server 无需更新
- Sandbox 无需更新
- 更新 AIProxy 镜像 tag: v0.1.8
## 🚀 新增内容
1. 知识库回答时，回答段落末尾增加引用。
2. MCP 工具支持 HTTP Streamable 协议。
3. MCP server 支持编辑工具名，适配部分客户端不支持中文名问题。
4. 工作流右键可自动对齐节点。
5. 支持生产环境自定义`config.json`路径。
6. API 调用，支持传递一个特殊 chatId(`NO_RECORD_HISTORIES`)，使得系统不会进行历史记录存储。
7. 支持 Rerank 模型按量计费。
8. 套餐兑换码功能。
9. 支付宝支付。
10. 短链数据埋点。
11. 新增 Jina AI 模型系统配置。
## ⚙️ 优化
1. Doc2x 文档解析，增加报错信息捕获，增加超时时长。
2. 调整 PG vector 查询语句，强制使用向量索引。
3. 对话时间统计，准确返回工作流整体运行时间。
4. 从 ai_proxy 获取音频解析时长。
5. AI 模型 Token 值均优先采用 API usage，确保 tokens 值准确，若为空，则再采用 GPT3.5 的估算方式。
6. 优化对话日志 list 接口，适配单个对话框，大量对话的场景。
## 🐛 修复
1. 文件上传分块大小限制，避免超出 MongoDB 限制。
2. 使用记录仪表盘，无法获取指定成员的使用统计。
3. 仪表盘接口，因未考虑时区问题，统计异常。
4. LLM 模型测试接口，无法测试未启用的 LLM。同时修复，模型测试接口会把模型自定义请求地址去除问题。
5. Copy app 权限问题。
6. 导出对话记录，限制单条对话记录消息上限 1000 组，避免导出失败。
7. 工作流变量下一段文本仍是工作流变量，不触发渲染。
8. 调试知识库检索模块，提示无权操作知识库。
9. 文本内容提取节点，默认值赋值逻辑。
10. 分享链接中，会强制返回嵌套应用中的引用内容。
11. 知识库集合元数据过滤时，不同知识库的同名标签使用 $and 筛选无法获取结果。
12. 修复应用列表，权限配置可能出现 index 刷新问题。
document/content/docs/self-host/upgrading/outdated/498.en.mdx 0 → 100644
---
title: V4.9.8
description: FastGPT V4.9.8 Release Notes
---
## Upgrade Guide
### 1. Back Up Your Data
### 2. Update Image Tags
- Update FastGPT image tag: v4.9.8
- Update FastGPT Pro image tag: v4.9.8
- mcp_server: no update required
- Sandbox: no update required
- AIProxy: no update required
## New Features
1. Support for parallel tool call execution.
2. All built-in tasks switched from non-stream mode to stream mode to avoid compatibility issues with models that don't support non-stream mode. To override, you can force `stream=false` in the model's `Extra Body` parameters.
3. Qwen3 model presets.
4. Yuque knowledge base now supports setting a root directory.
5. Configurable password expiration — users will be forced to change their password on next login after expiration.
6. Password login now includes preLogin temporary key verification.
7. Admin panel now supports configuring visibility of publishing channels and third-party knowledge bases.
## Improvements
1. Chat log list optimization to prevent memory overflow with large datasets.
2. Token calculation worker is now preloaded to prevent thread blocking from concurrent creation during main tasks.
3. Workflow node version control UI improvements.
4. Web fetch and html2md optimization: now supports video and audio tag conversion.
## Bug Fixes
1. App list / knowledge base list: incorrect permission display for delete row actions.
2. Opening knowledge base search parameters automatically enabling the rerank option.
3. Incorrect API request format for LLM json_schema mode.
4. Expired image indexes not properly cleared during retraining, causing image loss.
5. Retraining permission issues.
6. Documentation link URLs.
7. Claude tool calls failing due to empty index values.
8. Nested workflows with interactive nodes inside tool calls causing abnormal flow behavior.
document/content/docs/self-host/upgrading/outdated/498.mdx 0 → 100644
---
title: V4.9.8
description: FastGPT V4.9.8 更新说明
---
## 升级指南
### 1. 做好数据备份
### 2. 更新镜像 tag
- 更新 FastGPT 镜像 tag: v4.9.8
- 更新 FastGPT 商业版镜像 tag: v4.9.8
- mcp_server 无需更新
- Sandbox 无需更新
- AIProxy 无需更新
## 🚀 新增内容
1. 支持 Toolcalls 并行执行。
2. 将所有内置任务，从非 stream 模式调整成 stream 模式，避免部分模型不支持非 stream 模式。如需覆盖，则可以在模型`额外 Body`参数中，强制指定`stream=false`。
3. qwen3 模型预设
4. 语雀知识库支持设置根目录。
5. 可配置密码过期时间，过期后下次登录会强制要求修改密码。
6. 密码登录增加 preLogin 临时密钥校验。
7. 支持 Admin 后台配置发布渠道和第三方知识库的显示隐藏。
## ⚙️ 优化
1. Chat log list 优化，避免大数据时超出内存限制。
2. 预加载 token 计算 worker，避免主任务中并发创建导致线程阻塞。
3. 工作流节点版本控制交互优化。
4. 网络获取以及 html2md 优化，支持视频和音频标签的转换。
## 🐛 修复
1. 应用列表/知识库列表，删除行权限展示问题。
2. 打开知识库搜索参数后，重排选项自动被打开。
3. LLM json_schema 模式 API 请求格式错误。
4. 重新训练时，图片过期索引未成功清除，导致图片会丢失。
5. 重新训练权限问题。
6. 文档链接地址。
7. Claude 工具调用，由于 index 为空，导致工具调用失败。
8. 嵌套工作流，工具调用下包含交互节点时，流程异常。
document/content/docs/self-host/upgrading/outdated/499.en.mdx 0 → 100644
---
title: V4.9.9
description: FastGPT V4.9.9 Release Notes
---
## Upgrade Guide
### 1. Back Up Your Data
### 2. Pro Edition Users: Replace Your License
Pro edition users can contact the FastGPT team for a license replacement plan. After replacement, you can upgrade the system directly — the admin panel will prompt you to enter the new license.
### 3. Update Image Tags
- Update FastGPT image tag: v4.9.9
- Update FastGPT Pro image tag: v4.9.9
- mcp_server: no update required
- Sandbox: no update required
- AIProxy: no update required
## New Features
1. Switched from JWT to SessionId-based login authentication, with configurable maximum concurrent client sessions.
2. New Pro edition license management model.
3. WeChat Official Account calls now display and log chat conversation errors for easier troubleshooting.
4. API knowledge base now supports BasePath selection. Requires an additional API endpoint — see [API Knowledge Base Introduction](/docs/introduction/guide/knowledge_base/api_dataset/#4-获取文件详细信息用于获取文件信息) for details.
## Improvements
1. Optimized tool call logic for new tool detection.
2. Adjusted citation prompt text.
## Bug Fixes
1. Unable to retrieve app history save/publish records.
2. Member MCP tool creation permission issues.
3. Source citation display passing incorrect IDs, causing "no permission to access this file" errors.
4. Answer annotation frontend data errors.
document/content/docs/self-host/upgrading/outdated/499.mdx 0 → 100644
---
title: V4.9.9
description: FastGPT V4.9.9 更新说明
---
## 升级指南
### 1. 做好数据备份
### 2. 商业版用户替换新 License
商业版用户可以联系 FastGPT 团队支持同学，获取 License 替换方案。替换后，可以直接升级系统，管理后台会提示输入新 License。
### 3. 更新镜像 tag
- 更新 FastGPT 镜像 tag: v4.9.9
- 更新 FastGPT 商业版镜像 tag: v4.9.9
- mcp_server 无需更新
- Sandbox 无需更新
- AIProxy 无需更新
## 🚀 新增内容
1. 切换 SessionId 来替代 JWT 实现登录鉴权，可控制最大登录客户端数量。
2. 新的商业版 License 管理模式。
3. 公众号调用，显示记录 chat 对话错误，方便排查。
4. API 知识库支持 BasePath 选择，需增加 API 接口，具体可见[API 知识库介绍](/docs/introduction/guide/knowledge_base/api_dataset/#4-获取文件详细信息用于获取文件信息)
## ⚙️ 优化
1. 优化工具调用，新工具的判断逻辑。
2. 调整 Cite 引用提示词。
## 🐛 修复
1. 无法正常获取应用历史保存/发布记录。
2. 成员创建 MCP 工具权限问题。
3. 来源引用展示，存在 ID 传递错误，导致提示无权操作该文件。
4. 回答标注前端数据报错。
document/content/docs/self-host/upgrading/outdated/meta.en.json 0 → 100644
{
"title": "<4.12.0",
"description": "",
"pages": [
"4111",
"4110",
"4101",
"4100",
"4914",
"4913",
"4912",
"4911",
"4910",
"499",
"498",
"497",
"496",
"495",
"494",
"493",
"492",
"491",
"490",
"4823",
"4822",
"4821",
"4820",
"4819",
"4818",
"4817",
"4816",
"4815",
"4814",
"4813",
"4812",
"4811",
"4810",
"489",
"488",
"487",
"486",
"485",
"484",
"483",
"482",
"481",
"48",
"471",
"47",
"469",
"468",
"467",
"466",
"465",
"464",
"463",
"462",
"461",
"46",
"452",
"451",
"45",
"447",
"446",
"445",
"442",
"441",
"44",
"43",
"421",
"42",
"41",
"40"
]
}
document/content/docs/self-host/upgrading/outdated/meta.json 0 → 100644
{
"title": "<4.12.0",
"description": "",
"pages": [
"4111",
"4110",
"4101",
"4100",
"4914",
"4913",
"4912",
"4911",
"4910",
"499",
"498",
"497",
"496",
"495",
"494",
"493",
"492",
"491",
"490",
"4823",
"4822",
"4821",
"4820",
"4819",
"4818",
"4817",
"4816",
"4815",
"4814",
"4813",
"4812",
"4811",
"4810",
"489",
"488",
"487",
"486",
"485",
"484",
"483",
"482",
"481",
"48",
"471",
"47",
"469",
"468",
"467",
"466",
"465",
"464",
"463",
"462",
"461",
"46",
"452",
"451",
"45",
"447",
"446",
"445",
"442",
"441",
"44",
"43",
"421",
"42",
"41",
"40"
]
}
document/content/docs/self-host/upgrading/upgrade-intruction.en.mdx 0 → 100644
---
title: Upgrade Guide
description: FastGPT version upgrade guide
---
Upgrading FastGPT involves two steps:
1. Update the image
2. Run the upgrade initialization script
## Image Names
**GitHub Container Registry**
- FastGPT main image: ghcr.io/labring/fastgpt:latest
- Plugin image: ghcr.io/labring/fastgpt-plugin
- Code sandbox image: ghcr.io/labring/fastgpt-sandbox
- MCP SSE server image: ghcr.io/labring/fastgpt-mcp_server
- Commercial edition image: ghcr.io/c121914yu/fastgpt-pro:latest
**Alibaba Cloud**
- FastGPT main image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt
- Plugin image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-plugin
- Code sandbox image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox
- MCP SSE server image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server
- Commercial edition image: ghcr:registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-pro
An image consists of the image name and a `Tag`. For example, registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.6.1 refers to the `4.6.3` version image. Check Docker Hub or the GitHub repository for details.
## Updating Images on Sealos
1. Open [Sealos Cloud](https://cloud.sealos.io?uid=fnWRt09fZP) and find App Management on the desktop.
![](/imgs/updateImageSealos1.jpg)
2. Select the corresponding app - click the three dots on the right - Update.
![](/imgs/updateImageSealos2.png)
3. Update the image - Confirm changes.
If you need to modify the configuration file, scroll down to the `Configuration File` section to make changes.
![](/imgs/updateImageSealos3.png)
## Updating Images with Docker Compose
Simply modify the `image:` field in the `yml` file, then run:
```bash
docker-compose pull
docker-compose up -d
```
## Running the Upgrade Initialization Script
After updating the images, check the version notes in the documentation. Versions that require an upgrade script are typically labeled with "includes upgrade script". Open the corresponding documentation and follow the instructions to run the **upgrade script** -- in most cases, you just need to send a `POST` request.
## FAQ
### Why do I need to run an upgrade script?
When there are significant changes to the database schema that cannot be handled through default values, or when the migration logic is complex, an upgrade script is used to update certain database fields.
Following the initialization steps carefully will not cause any data loss. However, if the data volume is large, the initialization may take a while, during which the service may be temporarily unavailable.
### What is `{{host}}`?
`{{}}` denotes a variable. `{{host}}` refers to a variable named "host", which is your server's domain name or IP address.
On Sealos, you can find your domain name as shown below:
![](/imgs/updateImageSealos4.png)
### How to get the rootkey
You can find it in the `environment` section of your `docker-compose.yml` file -- it's the value of `ROOT_KEY`.
On Sealos, you can find it in the environment variables panel shown in the image above.
### How to upgrade across multiple versions
Back up your data first!
You can upgrade to the latest version and then run all the upgrade scripts in order. However, for stability, we recommend upgrading one version at a time. For example, if your current version is 4.4.7 and you need to upgrade to 4.6:
1. Update the image to 4.5, run the upgrade script
2. Update the image to 4.5.1, run the upgrade script
3. Update the image to 4.5.2, run the upgrade script
4. Update the image to 4.6, run the upgrade script
5. .....
Upgrade one version at a time.
document/content/docs/self-host/upgrading/upgrade-intruction.mdx 0 → 100644
---
title: 升级说明
description: FastGPT 版本升级说明
---
FastGPT 升级包括两个步骤：
1. 镜像升级
2. 执行升级初始化脚本
## 镜像名
**git版**
- FastGPT 主镜像: ghcr.io/labring/fastgpt:latest
- Plugin 镜像: ghcr.io/labring/fastgpt-plugin
- 代码沙箱镜像: ghcr.io/labring/fastgpt-sandbox
- MCP SSE setver 镜像: ghcr.io/labring/fastgpt-mcp_server
- 商业版镜像: ghcr.io/c121914yu/fastgpt-pro:latest
**阿里云**
- FastGPT 主镜像: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt
- Plugin 镜像: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-plugin
- 代码沙箱镜像: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox
- MCP SSE setver 镜像: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server
- 商业版镜像: ghcr:registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-pro
镜像由镜像名和`Tag`组成，例如: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.6.1 代表`4.6.3`版本镜像，具体可以看 docker hub, github 仓库。
## Sealos 修改镜像
1. 打开 [Sealos Cloud](https://cloud.sealos.io?uid=fnWRt09fZP)， 找到桌面上的应用管理
![](/imgs/updateImageSealos1.jpg)
2. 选择对应的应用 - 点击右边三个点 - 变更
![](/imgs/updateImageSealos2.png)
3. 修改镜像 - 确认变更
如果要修改配置文件，可以拉到下面的`配置文件`进行修改。
![](/imgs/updateImageSealos3.png)
## Docker-Compose 修改镜像
直接修改`yml`文件中的`image: `即可。随后执行:
```bash
docker-compose pull
docker-compose up -d
```
## 执行升级初始化脚本
镜像更新完后，可以查看文档中的`版本介绍`，通常需要执行升级脚本的版本都会标明`包含升级脚本`，打开对应的文档，参考说明执行**升级脚本**即可，大部分时候都是需要发送一个`POST`请求。
## QA
### 为什么需要执行升级脚本
数据表出现大幅度变更，无法通过设置默认值，或复杂度较高时，会通过升级脚本来更新部分数据表字段。
严格按初始化步骤进行操作，不会造成旧数据丢失。但在初始化过程中，如果数据量大，需要初始化的时间较长，这段时间可能会造成服务无法正常使用。
### `{{host}}` 是什么
`{{}}` 代表变量， `{{host}}`代表一个名为 host 的变量。指的是你服务器的域名或 IP。
Sealos 中，你可以在下图中找到你的域名：
![](/imgs/updateImageSealos4.png)
### 如何获取 rootkey
从`docker-compose.yml`中的`environment`中获取，对应的是`ROOT_KEY`的值。
sealos 中可以从上图左侧的环境变量中获取。
### 如何跨版本升级！！
先进行数据备份！！！
可以升级至最新版本，然后将所有升级脚本的版本都执行一遍。不过为了稳定，建议逐一版本升级。例如，当前版本是4.4.7，需要升级到4.6。
1. 修改镜像到4.5，执行升级脚本
2. 修改镜像到4.5.1，执行升级脚本
3. 修改镜像到4.5.2，执行升级脚本
4. 修改镜像到4.6，执行升级脚本
5. .....
逐一升级
document/content/docs/toc.en.mdx
......@@ -10,35 +10,11 @@ description: FastGPT Toc
- [/en/docs/faq/external_channel_integration](/en/docs/faq/external_channel_integration)
- [/en/docs/faq/other](/en/docs/faq/other)
- [/en/docs/faq/points_consumption](/en/docs/faq/points_consumption)
- [/en/docs/introduction/cloud](/en/docs/introduction/cloud)
- [/en/docs/introduction/cloud/faq](/en/docs/introduction/cloud/faq)
- [/en/docs/introduction/cloud/intro](/en/docs/introduction/cloud/intro)
- [/en/docs/introduction/cloud/privacy](/en/docs/introduction/cloud/privacy)
- [/en/docs/introduction/cloud/terms](/en/docs/introduction/cloud/terms)
- [/en/docs/introduction/commercial](/en/docs/introduction/commercial)
- [/en/docs/introduction/development/configuration](/en/docs/introduction/development/configuration)
- [/en/docs/introduction/development/custom-models/bge-rerank](/en/docs/introduction/development/custom-models/bge-rerank)
- [/en/docs/introduction/development/custom-models/chatglm2](/en/docs/introduction/development/custom-models/chatglm2)
- [/en/docs/introduction/development/custom-models/chatglm2-m3e](/en/docs/introduction/development/custom-models/chatglm2-m3e)
- [/en/docs/introduction/development/custom-models/m3e](/en/docs/introduction/development/custom-models/m3e)
- [/en/docs/introduction/development/custom-models/marker](/en/docs/introduction/development/custom-models/marker)
- [/en/docs/introduction/development/custom-models/mineru](/en/docs/introduction/development/custom-models/mineru)
- [/en/docs/introduction/development/custom-models/ollama](/en/docs/introduction/development/custom-models/ollama)
- [/en/docs/introduction/development/custom-models/xinference](/en/docs/introduction/development/custom-models/xinference)
- [/en/docs/introduction/development/design/dataset](/en/docs/introduction/development/design/dataset)
- [/en/docs/introduction/development/design/design_plugin](/en/docs/introduction/development/design/design_plugin)
- [/en/docs/introduction/development/docker](/en/docs/introduction/development/docker)
- [/en/docs/introduction/development/faq](/en/docs/introduction/development/faq)
- [/en/docs/introduction/development/intro](/en/docs/introduction/development/intro)
- [/en/docs/introduction/development/migration/docker_db](/en/docs/introduction/development/migration/docker_db)
- [/en/docs/introduction/development/migration/docker_mongo](/en/docs/introduction/development/migration/docker_mongo)
- [/en/docs/introduction/development/modelConfig/ai-proxy](/en/docs/introduction/development/modelConfig/ai-proxy)
- [/en/docs/introduction/development/modelConfig/intro](/en/docs/introduction/development/modelConfig/intro)
- [/en/docs/introduction/development/modelConfig/one-api](/en/docs/introduction/development/modelConfig/one-api)
- [/en/docs/introduction/development/modelConfig/ppio](/en/docs/introduction/development/modelConfig/ppio)
- [/en/docs/introduction/development/modelConfig/siliconCloud](/en/docs/introduction/development/modelConfig/siliconCloud)
- [/en/docs/introduction/development/object-storage](/en/docs/introduction/development/object-storage)
- [/en/docs/introduction/development/proxy/cloudflare](/en/docs/introduction/development/proxy/cloudflare)
- [/en/docs/introduction/development/proxy/http_proxy](/en/docs/introduction/development/proxy/http_proxy)
- [/en/docs/introduction/development/proxy/nginx](/en/docs/introduction/development/proxy/nginx)
- [/en/docs/introduction/development/sealos](/en/docs/introduction/development/sealos)
- [/en/docs/introduction/development/signoz](/en/docs/introduction/development/signoz)
- [/en/docs/introduction/guide/DialogBoxes/htmlRendering](/en/docs/introduction/guide/DialogBoxes/htmlRendering)
- [/en/docs/introduction/guide/DialogBoxes/quoteList](/en/docs/introduction/guide/DialogBoxes/quoteList)
- [/en/docs/introduction/guide/admin/sso](/en/docs/introduction/guide/admin/sso)
......@@ -92,102 +68,127 @@ description: FastGPT Toc
- [/en/docs/introduction/guide/team_permissions/invitation_link](/en/docs/introduction/guide/team_permissions/invitation_link)
- [/en/docs/introduction/guide/team_permissions/team_roles_permissions](/en/docs/introduction/guide/team_permissions/team_roles_permissions)
- [/en/docs/introduction/index](/en/docs/introduction/index)
- [/en/docs/introduction/opensource/intro](/en/docs/introduction/opensource/intro)
- [/en/docs/introduction/opensource/license](/en/docs/introduction/opensource/license)
- [/en/docs/openapi/app](/en/docs/openapi/app)
- [/en/docs/openapi/chat](/en/docs/openapi/chat)
- [/en/docs/openapi/dataset](/en/docs/openapi/dataset)
- [/en/docs/openapi/index](/en/docs/openapi/index)
- [/en/docs/openapi/intro](/en/docs/openapi/intro)
- [/en/docs/openapi/share](/en/docs/openapi/share)
- [/en/docs/protocol/open-source](/en/docs/protocol/open-source)
- [/en/docs/protocol/privacy](/en/docs/protocol/privacy)
- [/en/docs/protocol/terms](/en/docs/protocol/terms)
- [/en/docs/upgrading/4-10/4100](/en/docs/upgrading/4-10/4100)
- [/en/docs/upgrading/4-10/4101](/en/docs/upgrading/4-10/4101)
- [/en/docs/upgrading/4-11/4110](/en/docs/upgrading/4-11/4110)
- [/en/docs/upgrading/4-11/4111](/en/docs/upgrading/4-11/4111)
- [/en/docs/upgrading/4-12/4120](/en/docs/upgrading/4-12/4120)
- [/en/docs/upgrading/4-12/4121](/en/docs/upgrading/4-12/4121)
- [/en/docs/upgrading/4-12/4122](/en/docs/upgrading/4-12/4122)
- [/en/docs/upgrading/4-12/4123](/en/docs/upgrading/4-12/4123)
- [/en/docs/upgrading/4-12/4124](/en/docs/upgrading/4-12/4124)
- [/en/docs/upgrading/4-13/4130](/en/docs/upgrading/4-13/4130)
- [/en/docs/upgrading/4-13/4131](/en/docs/upgrading/4-13/4131)
- [/en/docs/upgrading/4-13/4132](/en/docs/upgrading/4-13/4132)
- [/en/docs/upgrading/4-14/4140](/en/docs/upgrading/4-14/4140)
- [/en/docs/upgrading/4-14/4141](/en/docs/upgrading/4-14/4141)
- [/en/docs/upgrading/4-14/4142](/en/docs/upgrading/4-14/4142)
- [/en/docs/upgrading/4-14/4143](/en/docs/upgrading/4-14/4143)
- [/en/docs/upgrading/4-14/4144](/en/docs/upgrading/4-14/4144)
- [/en/docs/upgrading/4-14/4145](/en/docs/upgrading/4-14/4145)
- [/en/docs/upgrading/4-14/41451](/en/docs/upgrading/4-14/41451)
- [/en/docs/upgrading/4-14/4146](/en/docs/upgrading/4-14/4146)
- [/en/docs/upgrading/4-14/4147](/en/docs/upgrading/4-14/4147)
- [/en/docs/upgrading/4-14/4148](/en/docs/upgrading/4-14/4148)
- [/en/docs/upgrading/4-8/40](/en/docs/upgrading/4-8/40)
- [/en/docs/upgrading/4-8/41](/en/docs/upgrading/4-8/41)
- [/en/docs/upgrading/4-8/42](/en/docs/upgrading/4-8/42)
- [/en/docs/upgrading/4-8/421](/en/docs/upgrading/4-8/421)
- [/en/docs/upgrading/4-8/43](/en/docs/upgrading/4-8/43)
- [/en/docs/upgrading/4-8/44](/en/docs/upgrading/4-8/44)
- [/en/docs/upgrading/4-8/441](/en/docs/upgrading/4-8/441)
- [/en/docs/upgrading/4-8/442](/en/docs/upgrading/4-8/442)
- [/en/docs/upgrading/4-8/445](/en/docs/upgrading/4-8/445)
- [/en/docs/upgrading/4-8/446](/en/docs/upgrading/4-8/446)
- [/en/docs/upgrading/4-8/447](/en/docs/upgrading/4-8/447)
- [/en/docs/upgrading/4-8/45](/en/docs/upgrading/4-8/45)
- [/en/docs/upgrading/4-8/451](/en/docs/upgrading/4-8/451)
- [/en/docs/upgrading/4-8/452](/en/docs/upgrading/4-8/452)
- [/en/docs/upgrading/4-8/46](/en/docs/upgrading/4-8/46)
- [/en/docs/upgrading/4-8/461](/en/docs/upgrading/4-8/461)
- [/en/docs/upgrading/4-8/462](/en/docs/upgrading/4-8/462)
- [/en/docs/upgrading/4-8/463](/en/docs/upgrading/4-8/463)
- [/en/docs/upgrading/4-8/464](/en/docs/upgrading/4-8/464)
- [/en/docs/upgrading/4-8/465](/en/docs/upgrading/4-8/465)
- [/en/docs/upgrading/4-8/466](/en/docs/upgrading/4-8/466)
- [/en/docs/upgrading/4-8/467](/en/docs/upgrading/4-8/467)
- [/en/docs/upgrading/4-8/468](/en/docs/upgrading/4-8/468)
- [/en/docs/upgrading/4-8/469](/en/docs/upgrading/4-8/469)
- [/en/docs/upgrading/4-8/47](/en/docs/upgrading/4-8/47)
- [/en/docs/upgrading/4-8/471](/en/docs/upgrading/4-8/471)
- [/en/docs/upgrading/4-8/48](/en/docs/upgrading/4-8/48)
- [/en/docs/upgrading/4-8/481](/en/docs/upgrading/4-8/481)
- [/en/docs/upgrading/4-8/4810](/en/docs/upgrading/4-8/4810)
- [/en/docs/upgrading/4-8/4811](/en/docs/upgrading/4-8/4811)
- [/en/docs/upgrading/4-8/4812](/en/docs/upgrading/4-8/4812)
- [/en/docs/upgrading/4-8/4813](/en/docs/upgrading/4-8/4813)
- [/en/docs/upgrading/4-8/4814](/en/docs/upgrading/4-8/4814)
- [/en/docs/upgrading/4-8/4815](/en/docs/upgrading/4-8/4815)
- [/en/docs/upgrading/4-8/4816](/en/docs/upgrading/4-8/4816)
- [/en/docs/upgrading/4-8/4817](/en/docs/upgrading/4-8/4817)
- [/en/docs/upgrading/4-8/4818](/en/docs/upgrading/4-8/4818)
- [/en/docs/upgrading/4-8/4819](/en/docs/upgrading/4-8/4819)
- [/en/docs/upgrading/4-8/482](/en/docs/upgrading/4-8/482)
- [/en/docs/upgrading/4-8/4820](/en/docs/upgrading/4-8/4820)
- [/en/docs/upgrading/4-8/4821](/en/docs/upgrading/4-8/4821)
- [/en/docs/upgrading/4-8/4822](/en/docs/upgrading/4-8/4822)
- [/en/docs/upgrading/4-8/4823](/en/docs/upgrading/4-8/4823)
- [/en/docs/upgrading/4-8/483](/en/docs/upgrading/4-8/483)
- [/en/docs/upgrading/4-8/484](/en/docs/upgrading/4-8/484)
- [/en/docs/upgrading/4-8/485](/en/docs/upgrading/4-8/485)
- [/en/docs/upgrading/4-8/486](/en/docs/upgrading/4-8/486)
- [/en/docs/upgrading/4-8/487](/en/docs/upgrading/4-8/487)
- [/en/docs/upgrading/4-8/488](/en/docs/upgrading/4-8/488)
- [/en/docs/upgrading/4-8/489](/en/docs/upgrading/4-8/489)
- [/en/docs/upgrading/4-9/490](/en/docs/upgrading/4-9/490)
- [/en/docs/upgrading/4-9/491](/en/docs/upgrading/4-9/491)
- [/en/docs/upgrading/4-9/4910](/en/docs/upgrading/4-9/4910)
- [/en/docs/upgrading/4-9/4911](/en/docs/upgrading/4-9/4911)
- [/en/docs/upgrading/4-9/4912](/en/docs/upgrading/4-9/4912)
- [/en/docs/upgrading/4-9/4913](/en/docs/upgrading/4-9/4913)
- [/en/docs/upgrading/4-9/4914](/en/docs/upgrading/4-9/4914)
- [/en/docs/upgrading/4-9/492](/en/docs/upgrading/4-9/492)
- [/en/docs/upgrading/4-9/493](/en/docs/upgrading/4-9/493)
- [/en/docs/upgrading/4-9/494](/en/docs/upgrading/4-9/494)
- [/en/docs/upgrading/4-9/495](/en/docs/upgrading/4-9/495)
- [/en/docs/upgrading/4-9/496](/en/docs/upgrading/4-9/496)
- [/en/docs/upgrading/4-9/497](/en/docs/upgrading/4-9/497)
- [/en/docs/upgrading/4-9/498](/en/docs/upgrading/4-9/498)
- [/en/docs/upgrading/4-9/499](/en/docs/upgrading/4-9/499)
- [/en/docs/self-host/config/json](/en/docs/self-host/config/json)
- [/en/docs/self-host/config/model/ai-proxy](/en/docs/self-host/config/model/ai-proxy)
- [/en/docs/self-host/config/model/intro](/en/docs/self-host/config/model/intro)
- [/en/docs/self-host/config/model/one-api](/en/docs/self-host/config/model/one-api)
- [/en/docs/self-host/config/model/ppio](/en/docs/self-host/config/model/ppio)
- [/en/docs/self-host/config/model/siliconCloud](/en/docs/self-host/config/model/siliconCloud)
- [/en/docs/self-host/config/object-storage](/en/docs/self-host/config/object-storage)
- [/en/docs/self-host/config/signoz](/en/docs/self-host/config/signoz)
- [/en/docs/self-host/custom-models/bge-rerank](/en/docs/self-host/custom-models/bge-rerank)
- [/en/docs/self-host/custom-models/chatglm2](/en/docs/self-host/custom-models/chatglm2)
- [/en/docs/self-host/custom-models/chatglm2-m3e](/en/docs/self-host/custom-models/chatglm2-m3e)
- [/en/docs/self-host/custom-models/m3e](/en/docs/self-host/custom-models/m3e)
- [/en/docs/self-host/custom-models/marker](/en/docs/self-host/custom-models/marker)
- [/en/docs/self-host/custom-models/mineru](/en/docs/self-host/custom-models/mineru)
- [/en/docs/self-host/custom-models/ollama](/en/docs/self-host/custom-models/ollama)
- [/en/docs/self-host/custom-models/xinference](/en/docs/self-host/custom-models/xinference)
- [/en/docs/self-host/deploy/docker](/en/docs/self-host/deploy/docker)
- [/en/docs/self-host/deploy/sealos](/en/docs/self-host/deploy/sealos)
- [/en/docs/self-host/design/dataset](/en/docs/self-host/design/dataset)
- [/en/docs/self-host/design/design_plugin](/en/docs/self-host/design/design_plugin)
- [/en/docs/self-host/dev](/en/docs/self-host/dev)
- [/en/docs/self-host/faq](/en/docs/self-host/faq)
- [/en/docs/self-host/index](/en/docs/self-host/index)
- [/en/docs/self-host/migration/docker_db](/en/docs/self-host/migration/docker_db)
- [/en/docs/self-host/migration/docker_mongo](/en/docs/self-host/migration/docker_mongo)
- [/en/docs/self-host/upgrading/4-12/4120](/en/docs/self-host/upgrading/4-12/4120)
- [/en/docs/self-host/upgrading/4-12/4121](/en/docs/self-host/upgrading/4-12/4121)
- [/en/docs/self-host/upgrading/4-12/4122](/en/docs/self-host/upgrading/4-12/4122)
- [/en/docs/self-host/upgrading/4-12/4123](/en/docs/self-host/upgrading/4-12/4123)
- [/en/docs/self-host/upgrading/4-12/4124](/en/docs/self-host/upgrading/4-12/4124)
- [/en/docs/self-host/upgrading/4-13/4130](/en/docs/self-host/upgrading/4-13/4130)
- [/en/docs/self-host/upgrading/4-13/4131](/en/docs/self-host/upgrading/4-13/4131)
- [/en/docs/self-host/upgrading/4-13/4132](/en/docs/self-host/upgrading/4-13/4132)
- [/en/docs/self-host/upgrading/4-14/4140](/en/docs/self-host/upgrading/4-14/4140)
- [/en/docs/self-host/upgrading/4-14/4141](/en/docs/self-host/upgrading/4-14/4141)
- [/en/docs/self-host/upgrading/4-14/4142](/en/docs/self-host/upgrading/4-14/4142)
- [/en/docs/self-host/upgrading/4-14/4143](/en/docs/self-host/upgrading/4-14/4143)
- [/en/docs/self-host/upgrading/4-14/4144](/en/docs/self-host/upgrading/4-14/4144)
- [/en/docs/self-host/upgrading/4-14/4145](/en/docs/self-host/upgrading/4-14/4145)
- [/en/docs/self-host/upgrading/4-14/41451](/en/docs/self-host/upgrading/4-14/41451)
- [/en/docs/self-host/upgrading/4-14/4146](/en/docs/self-host/upgrading/4-14/4146)
- [/en/docs/self-host/upgrading/4-14/4147](/en/docs/self-host/upgrading/4-14/4147)
- [/en/docs/self-host/upgrading/4-14/4148](/en/docs/self-host/upgrading/4-14/4148)
- [/en/docs/self-host/upgrading/outdated/40](/en/docs/self-host/upgrading/outdated/40)
- [/en/docs/self-host/upgrading/outdated/41](/en/docs/self-host/upgrading/outdated/41)
- [/en/docs/self-host/upgrading/outdated/4100](/en/docs/self-host/upgrading/outdated/4100)
- [/en/docs/self-host/upgrading/outdated/4101](/en/docs/self-host/upgrading/outdated/4101)
- [/en/docs/self-host/upgrading/outdated/4110](/en/docs/self-host/upgrading/outdated/4110)
- [/en/docs/self-host/upgrading/outdated/4111](/en/docs/self-host/upgrading/outdated/4111)
- [/en/docs/self-host/upgrading/outdated/42](/en/docs/self-host/upgrading/outdated/42)
- [/en/docs/self-host/upgrading/outdated/421](/en/docs/self-host/upgrading/outdated/421)
- [/en/docs/self-host/upgrading/outdated/43](/en/docs/self-host/upgrading/outdated/43)
- [/en/docs/self-host/upgrading/outdated/44](/en/docs/self-host/upgrading/outdated/44)
- [/en/docs/self-host/upgrading/outdated/441](/en/docs/self-host/upgrading/outdated/441)
- [/en/docs/self-host/upgrading/outdated/442](/en/docs/self-host/upgrading/outdated/442)
- [/en/docs/self-host/upgrading/outdated/445](/en/docs/self-host/upgrading/outdated/445)
- [/en/docs/self-host/upgrading/outdated/446](/en/docs/self-host/upgrading/outdated/446)
- [/en/docs/self-host/upgrading/outdated/447](/en/docs/self-host/upgrading/outdated/447)
- [/en/docs/self-host/upgrading/outdated/45](/en/docs/self-host/upgrading/outdated/45)
- [/en/docs/self-host/upgrading/outdated/451](/en/docs/self-host/upgrading/outdated/451)
- [/en/docs/self-host/upgrading/outdated/452](/en/docs/self-host/upgrading/outdated/452)
- [/en/docs/self-host/upgrading/outdated/46](/en/docs/self-host/upgrading/outdated/46)
- [/en/docs/self-host/upgrading/outdated/461](/en/docs/self-host/upgrading/outdated/461)
- [/en/docs/self-host/upgrading/outdated/462](/en/docs/self-host/upgrading/outdated/462)
- [/en/docs/self-host/upgrading/outdated/463](/en/docs/self-host/upgrading/outdated/463)
- [/en/docs/self-host/upgrading/outdated/464](/en/docs/self-host/upgrading/outdated/464)
- [/en/docs/self-host/upgrading/outdated/465](/en/docs/self-host/upgrading/outdated/465)
- [/en/docs/self-host/upgrading/outdated/466](/en/docs/self-host/upgrading/outdated/466)
- [/en/docs/self-host/upgrading/outdated/467](/en/docs/self-host/upgrading/outdated/467)
- [/en/docs/self-host/upgrading/outdated/468](/en/docs/self-host/upgrading/outdated/468)
- [/en/docs/self-host/upgrading/outdated/469](/en/docs/self-host/upgrading/outdated/469)
- [/en/docs/self-host/upgrading/outdated/47](/en/docs/self-host/upgrading/outdated/47)
- [/en/docs/self-host/upgrading/outdated/471](/en/docs/self-host/upgrading/outdated/471)
- [/en/docs/self-host/upgrading/outdated/48](/en/docs/self-host/upgrading/outdated/48)
- [/en/docs/self-host/upgrading/outdated/481](/en/docs/self-host/upgrading/outdated/481)
- [/en/docs/self-host/upgrading/outdated/4810](/en/docs/self-host/upgrading/outdated/4810)
- [/en/docs/self-host/upgrading/outdated/4811](/en/docs/self-host/upgrading/outdated/4811)
- [/en/docs/self-host/upgrading/outdated/4812](/en/docs/self-host/upgrading/outdated/4812)
- [/en/docs/self-host/upgrading/outdated/4813](/en/docs/self-host/upgrading/outdated/4813)
- [/en/docs/self-host/upgrading/outdated/4814](/en/docs/self-host/upgrading/outdated/4814)
- [/en/docs/self-host/upgrading/outdated/4815](/en/docs/self-host/upgrading/outdated/4815)
- [/en/docs/self-host/upgrading/outdated/4816](/en/docs/self-host/upgrading/outdated/4816)
- [/en/docs/self-host/upgrading/outdated/4817](/en/docs/self-host/upgrading/outdated/4817)
- [/en/docs/self-host/upgrading/outdated/4818](/en/docs/self-host/upgrading/outdated/4818)
- [/en/docs/self-host/upgrading/outdated/4819](/en/docs/self-host/upgrading/outdated/4819)
- [/en/docs/self-host/upgrading/outdated/482](/en/docs/self-host/upgrading/outdated/482)
- [/en/docs/self-host/upgrading/outdated/4820](/en/docs/self-host/upgrading/outdated/4820)
- [/en/docs/self-host/upgrading/outdated/4821](/en/docs/self-host/upgrading/outdated/4821)
- [/en/docs/self-host/upgrading/outdated/4822](/en/docs/self-host/upgrading/outdated/4822)
- [/en/docs/self-host/upgrading/outdated/4823](/en/docs/self-host/upgrading/outdated/4823)
- [/en/docs/self-host/upgrading/outdated/483](/en/docs/self-host/upgrading/outdated/483)
- [/en/docs/self-host/upgrading/outdated/484](/en/docs/self-host/upgrading/outdated/484)
- [/en/docs/self-host/upgrading/outdated/485](/en/docs/self-host/upgrading/outdated/485)
- [/en/docs/self-host/upgrading/outdated/486](/en/docs/self-host/upgrading/outdated/486)
- [/en/docs/self-host/upgrading/outdated/487](/en/docs/self-host/upgrading/outdated/487)
- [/en/docs/self-host/upgrading/outdated/488](/en/docs/self-host/upgrading/outdated/488)
- [/en/docs/self-host/upgrading/outdated/489](/en/docs/self-host/upgrading/outdated/489)
- [/en/docs/self-host/upgrading/outdated/490](/en/docs/self-host/upgrading/outdated/490)
- [/en/docs/self-host/upgrading/outdated/491](/en/docs/self-host/upgrading/outdated/491)
- [/en/docs/self-host/upgrading/outdated/4910](/en/docs/self-host/upgrading/outdated/4910)
- [/en/docs/self-host/upgrading/outdated/4911](/en/docs/self-host/upgrading/outdated/4911)
- [/en/docs/self-host/upgrading/outdated/4912](/en/docs/self-host/upgrading/outdated/4912)
- [/en/docs/self-host/upgrading/outdated/4913](/en/docs/self-host/upgrading/outdated/4913)
- [/en/docs/self-host/upgrading/outdated/4914](/en/docs/self-host/upgrading/outdated/4914)
- [/en/docs/self-host/upgrading/outdated/492](/en/docs/self-host/upgrading/outdated/492)
- [/en/docs/self-host/upgrading/outdated/493](/en/docs/self-host/upgrading/outdated/493)
- [/en/docs/self-host/upgrading/outdated/494](/en/docs/self-host/upgrading/outdated/494)
- [/en/docs/self-host/upgrading/outdated/495](/en/docs/self-host/upgrading/outdated/495)
- [/en/docs/self-host/upgrading/outdated/496](/en/docs/self-host/upgrading/outdated/496)
- [/en/docs/self-host/upgrading/outdated/497](/en/docs/self-host/upgrading/outdated/497)
- [/en/docs/self-host/upgrading/outdated/498](/en/docs/self-host/upgrading/outdated/498)
- [/en/docs/self-host/upgrading/outdated/499](/en/docs/self-host/upgrading/outdated/499)
- [/en/docs/self-host/upgrading/upgrade-intruction](/en/docs/self-host/upgrading/upgrade-intruction)
- [/en/docs/use-cases/app-cases/dalle3](/en/docs/use-cases/app-cases/dalle3)
- [/en/docs/use-cases/app-cases/english_essay_correction_bot](/en/docs/use-cases/app-cases/english_essay_correction_bot)
- [/en/docs/use-cases/app-cases/feishu_webhook](/en/docs/use-cases/app-cases/feishu_webhook)
......
document/content/docs/toc.mdx
......@@ -10,35 +10,11 @@ description: FastGPT 文档目录
- [/docs/faq/external_channel_integration](/docs/faq/external_channel_integration)
- [/docs/faq/other](/docs/faq/other)
- [/docs/faq/points_consumption](/docs/faq/points_consumption)
- [/docs/introduction/cloud](/docs/introduction/cloud)
- [/docs/introduction/cloud/faq](/docs/introduction/cloud/faq)
- [/docs/introduction/cloud/intro](/docs/introduction/cloud/intro)
- [/docs/introduction/cloud/privacy](/docs/introduction/cloud/privacy)
- [/docs/introduction/cloud/terms](/docs/introduction/cloud/terms)
- [/docs/introduction/commercial](/docs/introduction/commercial)
- [/docs/introduction/development/configuration](/docs/introduction/development/configuration)
- [/docs/introduction/development/custom-models/bge-rerank](/docs/introduction/development/custom-models/bge-rerank)
- [/docs/introduction/development/custom-models/chatglm2](/docs/introduction/development/custom-models/chatglm2)
- [/docs/introduction/development/custom-models/chatglm2-m3e](/docs/introduction/development/custom-models/chatglm2-m3e)
- [/docs/introduction/development/custom-models/m3e](/docs/introduction/development/custom-models/m3e)
- [/docs/introduction/development/custom-models/marker](/docs/introduction/development/custom-models/marker)
- [/docs/introduction/development/custom-models/mineru](/docs/introduction/development/custom-models/mineru)
- [/docs/introduction/development/custom-models/ollama](/docs/introduction/development/custom-models/ollama)
- [/docs/introduction/development/custom-models/xinference](/docs/introduction/development/custom-models/xinference)
- [/docs/introduction/development/design/dataset](/docs/introduction/development/design/dataset)
- [/docs/introduction/development/design/design_plugin](/docs/introduction/development/design/design_plugin)
- [/docs/introduction/development/docker](/docs/introduction/development/docker)
- [/docs/introduction/development/faq](/docs/introduction/development/faq)
- [/docs/introduction/development/intro](/docs/introduction/development/intro)
- [/docs/introduction/development/migration/docker_db](/docs/introduction/development/migration/docker_db)
- [/docs/introduction/development/migration/docker_mongo](/docs/introduction/development/migration/docker_mongo)
- [/docs/introduction/development/modelConfig/ai-proxy](/docs/introduction/development/modelConfig/ai-proxy)
- [/docs/introduction/development/modelConfig/intro](/docs/introduction/development/modelConfig/intro)
- [/docs/introduction/development/modelConfig/one-api](/docs/introduction/development/modelConfig/one-api)
- [/docs/introduction/development/modelConfig/ppio](/docs/introduction/development/modelConfig/ppio)
- [/docs/introduction/development/modelConfig/siliconCloud](/docs/introduction/development/modelConfig/siliconCloud)
- [/docs/introduction/development/object-storage](/docs/introduction/development/object-storage)
- [/docs/introduction/development/proxy/cloudflare](/docs/introduction/development/proxy/cloudflare)
- [/docs/introduction/development/proxy/http_proxy](/docs/introduction/development/proxy/http_proxy)
- [/docs/introduction/development/proxy/nginx](/docs/introduction/development/proxy/nginx)
- [/docs/introduction/development/sealos](/docs/introduction/development/sealos)
- [/docs/introduction/development/signoz](/docs/introduction/development/signoz)
- [/docs/introduction/guide/DialogBoxes/htmlRendering](/docs/introduction/guide/DialogBoxes/htmlRendering)
- [/docs/introduction/guide/DialogBoxes/quoteList](/docs/introduction/guide/DialogBoxes/quoteList)
- [/docs/introduction/guide/admin/sso](/docs/introduction/guide/admin/sso)
......@@ -92,102 +68,127 @@ description: FastGPT 文档目录
- [/docs/introduction/guide/team_permissions/invitation_link](/docs/introduction/guide/team_permissions/invitation_link)
- [/docs/introduction/guide/team_permissions/team_roles_permissions](/docs/introduction/guide/team_permissions/team_roles_permissions)
- [/docs/introduction/index](/docs/introduction/index)
- [/docs/introduction/opensource/intro](/docs/introduction/opensource/intro)
- [/docs/introduction/opensource/license](/docs/introduction/opensource/license)
- [/docs/openapi/app](/docs/openapi/app)
- [/docs/openapi/chat](/docs/openapi/chat)
- [/docs/openapi/dataset](/docs/openapi/dataset)
- [/docs/openapi/index](/docs/openapi/index)
- [/docs/openapi/intro](/docs/openapi/intro)
- [/docs/openapi/share](/docs/openapi/share)
- [/docs/protocol/open-source](/docs/protocol/open-source)
- [/docs/protocol/privacy](/docs/protocol/privacy)
- [/docs/protocol/terms](/docs/protocol/terms)
- [/docs/upgrading/4-10/4100](/docs/upgrading/4-10/4100)
- [/docs/upgrading/4-10/4101](/docs/upgrading/4-10/4101)
- [/docs/upgrading/4-11/4110](/docs/upgrading/4-11/4110)
- [/docs/upgrading/4-11/4111](/docs/upgrading/4-11/4111)
- [/docs/upgrading/4-12/4120](/docs/upgrading/4-12/4120)
- [/docs/upgrading/4-12/4121](/docs/upgrading/4-12/4121)
- [/docs/upgrading/4-12/4122](/docs/upgrading/4-12/4122)
- [/docs/upgrading/4-12/4123](/docs/upgrading/4-12/4123)
- [/docs/upgrading/4-12/4124](/docs/upgrading/4-12/4124)
- [/docs/upgrading/4-13/4130](/docs/upgrading/4-13/4130)
- [/docs/upgrading/4-13/4131](/docs/upgrading/4-13/4131)
- [/docs/upgrading/4-13/4132](/docs/upgrading/4-13/4132)
- [/docs/upgrading/4-14/4140](/docs/upgrading/4-14/4140)
- [/docs/upgrading/4-14/4141](/docs/upgrading/4-14/4141)
- [/docs/upgrading/4-14/4142](/docs/upgrading/4-14/4142)
- [/docs/upgrading/4-14/4143](/docs/upgrading/4-14/4143)
- [/docs/upgrading/4-14/4144](/docs/upgrading/4-14/4144)
- [/docs/upgrading/4-14/4145](/docs/upgrading/4-14/4145)
- [/docs/upgrading/4-14/41451](/docs/upgrading/4-14/41451)
- [/docs/upgrading/4-14/4146](/docs/upgrading/4-14/4146)
- [/docs/upgrading/4-14/4147](/docs/upgrading/4-14/4147)
- [/docs/upgrading/4-14/4148](/docs/upgrading/4-14/4148)
- [/docs/upgrading/4-8/40](/docs/upgrading/4-8/40)
- [/docs/upgrading/4-8/41](/docs/upgrading/4-8/41)
- [/docs/upgrading/4-8/42](/docs/upgrading/4-8/42)
- [/docs/upgrading/4-8/421](/docs/upgrading/4-8/421)
- [/docs/upgrading/4-8/43](/docs/upgrading/4-8/43)
- [/docs/upgrading/4-8/44](/docs/upgrading/4-8/44)
- [/docs/upgrading/4-8/441](/docs/upgrading/4-8/441)
- [/docs/upgrading/4-8/442](/docs/upgrading/4-8/442)
- [/docs/upgrading/4-8/445](/docs/upgrading/4-8/445)
- [/docs/upgrading/4-8/446](/docs/upgrading/4-8/446)
- [/docs/upgrading/4-8/447](/docs/upgrading/4-8/447)
- [/docs/upgrading/4-8/45](/docs/upgrading/4-8/45)
- [/docs/upgrading/4-8/451](/docs/upgrading/4-8/451)
- [/docs/upgrading/4-8/452](/docs/upgrading/4-8/452)
- [/docs/upgrading/4-8/46](/docs/upgrading/4-8/46)
- [/docs/upgrading/4-8/461](/docs/upgrading/4-8/461)
- [/docs/upgrading/4-8/462](/docs/upgrading/4-8/462)
- [/docs/upgrading/4-8/463](/docs/upgrading/4-8/463)
- [/docs/upgrading/4-8/464](/docs/upgrading/4-8/464)
- [/docs/upgrading/4-8/465](/docs/upgrading/4-8/465)
- [/docs/upgrading/4-8/466](/docs/upgrading/4-8/466)
- [/docs/upgrading/4-8/467](/docs/upgrading/4-8/467)
- [/docs/upgrading/4-8/468](/docs/upgrading/4-8/468)
- [/docs/upgrading/4-8/469](/docs/upgrading/4-8/469)
- [/docs/upgrading/4-8/47](/docs/upgrading/4-8/47)
- [/docs/upgrading/4-8/471](/docs/upgrading/4-8/471)
- [/docs/upgrading/4-8/48](/docs/upgrading/4-8/48)
- [/docs/upgrading/4-8/481](/docs/upgrading/4-8/481)
- [/docs/upgrading/4-8/4810](/docs/upgrading/4-8/4810)
- [/docs/upgrading/4-8/4811](/docs/upgrading/4-8/4811)
- [/docs/upgrading/4-8/4812](/docs/upgrading/4-8/4812)
- [/docs/upgrading/4-8/4813](/docs/upgrading/4-8/4813)
- [/docs/upgrading/4-8/4814](/docs/upgrading/4-8/4814)
- [/docs/upgrading/4-8/4815](/docs/upgrading/4-8/4815)
- [/docs/upgrading/4-8/4816](/docs/upgrading/4-8/4816)
- [/docs/upgrading/4-8/4817](/docs/upgrading/4-8/4817)
- [/docs/upgrading/4-8/4818](/docs/upgrading/4-8/4818)
- [/docs/upgrading/4-8/4819](/docs/upgrading/4-8/4819)
- [/docs/upgrading/4-8/482](/docs/upgrading/4-8/482)
- [/docs/upgrading/4-8/4820](/docs/upgrading/4-8/4820)
- [/docs/upgrading/4-8/4821](/docs/upgrading/4-8/4821)
- [/docs/upgrading/4-8/4822](/docs/upgrading/4-8/4822)
- [/docs/upgrading/4-8/4823](/docs/upgrading/4-8/4823)
- [/docs/upgrading/4-8/483](/docs/upgrading/4-8/483)
- [/docs/upgrading/4-8/484](/docs/upgrading/4-8/484)
- [/docs/upgrading/4-8/485](/docs/upgrading/4-8/485)
- [/docs/upgrading/4-8/486](/docs/upgrading/4-8/486)
- [/docs/upgrading/4-8/487](/docs/upgrading/4-8/487)
- [/docs/upgrading/4-8/488](/docs/upgrading/4-8/488)
- [/docs/upgrading/4-8/489](/docs/upgrading/4-8/489)
- [/docs/upgrading/4-9/490](/docs/upgrading/4-9/490)
- [/docs/upgrading/4-9/491](/docs/upgrading/4-9/491)
- [/docs/upgrading/4-9/4910](/docs/upgrading/4-9/4910)
- [/docs/upgrading/4-9/4911](/docs/upgrading/4-9/4911)
- [/docs/upgrading/4-9/4912](/docs/upgrading/4-9/4912)
- [/docs/upgrading/4-9/4913](/docs/upgrading/4-9/4913)
- [/docs/upgrading/4-9/4914](/docs/upgrading/4-9/4914)
- [/docs/upgrading/4-9/492](/docs/upgrading/4-9/492)
- [/docs/upgrading/4-9/493](/docs/upgrading/4-9/493)
- [/docs/upgrading/4-9/494](/docs/upgrading/4-9/494)
- [/docs/upgrading/4-9/495](/docs/upgrading/4-9/495)
- [/docs/upgrading/4-9/496](/docs/upgrading/4-9/496)
- [/docs/upgrading/4-9/497](/docs/upgrading/4-9/497)
- [/docs/upgrading/4-9/498](/docs/upgrading/4-9/498)
- [/docs/upgrading/4-9/499](/docs/upgrading/4-9/499)
- [/docs/self-host/config/json](/docs/self-host/config/json)
- [/docs/self-host/config/model/ai-proxy](/docs/self-host/config/model/ai-proxy)
- [/docs/self-host/config/model/intro](/docs/self-host/config/model/intro)
- [/docs/self-host/config/model/one-api](/docs/self-host/config/model/one-api)
- [/docs/self-host/config/model/ppio](/docs/self-host/config/model/ppio)
- [/docs/self-host/config/model/siliconCloud](/docs/self-host/config/model/siliconCloud)
- [/docs/self-host/config/object-storage](/docs/self-host/config/object-storage)
- [/docs/self-host/config/signoz](/docs/self-host/config/signoz)
- [/docs/self-host/custom-models/bge-rerank](/docs/self-host/custom-models/bge-rerank)
- [/docs/self-host/custom-models/chatglm2](/docs/self-host/custom-models/chatglm2)
- [/docs/self-host/custom-models/chatglm2-m3e](/docs/self-host/custom-models/chatglm2-m3e)
- [/docs/self-host/custom-models/m3e](/docs/self-host/custom-models/m3e)
- [/docs/self-host/custom-models/marker](/docs/self-host/custom-models/marker)
- [/docs/self-host/custom-models/mineru](/docs/self-host/custom-models/mineru)
- [/docs/self-host/custom-models/ollama](/docs/self-host/custom-models/ollama)
- [/docs/self-host/custom-models/xinference](/docs/self-host/custom-models/xinference)
- [/docs/self-host/deploy/docker](/docs/self-host/deploy/docker)
- [/docs/self-host/deploy/sealos](/docs/self-host/deploy/sealos)
- [/docs/self-host/design/dataset](/docs/self-host/design/dataset)
- [/docs/self-host/design/design_plugin](/docs/self-host/design/design_plugin)
- [/docs/self-host/dev](/docs/self-host/dev)
- [/docs/self-host/faq](/docs/self-host/faq)
- [/docs/self-host/index](/docs/self-host/index)
- [/docs/self-host/migration/docker_db](/docs/self-host/migration/docker_db)
- [/docs/self-host/migration/docker_mongo](/docs/self-host/migration/docker_mongo)
- [/docs/self-host/upgrading/4-12/4120](/docs/self-host/upgrading/4-12/4120)
- [/docs/self-host/upgrading/4-12/4121](/docs/self-host/upgrading/4-12/4121)
- [/docs/self-host/upgrading/4-12/4122](/docs/self-host/upgrading/4-12/4122)
- [/docs/self-host/upgrading/4-12/4123](/docs/self-host/upgrading/4-12/4123)
- [/docs/self-host/upgrading/4-12/4124](/docs/self-host/upgrading/4-12/4124)
- [/docs/self-host/upgrading/4-13/4130](/docs/self-host/upgrading/4-13/4130)
- [/docs/self-host/upgrading/4-13/4131](/docs/self-host/upgrading/4-13/4131)
- [/docs/self-host/upgrading/4-13/4132](/docs/self-host/upgrading/4-13/4132)
- [/docs/self-host/upgrading/4-14/4140](/docs/self-host/upgrading/4-14/4140)
- [/docs/self-host/upgrading/4-14/4141](/docs/self-host/upgrading/4-14/4141)
- [/docs/self-host/upgrading/4-14/4142](/docs/self-host/upgrading/4-14/4142)
- [/docs/self-host/upgrading/4-14/4143](/docs/self-host/upgrading/4-14/4143)
- [/docs/self-host/upgrading/4-14/4144](/docs/self-host/upgrading/4-14/4144)
- [/docs/self-host/upgrading/4-14/4145](/docs/self-host/upgrading/4-14/4145)
- [/docs/self-host/upgrading/4-14/41451](/docs/self-host/upgrading/4-14/41451)
- [/docs/self-host/upgrading/4-14/4146](/docs/self-host/upgrading/4-14/4146)
- [/docs/self-host/upgrading/4-14/4147](/docs/self-host/upgrading/4-14/4147)
- [/docs/self-host/upgrading/4-14/4148](/docs/self-host/upgrading/4-14/4148)
- [/docs/self-host/upgrading/outdated/40](/docs/self-host/upgrading/outdated/40)
- [/docs/self-host/upgrading/outdated/41](/docs/self-host/upgrading/outdated/41)
- [/docs/self-host/upgrading/outdated/4100](/docs/self-host/upgrading/outdated/4100)
- [/docs/self-host/upgrading/outdated/4101](/docs/self-host/upgrading/outdated/4101)
- [/docs/self-host/upgrading/outdated/4110](/docs/self-host/upgrading/outdated/4110)
- [/docs/self-host/upgrading/outdated/4111](/docs/self-host/upgrading/outdated/4111)
- [/docs/self-host/upgrading/outdated/42](/docs/self-host/upgrading/outdated/42)
- [/docs/self-host/upgrading/outdated/421](/docs/self-host/upgrading/outdated/421)
- [/docs/self-host/upgrading/outdated/43](/docs/self-host/upgrading/outdated/43)
- [/docs/self-host/upgrading/outdated/44](/docs/self-host/upgrading/outdated/44)
- [/docs/self-host/upgrading/outdated/441](/docs/self-host/upgrading/outdated/441)
- [/docs/self-host/upgrading/outdated/442](/docs/self-host/upgrading/outdated/442)
- [/docs/self-host/upgrading/outdated/445](/docs/self-host/upgrading/outdated/445)
- [/docs/self-host/upgrading/outdated/446](/docs/self-host/upgrading/outdated/446)
- [/docs/self-host/upgrading/outdated/447](/docs/self-host/upgrading/outdated/447)
- [/docs/self-host/upgrading/outdated/45](/docs/self-host/upgrading/outdated/45)
- [/docs/self-host/upgrading/outdated/451](/docs/self-host/upgrading/outdated/451)
- [/docs/self-host/upgrading/outdated/452](/docs/self-host/upgrading/outdated/452)
- [/docs/self-host/upgrading/outdated/46](/docs/self-host/upgrading/outdated/46)
- [/docs/self-host/upgrading/outdated/461](/docs/self-host/upgrading/outdated/461)
- [/docs/self-host/upgrading/outdated/462](/docs/self-host/upgrading/outdated/462)
- [/docs/self-host/upgrading/outdated/463](/docs/self-host/upgrading/outdated/463)
- [/docs/self-host/upgrading/outdated/464](/docs/self-host/upgrading/outdated/464)
- [/docs/self-host/upgrading/outdated/465](/docs/self-host/upgrading/outdated/465)
- [/docs/self-host/upgrading/outdated/466](/docs/self-host/upgrading/outdated/466)
- [/docs/self-host/upgrading/outdated/467](/docs/self-host/upgrading/outdated/467)
- [/docs/self-host/upgrading/outdated/468](/docs/self-host/upgrading/outdated/468)
- [/docs/self-host/upgrading/outdated/469](/docs/self-host/upgrading/outdated/469)
- [/docs/self-host/upgrading/outdated/47](/docs/self-host/upgrading/outdated/47)
- [/docs/self-host/upgrading/outdated/471](/docs/self-host/upgrading/outdated/471)
- [/docs/self-host/upgrading/outdated/48](/docs/self-host/upgrading/outdated/48)
- [/docs/self-host/upgrading/outdated/481](/docs/self-host/upgrading/outdated/481)
- [/docs/self-host/upgrading/outdated/4810](/docs/self-host/upgrading/outdated/4810)
- [/docs/self-host/upgrading/outdated/4811](/docs/self-host/upgrading/outdated/4811)
- [/docs/self-host/upgrading/outdated/4812](/docs/self-host/upgrading/outdated/4812)
- [/docs/self-host/upgrading/outdated/4813](/docs/self-host/upgrading/outdated/4813)
- [/docs/self-host/upgrading/outdated/4814](/docs/self-host/upgrading/outdated/4814)
- [/docs/self-host/upgrading/outdated/4815](/docs/self-host/upgrading/outdated/4815)
- [/docs/self-host/upgrading/outdated/4816](/docs/self-host/upgrading/outdated/4816)
- [/docs/self-host/upgrading/outdated/4817](/docs/self-host/upgrading/outdated/4817)
- [/docs/self-host/upgrading/outdated/4818](/docs/self-host/upgrading/outdated/4818)
- [/docs/self-host/upgrading/outdated/4819](/docs/self-host/upgrading/outdated/4819)
- [/docs/self-host/upgrading/outdated/482](/docs/self-host/upgrading/outdated/482)
- [/docs/self-host/upgrading/outdated/4820](/docs/self-host/upgrading/outdated/4820)
- [/docs/self-host/upgrading/outdated/4821](/docs/self-host/upgrading/outdated/4821)
- [/docs/self-host/upgrading/outdated/4822](/docs/self-host/upgrading/outdated/4822)
- [/docs/self-host/upgrading/outdated/4823](/docs/self-host/upgrading/outdated/4823)
- [/docs/self-host/upgrading/outdated/483](/docs/self-host/upgrading/outdated/483)
- [/docs/self-host/upgrading/outdated/484](/docs/self-host/upgrading/outdated/484)
- [/docs/self-host/upgrading/outdated/485](/docs/self-host/upgrading/outdated/485)
- [/docs/self-host/upgrading/outdated/486](/docs/self-host/upgrading/outdated/486)
- [/docs/self-host/upgrading/outdated/487](/docs/self-host/upgrading/outdated/487)
- [/docs/self-host/upgrading/outdated/488](/docs/self-host/upgrading/outdated/488)
- [/docs/self-host/upgrading/outdated/489](/docs/self-host/upgrading/outdated/489)
- [/docs/self-host/upgrading/outdated/490](/docs/self-host/upgrading/outdated/490)
- [/docs/self-host/upgrading/outdated/491](/docs/self-host/upgrading/outdated/491)
- [/docs/self-host/upgrading/outdated/4910](/docs/self-host/upgrading/outdated/4910)
- [/docs/self-host/upgrading/outdated/4911](/docs/self-host/upgrading/outdated/4911)
- [/docs/self-host/upgrading/outdated/4912](/docs/self-host/upgrading/outdated/4912)
- [/docs/self-host/upgrading/outdated/4913](/docs/self-host/upgrading/outdated/4913)
- [/docs/self-host/upgrading/outdated/4914](/docs/self-host/upgrading/outdated/4914)
- [/docs/self-host/upgrading/outdated/492](/docs/self-host/upgrading/outdated/492)
- [/docs/self-host/upgrading/outdated/493](/docs/self-host/upgrading/outdated/493)
- [/docs/self-host/upgrading/outdated/494](/docs/self-host/upgrading/outdated/494)
- [/docs/self-host/upgrading/outdated/495](/docs/self-host/upgrading/outdated/495)
- [/docs/self-host/upgrading/outdated/496](/docs/self-host/upgrading/outdated/496)
- [/docs/self-host/upgrading/outdated/497](/docs/self-host/upgrading/outdated/497)
- [/docs/self-host/upgrading/outdated/498](/docs/self-host/upgrading/outdated/498)
- [/docs/self-host/upgrading/outdated/499](/docs/self-host/upgrading/outdated/499)
- [/docs/self-host/upgrading/upgrade-intruction](/docs/self-host/upgrading/upgrade-intruction)
- [/docs/use-cases/app-cases/dalle3](/docs/use-cases/app-cases/dalle3)
- [/docs/use-cases/app-cases/english_essay_correction_bot](/docs/use-cases/app-cases/english_essay_correction_bot)
- [/docs/use-cases/app-cases/feishu_webhook](/docs/use-cases/app-cases/feishu_webhook)
......
document/content/docs/upgrading/4-10/meta.en.json deleted 100644 → 0
{
"title": "4.10.x",
"description": "",
"pages": [
"4101",
"4100"
]
}
document/content/docs/upgrading/4-11/meta.en.json deleted 100644 → 0
{
"title": "4.11.x",
"description": "",
"pages": [
"4111",
"4110"
]
}
document/content/docs/upgrading/4-12/meta.en.json deleted 100644 → 0
{
"title": "4.12.x",
"description": "",
"pages": [
"4124",
"4123",
"4122",
"4121",
"4120"
]
}
document/content/docs/upgrading/4-13/meta.en.json deleted 100644 → 0
{
"title": "4.13.x",
"description": "",
"pages": [
"4132",
"4131",
"4130"
]
}
document/content/docs/upgrading/4-8/484.en.mdx deleted 100644 → 0
---
title: V4.8.4 (Includes Upgrade Script)
description: FastGPT V4.8.4 Release Notes
---
## Upgrade Guide
### 1. Update Images
- Update the fastgpt image tag to v4.8.4
- Update the fastgpt-sandbox image tag to v4.8.4 (optional, no changes)
- Update the commercial edition image tag to v4.8.4
### 2. Commercial Edition Initialization
From any terminal, send 1 HTTP request. Replace `{{rootkey}}` with the `rootkey` from your environment variables, and `{{host}}` with your **FastGPT commercial edition domain**.
```bash
curl --location --request POST 'https://{{host}}/api/admin/init/484' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
## V4.8.4 Release Notes
1. New - Apps now use the new permission system.
2. New - Apps now support folders.
3. Improved - Text splitting now removes consecutive line breaks and tabs to avoid performance issues with large text.
4. Critical Fix - Fixed system plugin runtime pool data pollution. Since data was loaded from memory, it caused global state contamination.
5. Fixed - Debug mode showing abnormal connections when source and target content are identical.
6. Fixed - Scheduled execution initialization error.
7. Fixed - App invocation parameter passing error.
8. Fixed - Incorrect nodeId when copying complex nodes with Ctrl+C/V.
9. Adjusted global theme for the component library.
document/content/docs/upgrading/4-8/484.mdx deleted 100644 → 0
---
title: V4.8.4(包含升级脚本)
description: FastGPT V4.8.4 更新说明
---
## 升级指南
### 1. 修改镜像
- fastgpt 镜像 tag 修改成 v4.8.4
- fastgpt-sandbox 镜像 tag 修改成 v4.8.4 (选择性，无变更)
- 商业版镜像 tag 修改成 v4.8.4
### 2. 商业版用户执行初始化
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 商业版的域名**。
```bash
curl --location --request POST 'https://{{host}}/api/admin/init/484' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
## V4.8.4 更新说明
1. 新增 - 应用使用新权限系统。
2. 新增 - 应用支持文件夹。
3. 优化 - 文本分割增加连续换行、制表符清除，避免大文本性能问题。
4. 重要修复 - 修复系统插件运行池数据污染问题，由于从内存获取，会导致全局污染。
5. 修复 - Debug 模式下，相同 source 和 target 内容，导致连线显示异常。
6. 修复 - 定时执行初始化错误。
7. 修复 - 应用调用传参异常。
8. 修复 - ctrl + cv 复杂节点时，nodeId错误。
9. 调整组件库全局theme。
document/content/docs/upgrading/4-8/485.en.mdx deleted 100644 → 0
---
title: V4.8.5 (Includes Upgrade Script)
description: FastGPT V4.8.5 Release Notes
---
## Upgrade Guide
### 1. Back Up Your Database
### 2. Update Images
- Update the fastgpt image tag to v4.8.5
- Update the commercial edition image tag to v4.8.5
### 3. Run Initialization
From any terminal, send 1 HTTP request. Replace `{{rootkey}}` with the `rootkey` from your environment variables, and `{{host}}` with your **FastGPT domain**.
```bash
curl --location --request POST 'https://{{host}}/api/admin/initv485' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
This will merge the plugin data table into the app table. The plugin table will not be deleted.
------
**Commercial edition users: run the additional initialization below**
From any terminal, send 1 HTTP request. Replace `{{rootkey}}` with the `rootkey` from your environment variables, and `{{host}}` with your **FastGPT domain**:
```bash
curl --location --request POST 'https://{{host}}/api/admin/init/485' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
This will reset the Knowledge Base permission system.
## V4.8.5 Release Notes
1. New - Merged plugins and apps into a unified workspace.
2. New - App duplication feature.
3. New - App template creation.
4. New - Code execution results can now be used as tool output.
5. New - Markdown image output supports pinch-to-zoom on mobile.
6. Improved - Raw file encoding for storage and retrieval.
7. Improved - Simple mode now filters out deleted Knowledge Bases to avoid false error states.
8. Improved - Folder reading now supports more than 100 files per folder.
9. Improved - QA splitting / manual entry: when an `a` field is present, the `q` field is automatically used as a supplementary index.
10. Improved - Chat dialog page code.
11. Improved - New workflow nodes are now auto-numbered.
12. Fixed - Scheduled tasks could not actually be disabled.
13. Fixed - Input guide special characters causing regex errors.
14. Fixed - Files containing unescaped `%` characters causing page crashes.
15. Fixed - Page crash when selecting Knowledge Base references in custom input.
document/content/docs/upgrading/4-8/485.mdx deleted 100644 → 0
---
title: V4.8.5(包含升级脚本)
description: FastGPT V4.8.5 更新说明
---
## 升级指南
### 1. 做好数据库备份
### 2. 修改镜像
- fastgpt 镜像 tag 修改成 v4.8.5
- 商业版镜像 tag 修改成 v4.8.5
### 3. 执行初始化
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/initv485' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
会把插件的数据表合并到应用中，插件表不会删除。
------
**商业版用户执行额外的初始化**
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/init/485' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
会重置知识库权限系统。
## V4.8.5 更新说明
1. 新增 - 合并插件和应用，统一成工作台
2. 新增 - 应用创建副本功能
3. 新增 - 应用创建模板
4. 新增 - 支持代码运行结果作为工具输出。
5. 新增 - Markdown 图片输出，支持移动端放大缩放。
6. 优化 - 原文件编码存取
7. 优化 - 知识库删除后，简易模式会过滤掉删除的知识库，避免错误判断。
8. 优化 - 文件夹读取，支持单个文件夹超出 100 个文件
9. 优化 - 问答拆分/手动录入，当有`a`字段时，自动将`q`作为补充索引。
10. 优化 - 对话框页面代码
11. 优化 - 工作流新节点自动增加序号名
12. 修复 - 定时任务无法实际关闭
13. 修复 - 输入引导特殊字符导致正则报错
14. 修复 - 文件包含特殊字符`%`，且为转义时会导致页面崩溃
15. 修复 - 自定义输入选择知识库引用时页面崩溃
document/content/docs/upgrading/4-8/486.en.mdx deleted 100644 → 0
---
title: V4.8.6 (Includes Upgrade Script)
description: FastGPT V4.8.6 Release Notes
---
## Upgrade Guide
### 1. Back Up Your Database
### 2. Update Images
- Update the fastgpt image tag to v4.8.6
- Update the fastgpt-sandbox image tag to v4.8.6
- Update the commercial edition image tag to v4.8.6
### 3. Run Initialization
From any terminal, send 1 HTTP request. Replace `{{rootkey}}` with the `rootkey` from your environment variables, and `{{host}}` with your **FastGPT domain**.
```bash
curl --location --request POST 'https://{{host}}/api/admin/initv486' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
This will initialize inherited permissions for apps.
-------
## V4.8.6 Release Notes
1. New - App permission inheritance.
2. New - Knowledge Base now supports disabling individual collections.
3. New - System plugin architecture change. Added link reader and math calculator plugins. The official release will include documentation on creating custom system plugins.
4. New - Code sandbox runtime parameters.
5. New - Option to hide the header during AI conversations, primarily for mobile optimization.
6. Improved - File reading now defaults to MongoDB secondary nodes to reduce primary node load.
7. Improved - Prompt templates.
8. Improved - Fixed duplicate Mongo model loading.
9. Fixed - Creating a link collection not returning the ID.
10. Fixed - API documentation descriptions.
11. Fixed - API system prompt merging.
12. Fixed - Content inside team plugin folders failing to load.
13. Fixed - Knowledge Base collection folder breadcrumbs failing to load.
14. Fixed - Markdown export conversation error.
15. Fixed - Prompt template closing tag error.
16. Fixed - Documentation descriptions.
document/content/docs/upgrading/4-8/486.mdx deleted 100644 → 0
---
title: V4.8.6(包含升级脚本)
description: FastGPT V4.8.6 更新说明
---
## 升级指南
### 1. 做好数据库备份
### 2. 修改镜像
- fastgpt 镜像 tag 修改成 v4.8.6
- fastgpt-sandbox 镜像 tag 修改成 v4.8.6
- 商业版镜像 tag 修改成 v4.8.6
### 3. 执行初始化
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/initv486' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
会初始化应用的继承权限
-------
## V4.8.6 更新说明
1. 新增 - 应用权限继承
2. 新增 - 知识库支持单个集合禁用功能
3. 新增 - 系统插件模式变更，新增链接读取和数学计算器插件，正式版会更新如何自定义系统插件
4. 新增 - 代码沙盒运行参数
5. 新增 - AI对话时隐藏头部的功能，主要是适配移动端
6. 优化 - 文件读取，Mongo 默认使用从节点，减轻主节点压力
7. 优化 - 提示词模板
8. 优化 - Mongo model 重复加载
9. 修复 - 创建链接集合未返回 id
10. 修复 - 文档接口说明
11. 修复 - api system 提示合并
12. 修复 - 团队插件目录内的内容无法加载
13. 修复 - 知识库集合目录面包屑无法加载
14. 修复 - Markdown 导出对话异常
15. 修复 - 提示模板结束标签错误
16. 修复 - 文档描述
document/content/docs/upgrading/4-8/487.en.mdx deleted 100644 → 0
---
title: V4.8.7
description: FastGPT V4.8.7 Release Notes
---
## Upgrade Guide
### 1. Back up your database
### 2. Update images
- Update the fastgpt image tag to v4.8.7
- Update the commercial edition image tag to v4.8.7
-------
## V4.8.7 Release Notes
1. New - Plugins now support standalone execution, publishing, and log viewing.
2. New - App search.
3. Improved - Chat dialog code.
4. Improved - Upgraded Dockerfile Node and pnpm versions.
5. Improved - Vision mode now works properly with local domain deployments.
6. Fixed - Unable to modify global variables in Simple Mode.
7. Fixed - GPT-4o unable to use tools and images simultaneously.
document/content/docs/upgrading/4-8/488.en.mdx deleted 100644 → 0
---
title: V4.8.8 (Includes Migration Script)
description: FastGPT V4.8.8 Release Notes
---
## Upgrade Guide
### 1. Back up your database
### 2. Update images
- Update the fastgpt image tag to v4.8.8-fix2
- Update the commercial edition image tag to v4.8.8
### 3. Run initialization
From any terminal, send an HTTP request. Replace `{{rootkey}}` with the `rootkey` from your environment variables, and `{{host}}` with your **FastGPT domain**.
```bash
curl --location --request POST 'https://{{host}}/api/admin/initv488' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
This will initialize inherited permissions for Knowledge Bases.
-------
## V4.8.8 Release Notes
[View full release notes](https://github.com/labring/FastGPT/releases/tag/v4.8.8)
1. New - Restructured system plugin architecture. Community members can now submit system plugins via PR. See: [How to Submit System Plugins to the FastGPT Community](https://fael3z0zfze.feishu.cn/wiki/ERZnw9R26iRRG0kXZRec6WL9nwh).
2. New - DuckDuckGo system plugin.
3. New - Lark webhook system plugin.
4. New - Revamped variable input method. Prompt input fields and all Textarea inputs in workflows now support typing `/` to trigger variable selection, allowing you to directly pick any upstream output value without dynamic imports.
5. Commercial - Knowledge Base permission inheritance.
6. Improved - Mobile quick app switching interaction.
7. Improved - Node icons.
8. Improved - Added a dedicated copy button to chat references for easier copying. Added collapsible reference content.
9. Improved - Upgraded OpenAI SDK with a custom Whisper model interface (the SDK's built-in Whisper interface doesn't seem to work well with standard FastAPI endpoints).
10. Fixed - Permission table declaration issue.
11. Fixed - Parallel execution nodes not recording run time correctly.
12. Fixed - Run details not displaying nested node information correctly.
13. Fixed - Simple Mode failing to load Knowledge Base configuration on first entry.
14. Fixed - Log debug level configuration not taking effect.
15. Fixed - When running plugins standalone, plugin input values were being variable-substituted, potentially causing downstream node variable issues.
document/content/docs/upgrading/4-8/488.mdx deleted 100644 → 0
---
title: V4.8.8(包含升级脚本)
description: FastGPT V4.8.8 更新说明
---
## 升级指南
### 1. 做好数据库备份
### 2. 修改镜像
- fastgpt 镜像 tag 修改成 v4.8.8-fix2
- 商业版镜像 tag 修改成 v4.8.8
### 3. 执行初始化
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/initv488' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
会初始化知识库的继承权限
-------
## V4.8.8 更新说明
[点击查看完整更新](https://github.com/labring/FastGPT/releases/tag/v4.8.8)
1. 新增 - 重构系统插件的结构。允许向开源社区 PR 系统插件，具体可见: [如何向 FastGPT 社区提交系统插件](https://fael3z0zfze.feishu.cn/wiki/ERZnw9R26iRRG0kXZRec6WL9nwh)。
2. 新增 - DuckDuckGo 系统插件。
3. 新增 - 飞书 webhook 系统插件。
4. 新增 - 修改变量填写方式。提示词输入框以以及工作流中所有 Textarea 输入框，支持输入 / 唤起变量选择，可直接选择所有上游输出值，无需动态引入。
5. 商业版新增 - 知识库权限继承。
6. 优化 - 移动端快速切换应用交互。
7. 优化 - 节点图标。
8. 优化 - 对话框引用增加额外复制案件，便于复制。增加引用内容折叠。
9. 优化 - OpenAI sdk 升级，并自定义了 whisper 模型接口（未仔细查看 sdk 实现，但 sdk 中 whisper 接口，似乎无法适配一般 fastapi 接口）
10. 修复 - Permission 表声明问题。
11. 修复 - 并行执行节点，运行时间未正确记录。
12. 修复 - 运行详情未正确展示嵌套节点信息。
13. 修复 - 简易模式，首次进入，无法正确获取知识库配置。
14. 修复 - Log debug level 配置无效。
15. 修复 - 插件独立运行时，会将插件输入的值进行变量替换，可能导致后续节点变量异常。
document/content/docs/upgrading/4-8/489.en.mdx deleted 100644 → 0
---
title: V4.8.9 (Requires Initialization)
description: FastGPT V4.8.9 Release Notes
---
## Upgrade Guide
### 1. Back up your database
### 2. Update images
- Update the FastGPT image tag to v4.8.9
- Update the FastGPT commercial edition image tag to v4.8.9
- Sandbox image update is optional
### 3. Run initialization (Commercial Edition)
From any terminal, send an HTTP request. Replace `{{rootkey}}` with the `rootkey` from your environment variables, and `{{host}}` with your **FastGPT domain**:
```bash
curl --location --request POST 'https://{{host}}/api/admin/init/489' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
This initializes notification methods for multi-tenancy (internal use only, no action needed).
-------
## V4.8.9 Release Notes
1. New - File upload configuration. Image upload capability is now determined by system configuration rather than relying on vision model availability.
2. New - AI chat node and tool calls support toggling "Enable image recognition". When enabled, it automatically retrieves images uploaded in the chat and image URLs from "User question".
3. New - Document parsing node.
4. Commercial - Team notification account binding for receiving important messages.
5. Commercial - Knowledge Base collection tagging for tag-based management.
6. Commercial - Knowledge Base search node supports tag filtering and creation date filtering.
7. Commercial - Transfer app owner permissions.
8. New - Delete all conversation starters.
9. New - QA splitting supports custom chunk sizes, and optimized the issue where GPT-4o-mini produced very little content with large chunks.
10. Improved - Lazy loading for chat messages to reduce network transfer.
11. Improved - Clear file selection cache to allow re-selecting the same file.
12. Fixed - Knowledge Base file upload progress not reaching 100% under unstable network or with many files.
13. Fixed - After deleting an app, returning to chat and selecting the last conversation from the deleted app showed an error.
14. Fixed - Plugin dynamic variable default values not displaying correctly.
15. Fixed - Tool call temperature and max response values not taking effect.
16. Fixed - In function call mode, GPT models require the `content` parameter in assistant role messages (doesn't affect most models since nearly all have switched to ToolChoice mode; FC mode is deprecated).
17. Fixed - Knowledge Base file upload progress updates could be incorrect.
18. Fixed - Knowledge Base page always resetting to the first page during rebuilding.
19. Fixed - Knowledge Base list OpenAPI authentication issue.
20. Fixed - Unable to provide feedback on new conversations via share links.
document/content/docs/upgrading/4-8/489.mdx deleted 100644 → 0
---
title: V4.8.9（需要初始化）
description: FastGPT V4.8.9 更新说明
---
## 升级指南
### 1. 做好数据库备份
### 2. 修改镜像
- 更新 FastGPT 镜像 tag: v4.8.9
- 更新 FastGPT 商业版镜像 tag: v4.8.9
- Sandbox 镜像，可以不更新
### 3. 商业版执行初始化
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/init/489' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
会初始化多租户的通知方式，仅内部使用的，无需执行。
-------
## V4.8.9 更新说明
1. 新增 - 文件上传配置，不再依赖视觉模型决定是否可上传图片，而是通过系统配置决定。
2. 新增 - AI 对话节点和工具调用支持选择“是否开启图片识别”，开启后会自动获取对话框上传的图片和“用户问题”中的图片链接。
3. 新增 - 文档解析节点。
4. 商业版新增 - 团队通知账号绑定，用于接收重要信息。
5. 商业版新增 - 知识库集合标签功能，可以对知识库进行标签管理。
6. 商业版新增 - 知识库搜索节点支持标签过滤和创建时间过滤。
7. 商业版新增 - 转移 App owner 权限。
8. 新增 - 删除所有对话引导内容。
9. 新增 - QA 拆分支持自定义 chunk 大小，并优化 gpt4o-mini 拆分时，chunk 太大导致生成内容很少的问题。
10. 优化 - 对话框信息懒加载，减少网络传输。
11. 优化 - 清除选文件缓存，支持重复选择同一个文件。
12. 修复 - 知识库上传文件，网络不稳定或文件较多情况下，进度无法到 100%。
13. 修复 - 删除应用后回到聊天选择最后一次对话的应用为删除的应用时提示无该应用问题。
14. 修复 - 插件动态变量配置默认值时，无法正常显示默认值。
15. 修复 - 工具调用温度和最大回复值未生效。
16. 修复 - 函数调用模式，assistant role 中，GPT 模型必须传入 content 参数。（不影响大部分模型，目前基本都改用用 ToolChoice 模式，FC 模式已弃用）。
17. 修复 - 知识库文件上传进度更新可能异常。
18. 修复 - 知识库 rebuilding 时候，页面总是刷新到第一页。
19. 修复 - 知识库 list openapi 鉴权问题。
20. 修复 - 分享链接，新对话无法反馈。
document/content/docs/upgrading/4-8/meta.en.json deleted 100644 → 0
{
"title": "<4.9.0",
"description": "",
"pages": [
"4823",
"4822",
"4821",
"4820",
"4819",
"4818",
"4817",
"4816",
"4815",
"4814",
"4813",
"4812",
"4811",
"4810",
"489",
"488",
"487",
"486",
"485",
"484",
"483",
"482",
"481",
"48",
"471",
"47",
"469",
"468",
"467",
"466",
"465",
"464",
"463",
"462",
"461",
"46",
"452",
"451",
"45",
"447",
"446",
"445",
"442",
"441",
"44",
"43",
"421",
"42",
"41",
"40"
]
}
document/content/docs/upgrading/4-8/meta.json deleted 100644 → 0
{
"title": "<4.9.0",
"description": "",
"pages": [
"4823",
"4822",
"4821",
"4820",
"4819",
"4818",
"4817",
"4816",
"4815",
"4814",
"4813",
"4812",
"4811",
"4810",
"489",
"488",
"487",
"486",
"485",
"484",
"483",
"482",
"481",
"48",
"471",
"47",
"469",
"468",
"467",
"466",
"465",
"464",
"463",
"462",
"461",
"46",
"452",
"451",
"45",
"447",
"446",
"445",
"442",
"441",
"44",
"43",
"421",
"42",
"41",
"40"
]
}
document/content/docs/upgrading/4-9/491.en.mdx deleted 100644 → 0
---
title: V4.9.1
description: FastGPT V4.9.1 Release Notes
---
## Upgrade Guide
### 1. Back Up Your Database
### 2. Update Images
- Update FastGPT image tag: v4.9.1-fix2
- Update FastGPT Pro image tag: v4.9.1-fix2
- Sandbox image: no update required
- AIProxy image changed to: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.1.3
### 3. Run the Upgrade Script
From any terminal, send an HTTP request. Replace `{{rootkey}}` with the `rootkey` from your environment variables, and `{{host}}` with your **FastGPT domain**.
```bash
curl --location --request POST 'https://{{host}}/api/admin/initv491' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
**Script Functions**
Re-processes tokenization using the latest jieba dictionary. This takes a while — you can monitor progress in the logs.
## New Features
1. Pro edition supports single-team mode for better internal member management.
2. Knowledge base chunk reader.
3. API knowledge base supports PDF enhanced parsing.
4. Team member invitations now use an invite link model.
5. Hybrid search weight configuration support.
6. Rerank model selection and weight configuration support. The knowledge base search weight calculation has been adjusted from `vector search weight + full-text search weight + rerank weight` to `search weight + rerank weight`. This may affect search results — you can adjust the relevant weights to adapt your data.
## Improvements
1. Knowledge base data input UI improvements.
2. App-bound knowledge base data fetching moved to backend processing.
3. Added dependency package security version checks and upgraded some dependencies.
4. Model testing code improvements.
5. Optimized reasoning output parsing: as long as a model is configured to support reasoning, `<think>` tags will always be parsed, even when reasoning is disabled during a conversation.
6. Loaded the latest jieba dictionary for improved full-text search tokenization.
## Bug Fixes
1. Max response tokens tooltip showing incorrect values.
2. HTTP Node failing to parse strings containing newline characters.
3. Knowledge base question optimization not passing conversation history.
4. Missing error message translations.
5. Content extraction node: incorrect schema for array types.
6. Model channel testing not actually targeting the specified channel.
7. Adding a custom model would also save default model fields, causing incorrect default model detection.
8. Prompt-mode tool calls not null-checking the reasoning chain, causing UI rendering errors.
9. Editing app info causing avatar loss.
10. Share link titles being reset on refresh.
11. Authentication failure when calculating parentPath, causing it to be cleared.
document/content/docs/upgrading/4-9/491.mdx deleted 100644 → 0
---
title: V4.9.1
description: FastGPT V4.9.1 更新说明
---
## 更新指南
### 1. 做好数据库备份
### 2. 更新镜像
- 更新 FastGPT 镜像 tag: v4.9.1-fix2
- 更新 FastGPT 商业版镜像 tag: v4.9.1-fix2
- Sandbox 镜像，可以不更新
- AIProxy 镜像修改为: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.1.3
### 3. 执行升级脚本
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/initv491' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
**脚本功能**
重新使用最新的 jieba 分词库进行分词处理。时间较长，可以从日志里查看进度。
## 🚀 新增内容
1. 商业版支持单团队模式，更好的管理内部成员。
2. 知识库分块阅读器。
3. API 知识库支持 PDF 增强解析。
4. 邀请团队成员，改为邀请链接模式。
5. 支持混合检索权重设置。
6. 支持重排模型选择和权重设置，同时调整了知识库搜索权重计算方式，改成 搜索权重 + 重排权重，而不是向量检索权重+全文检索权重+重排权重。会对检索结果有一定影响，可以通过调整相关权重来进行数据适配。
## ⚙️ 优化
1. 知识库数据输入框交互
2. 应用拉取绑定知识库数据交由后端处理。
3. 增加依赖包安全版本检测，并升级部分依赖包。
4. 模型测试代码。
5. 优化思考过程解析逻辑：只要配置了模型支持思考，均会解析 `<think>` 标签，不会因为对话时，关闭思考而不解析。
6. 载入最新 jieba 分词库，增强全文检索分词效果。
## 🐛 修复
1. 最大响应 tokens 提示显示错误的问题。
2. HTTP Node 中，字符串包含换行符时，会解析失败。
3. 知识库问题优化中，未传递历史记录。
4. 错误提示翻译缺失。
5. 内容提取节点，array 类型 schema 错误。
6. 模型渠道测试时，实际未指定渠道测试。
7. 新增自定义模型时，会把默认模型字段也保存，导致默认模型误判。
8. 修复 promp 模式工具调用，未判空思考链，导致 UI 错误展示。
9. 编辑应用信息导致头像丢失。
10. 分享链接标题会被刷新掉。
11. 计算 parentPath 时，存在鉴权失败清空。
document/content/docs/upgrading/4-9/4910.en.mdx deleted 100644 → 0
---
title: V4.9.10
description: FastGPT V4.9.10 Release Notes
---
## Upgrade Guide
Important: This update rebuilds the full-text index. During the rebuild, full-text search results will be empty. On a 4c16g instance, rebuilding approximately 7 million full-text indexes takes about 25 minutes. For a seamless upgrade, you'll need to handle table synchronization yourself.
### 1. Back Up Your Data
### 2. Update Image Tags
- Update FastGPT image tag: v4.9.10-fix2
- Update FastGPT Pro image tag: v4.9.10-fix2
- mcp_server: no update required
- Sandbox: no update required
- AIProxy: no update required
## New Features
1. Support for setting the `systemEnv.hnswMaxScanTuples` parameter in PG to increase the total data volume for iterative search.
2. Knowledge base preprocessing now includes a "Chunk Conditions" parameter to control when chunking should be skipped.
3. Knowledge base preprocessing now includes a "Paragraph Priority" mode with configurable maximum paragraph depth. The previous "Length Priority" mode no longer includes embedded paragraph priority logic.
4. Workflow adjusted to single-direction input/output connections, with quick "add next node" support.
5. Lark and Yuque knowledge bases are now available in the Community Edition.
6. Latest Gemini and Claude model presets.
## Improvements
1. Increased default timeout for LLM stream calls.
2. Various confirmation dialog UI improvements.
3. Renamed the knowledge base "Table Dataset" to "Backup Import". Also added support for exporting and importing knowledge base indexes.
4. Knowledge base citation limit in workflows: if no related AI nodes exist in the workflow, the interaction mode switches to manual input only, with a limit of 10 million.
5. Mobile voice input now accurately detects whether the device is a phone rather than just a small screen.
6. Optimized context truncation algorithm to always preserve at least one Human message.
## Bug Fixes
1. Incorrect score sorting during full-text search across multiple knowledge bases.
2. Stream response potentially capturing incorrect `finish_reason` values.
3. Tool call mode not saving reasoning output.
4. Knowledge base `indexSize` parameter not taking effect.
5. Incorrect preview citations and context after 2 levels of workflow nesting.
6. Extra leading space when converting xlsx to Markdown.
7. Base64 images in Markdown files not being extracted and saved during file reading.
document/content/docs/upgrading/4-9/4910.mdx deleted 100644 → 0
---
title: V4.9.10
description: FastGPT V4.9.10 更新说明
---
## 升级指南
重要提示：本次更新会重新构建全文索引，构建期间，全文检索结果会为空，4c16g 700 万组全文索引大致消耗 25 分钟。如需无缝升级，需自行做表同步工程。
### 1. 做好数据备份
### 2. 更新镜像 tag
- 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
## 🚀 新增内容
1. 支持 PG 设置`systemEnv.hnswMaxScanTuples`参数，提高迭代搜索的数据总量。
2. 知识库预处理参数增加 “分块条件”，可控制某些情况下不进行分块处理。
3. 知识库预处理参数增加 “段落优先” 模式，可控制最大段落深度。原“长度优先”模式，不再内嵌段落优先逻辑。
4. 工作流调整为单向接入和接出，支持快速的添加下一步节点。
5. 开放飞书和语雀知识库到社区版。
6. gemini 和 claude 最新模型预设。
## ⚙️ 优化
1. LLM stream调用，默认超时调大。
2. 部分确认交互优化。
3. 纠正原先知识库的“表格数据集”名称，改成“备份导入”。同时支持知识库索引的导出和导入。
4. 工作流知识库引用上限，如果工作流中没有相关 AI 节点，则交互模式改成纯手动输入，并且上限为 1000万。
5. 语音输入，移动端判断逻辑，准确判断是否为手机，而不是小屏。
6. 优化上下文截取算法，至少保证留下一组 Human 信息。
## 🐛 修复
1. 全文检索多知识库时排序得分排序不正确。
2. 流响应捕获 finish_reason 可能不正确。
3. 工具调用模式，未保存思考输出。
4. 知识库 indexSize 参数未生效。
5. 工作流嵌套 2 层后，获取预览引用、上下文不正确。
6. xlsx 转成 Markdown 时候，前面会多出一个空格。
7. 读取 Markdown 文件时，Base64 图片未进行额外抓换保存。
document/content/docs/upgrading/4-9/4911.en.mdx deleted 100644 → 0
---
title: V4.9.11 (Includes Upgrade Script)
description: FastGPT V4.9.11 Release Notes
---
## Upgrade Guide
### 1. Update Images:
- Update FastGPT image tag: v4.9.11
- Update FastGPT Pro image tag: v4.9.11
- mcp_server: no update required
- Update Sandbox image tag: v4.9.11
- AIProxy: no update required
### 2. Run the Upgrade Script
This script only needs to be run by Pro edition users.
From any terminal, send an HTTP request. Replace `{{rootkey}}` with the `rootkey` from your environment variables, and `{{host}}` with your **FastGPT domain**.
```bash
curl --location --request POST 'https://{{host}}/api/admin/initv4911' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
**Script Functions**
1. Migrates third-party knowledge base API configurations.
## New Features
1. Pro edition supports image knowledge bases.
2. Added node search functionality in the workflow editor.
3. Sub-workflow version control in workflows now supports a "Keep Latest Version" option — no manual updates needed.
4. Additional audit operation logs.
5. Knowledge base now has an async document parsing queue — documents can be imported without waiting for parsing to complete.
6. Third-party knowledge base development documentation. [View here](/docs/introduction/guide/knowledge_base/third_dataset/)
## Improvements
1. Raw text cache now uses GridFS storage for higher capacity.
2. Added knowledge base template import option.
## Bug Fixes
1. Admin-declared global system tools in workflows unable to be version-managed.
2. Context errors when an interactive node precedes a tool call node.
3. Backup import failing to chunk content under 1,000 characters.
4. Custom PDF parsing unable to save Base64 images.
5. Non-stream requests not performing CITE marker replacement.
6. Hidden security vulnerability in the Python sandbox.
7. Missing confirm button when importing plugins via curl.
document/content/docs/upgrading/4-9/4911.mdx deleted 100644 → 0
---
title: V4.9.11(包含升级脚本)
description: FastGPT V4.9.11 更新说明
---
## 更新指南
### 1. 更新镜像：
- 更新 FastGPT 镜像 tag: v4.9.11
- 更新 FastGPT 商业版镜像 tag: v4.9.11
- mcp_server 无需更新
- 更新 Sandbox 镜像 tag: v4.9.11
- AIProxy 无需更新
### 2. 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/initv4911' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
**脚本功能**
1. 移动第三方知识库 API 配置。
## 🚀 新增内容
1. 商业版支持图片知识库。
2. 工作流中增加节点搜索功能。
3. 工作流中，子流程版本控制，可选择“保持最新版本”，无需手动更新。
4. 增加更多审计操作日志。
5. 知识库增加文档解析异步队列，导入文档时，无需等待文档解析完毕才进行导入。
6. 第三方知识库开发文档, [点击查看](/docs/introduction/guide/knowledge_base/third_dataset/)
## ⚙️ 优化
1. 原文缓存改用 gridfs 存储，提高上限。
2. 增加知识库模板导入选项。
## 🐛 修复
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。
4. 自定义 PDF 解析，无法保存 base64 图片。
5. 非流请求，未进行 CITE 标记替换。
6. Python 沙盒存在隐藏风险。
7. curl 导入插件缺失确认按键
document/content/docs/upgrading/4-9/4912.en.mdx deleted 100644 → 0
---
title: V4.9.12
description: FastGPT V4.9.12 Release Notes
---
## Upgrade Guide
### 1. Update Environment Variables
Add the following environment variable to both the `fastgpt` and `fastgpt-pro` image configurations: `AES256_SECRET_KEY=` — used for secret key encryption.
### 2. Update Images:
- Update FastGPT image tag: v4.9.12
- Update FastGPT Pro image tag: v4.9.12
- mcp_server: no update required
- Sandbox: no update required
- Update AIProxy image tag: v0.2.2
## New Features
1. Enhanced AI Proxy monitoring with chart and table views for model call and performance metrics.
2. HTTP nodes and MCP now support separate "Auth Configuration" — plaintext credentials are never sent back to the client, ensuring data security.
3. Question classification and content extraction now automatically include the previous round's results in the prompt for additional guidance.
4. Conditional node now supports variable references.
5. Pro edition supports LLM-based automatic segment detection during knowledge base chunking.
6. Admin dashboard with data analytics.
7. Doubao 1.6 series models and updated Qwen model configurations.
## Improvements
1. Password validation now accepts more special characters.
2. Backend now fully computes knowledge base chunk parameters to prevent default values from being incorrectly applied in auto mode.
3. Text chunking moved to a worker thread to avoid blocking.
4. More subscription plan usage information displayed.
5. Input box styling improvements, with updated voice input UI for both desktop and mobile.
6. MCP tool calls now use raw schema for invocation to ensure completeness.
7. Deleting knowledge base files no longer fails if the file doesn't exist.
8. Upgraded MCP SDK with compatibility for the latest HTTP Streamable protocol.
9. Yuque document library now recursively fetches data from document-type directories.
## Bug Fixes
1. Custom QA extraction prompts being overwritten.
2. Template import failing when empty indexes exist in the data.
3. Potential XSS vulnerability on the login page.
4. Voice input in the text box causing the file list to be lost.
5. Image TTL field not being cleared in knowledge base documents, causing images to expire.
6. MCP tool storage not escaping integer type data.
document/content/docs/upgrading/4-9/4912.mdx deleted 100644 → 0
---
title: V4.9.12
description: FastGPT V4.9.12 更新说明
---
## 更新指南
### 1. 更新环境变量
在 `fastgpt`和`fastgpt-pro`镜像环境变量中加入: `AES256_SECRET_KEY=` 变量，用于密钥加密。
### 2. 更新镜像：
- 更新 FastGPT 镜像 tag: v4.9.12
- 更新 FastGPT 商业版镜像 tag: v4.9.12
- mcp_server 无需更新
- Sandbox 无需更新
- 更新 AIProxy 镜像 tag: v0.2.2
## 🚀 新增内容
1. AI proxy 监控完善，支持以图表/表格形式查看模型调用和性能情况。
2. HTTP 节点和 MCP 支持单独“鉴权配置”，鉴权配置明文不会二次返回客户端，以保障数据安全。
3. 问题分类和内容提取，提示词中自动加入上一轮结果进行额外引导。
4. 判断器支持变量引用。
5. 商业版支持知识库分块时，LLM 进行自动分段识别。
6. Admin 管理员数据看板。
7. 豆包 1.6 系列模型，更新 qwen 模型配置。
## ⚙️ 优化
1. 密码校验时，增加更多的特殊字符
2. 后端全量计算知识库 chunk 参数，避免自动模式下部分参数未正确使用默认值。
3. 将文本分块移至 worker 线程，避免阻塞。
4. 展示更多套餐用量信息。
5. 优化输入框样式，桌面和移动端的语音输入样式更新。
6. MCP 工具调用，使用 Raw schema 进行工具调用，保障完整性。
7. 删除知识库文件时，如果文件不存在，不会阻断删除。
8. 升级 MCP SDK，兼容最新的 HTTPStreamable。
9. 语雀文档库，递归获取文档类型目录下的数据。
## 🐛 修复
1. 自定义问答提取提示词被覆盖。
2. 模板导入时，存在空 indexes 时，导致数据插入失败。
3. 登录页可能存在的 XSS 攻击。
4. 输入框语音输入时候会丢失文件列表的问题。
5. 知识库文档中图片 TTL 字段未清除，导致图片过期。
6. MCP 工具存储时，未转义 int 类型数据。
document/content/docs/upgrading/4-9/4913.en.mdx deleted 100644 → 0
---
title: V4.9.13
description: FastGPT V4.9.13 Release Notes
---
## Upgrade Guide
### 1. Update Images:
- Update FastGPT image tag: v4.9.13
- Update FastGPT Pro image tag: v4.9.13
- mcp_server: no update required
- Sandbox: no update required
- AIProxy: no update required
## New Features
1. Subscription plan caching to reduce MongoDB query frequency.
## Improvements
1. All NodeId random value generation adjusted to avoid starting with a digit.
2. Knowledge base collection search now supports nested search.
## Bug Fixes
1. Chat log date range selection issues.
2. System prompt potentially being duplicated when passed via API calls.
3. AI chat/tool calls reading files from history even when no file link was selected.
4. Manually updating knowledge base indexes incorrectly deleting old indexes, causing manual indexes to become ineffective.
document/content/docs/upgrading/4-9/4913.mdx deleted 100644 → 0
---
title: V4.9.13
description: FastGPT V4.9.13 更新说明
---
## 更新指南
### 1. 更新镜像：
- 更新 FastGPT 镜像 tag: v4.9.13
- 更新 FastGPT 商业版镜像 tag: v4.9.13
- mcp_server 无需更新
- Sandbox 无需更新
- AIProxy 无需更新
## 🚀 新增内容
1. 套餐缓存，减少 MongoDB 查询次数。
## ⚙️ 优化
1. 所有 NodeId 调整随机值生成，避免首字母数字开头。
2. 知识库集合搜索，支持嵌套搜索。
## 🐛 修复
1. 对话日志，日期范围选择问题。
2. API 调用时，传入的 system 提示词可能会重复。
3. AI 对话/工具调用，未选择文件链接时，也会从历史记录读取文件。
4. 手动更新知识库索引时，错误的删除旧索引，导致手动索引无效。
document/content/docs/upgrading/4-9/4914.en.mdx deleted 100644 → 0
---
title: V4.9.14
description: FastGPT V4.9.14 Release Notes
---
## Upgrade Guide
### 1. Update Images:
- Update FastGPT image tag: v4.9.14
- Update FastGPT Pro image tag: v4.9.14
- mcp_server: no update required
- Sandbox: no update required
- AIProxy: no update required
## New Features
1. Knowledge base import now supports automatically adding the filename to the system index.
2. Admin-side audit logs.
## Improvements
1. Unified knowledge base training queue code logic.
2. Input box UX improvements.
3. Image knowledge base now automatically removes line breaks from descriptions to prevent model output line breaks from breaking image display.
4. Image indexing now generates separate image content descriptions, and attaches them to search results after retrieval — enabling LLMs to understand image content.
5. Auto-completion for MCP Schema entries missing the `properties` field to prevent errors with certain models.
6. Error handling for potential JSON import template failures.
7. Dangerous characters filtered during CSV export.
8. Added security request headers.
9. Changing password now invalidates all other active sessions.
10. Citation display optimization: detects preceding URLs and automatically adds spacing.
## Bug Fixes
1. Knowledge base data input incorrectly detecting QA mode.
2. Knowledge base tag condition conflicts.
3. Chat log like/dislike statistics.
document/content/docs/upgrading/4-9/4914.mdx deleted 100644 → 0
---
title: V4.9.14
description: FastGPT V4.9.14 更新说明
---
## 更新指南
### 1. 更新镜像：
- 更新 FastGPT 镜像 tag: v4.9.14
- 更新 FastGPT 商业版镜像 tag: v4.9.14
- mcp_server 无需更新
- Sandbox 无需更新
- AIProxy 无需更新
## 🚀 新增内容
1. 知识库导入，支持配置：自动将文件名加入系统索引中。
2. Admin 端审计日志。
## ⚙️ 优化
1. 统一知识库训练队列代码逻辑。
2. 输入框 UX。
3. 图片知识库自动去除介绍中的换行，避免模型输出换行导致无法显示图片。
4. 图片索引过程会单独描述图片内容，并在检索后会将图片描述赋予检索结果，使语言模型也可以对图片进行理解。
5. 对于 MCP Schema 中，缺少`properties`属性的值，进行自动补全，避免部分模型报错。
6. 对 JSON 导入模板可能的报错进行捕获。
7. 过滤 CSV 导出时可能存在的危险字符串。
8. 添加安全请求头。
9. 修改密码，强制其他登录端失效。
10. Cite 引用展示优化，识别前置的 url 并自动加空格。
## 🐛 修复
1. 知识库数据输入，识别 QA 模式错误。
2. 知识库标签条件冲突。
3. 对话日志点赞点踩统计。
document/content/docs/upgrading/4-9/492.en.mdx deleted 100644 → 0
---
title: V4.9.2
description: FastGPT V4.9.2 Release Notes
---
## Upgrade Guide
You can skip directly to v4.9.3 — v4.9.2 has a workflow data type conversion bug.
### 1. Back Up Your Database
### 2. SSO Migration
Pro edition users using SSO or member sync with DingTalk or WeCom need to migrate their existing SSO configuration:
Refer to [SSO & External Member Sync](/docs/introduction/guide/admin/sso) for deploying and configuring the `sso-service`.
1. Before upgrading images, copy and back up the existing configuration from the Pro admin panel (e.g., for WeCom, copy the AppId, Secret, etc.).
2. Follow the documentation above to deploy the SSO service and configure the relevant environment variables.
3. If you were previously using WeCom org structure sync, after upgrading, switch the team mode to "Sync Mode" in the Pro admin panel.
### 3. Configuration Parameter Changes
Rename the `systemEnv.pgHNSWEfSearch` parameter in your `config.json` file to `hnswEfSearch`.
Pro edition users can make this change in the admin panel under `System Configuration - Basic Settings` after upgrading.
### 4. Update Images
- Update FastGPT image tag: v4.9.2
- Update FastGPT Pro image tag: v4.9.2
- Sandbox image: no update required
- AIProxy image changed to: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.1.4
## Important Updates
- Knowledge base data import API changes: added optional parameters `chunkSettingMode`, `chunkSplitMode`, and `indexSize`. See the [Knowledge Base Data Import API](/docs/openapi/dataset) documentation for details.
## New Features
1. Knowledge base chunking optimization: supports separate configuration for chunk size and index size, allowing extra-large chunks that trade higher input tokens for complete chunks.
2. Knowledge base chunking now includes custom separator presets and supports custom newline-based splitting.
3. External variables renamed to Custom Variables. Now supports debugging during testing, and the variable is hidden in share links.
4. Collection sync now supports syncing title changes.
5. Team member management overhaul: extracted mainstream IM SSO (WeCom, Lark, DingTalk) and added support for connecting to FastGPT via custom SSO. Also improved member sync with external systems.
6. Support for `oceanbase` vector database. Set the `OCEANBASE_URL` environment variable to enable.
7. PDF parsing example based on mistral-ocr.
8. PDF parsing example based on miner-u.
## Improvements
1. Chat log export now includes member names.
2. Invite link UI improvements.
3. When SSL certificate is unavailable and copy fails, a dialog is shown for manual copying.
4. FastGPT now properly displays AI Proxy channel names even when channels are not built in.
5. Upgraded Next.js to version 14.2.25.
6. Workflow node array-string type now auto-adapts to string input.
7. Workflow node array type now automatically JSON-parses string input.
8. AI Proxy log optimization: removed retry failure logs, keeping only the final error log.
9. Personal info and notification display improvements.
10. Model testing loading animation improvements.
11. Minor chunking algorithm adjustments:
- Stronger continuity between cross-processing symbols.
- Code blocks now use the LLM model context as chunk size to better preserve code block integrity.
- Tables now use the LLM model context as chunk size to better preserve table integrity.
## Bug Fixes
1. Lark and Yuque knowledge bases unable to sync.
2. Channel testing using the custom request URL instead of the channel request URL when a custom URL was configured.
3. Speech recognition model testing unable to test disabled models.
4. Admin-configured system plugins failing authentication when the plugin contains other system apps.
5. Removing TTS custom request URL requiring the requestAuth field to be filled.
document/content/docs/upgrading/4-9/492.mdx deleted 100644 → 0
---
title: V4.9.2
description: FastGPT V4.9.2 更新说明
---
## 更新指南
可直接升级v4.9.3，v4.9.2存在一个工作流数据类型转化错误。
### 1. 做好数据库备份
### 2. SSO 迁移
使用了 SSO 或成员同步的商业版用户，并且是对接`钉钉`、`企微`的，需要迁移已有的 SSO 相关配置:
参考：[SSO & 外部成员同步](/docs/introduction/guide/admin/sso)中的配置进行`sso-service`的部署和配置。
1. 先将原商业版后台中的相关配置项复制备份出来（以企微为例，将 AppId, Secret 等复制出来）再进行镜像升级。
2. 参考上述文档，部署 SSO 服务，配置相关的环境变量
3. 如果原先使用企微组织架构同步的用户，升级完镜像后，需要在商业版后台切换团队模式为“同步模式”
### 3. 配置参数变更
修改`config.json`文件中`systemEnv.pgHNSWEfSearch`参数名，改成`hnswEfSearch`。
商业版用户升级镜像后，直接在后台`系统配置-基础配置`中进行变更。
### 4. 更新镜像
- 更新 FastGPT 镜像 tag: v4.9.2
- 更新 FastGPT 商业版镜像 tag: v4.9.2
- Sandbox 镜像，可以不更新
- AIProxy 镜像修改为: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.1.4
## 重要更新
- 知识库导入数据 API 变更，增加`chunkSettingMode`,`chunkSplitMode`,`indexSize`可选参数，具体可参考 [知识库导入数据 API](/docs/openapi/dataset) 文档。
## 🚀 新增内容
1. 知识库分块优化：支持单独配置分块大小和索引大小，允许进行超大分块，以更大的输入 Tokens 换取完整分块。
2. 知识库分块增加自定义分隔符预设值，同时支持自定义换行符分割。
3. 外部变量改名：自定义变量。 并且支持在测试时调试，在分享链接中，该变量直接隐藏。
4. 集合同步时，支持同步修改标题。
5. 团队成员管理重构，抽离主流 IM SSO（企微、飞书、钉钉），并支持通过自定义 SSO 接入 FastGPT。同时完善与外部系统的成员同步。
6. 支持 `oceanbase` 向量数据库。填写环境变量`OCEANBASE_URL`即可。
7. 基于 mistral-ocr 的 PDF 解析示例。
8. 基于 miner-u 的 PDF 解析示例。
## ⚙️ 优化
1. 导出对话日志时，支持导出成员名。
2. 邀请链接交互。
3. 无 SSL 证书时复制失败，会提示弹窗用于手动复制。
4. FastGPT 未内置 ai proxy 渠道时，也能正常展示其名称。
5. 升级 nextjs 版本至 14.2.25。
6. 工作流节点数组字符串类型，自动适配 string 输入。
7. 工作流节点数组类型，自动进行 JSON parse 解析 string 输入。
8. AI proxy 日志优化，去除重试失败的日志，仅保留最后一份错误日志。
9. 个人信息和通知展示优化。
10. 模型测试 loading 动画优化。
11. 分块算法小调整：
- 跨处理符号之间连续性更强。
- 代码块分割时，用 LLM 模型上下文作为分块大小，尽可能保证代码块完整性。
- 表格分割时，用 LLM 模型上下文作为分块大小，尽可能保证表格完整性。
## 🐛 修复
1. 飞书和语雀知识库无法同步。
2. 渠道测试时，如果配置了模型自定义请求地址，会走自定义请求地址，而不是渠道请求地址。
3. 语音识别模型测试未启用的模型时，无法正常测试。
4. 管理员配置系统插件时，如果插件包含其他系统应用，无法正常鉴权。
5. 移除 TTS 自定义请求地址时，必须需要填 requestAuth 字段。
document/content/docs/upgrading/4-9/494.en.mdx deleted 100644 → 0
---
title: V4.9.4
description: FastGPT V4.9.4 Release Notes
---
## Upgrade Guide
### 1. Back Up Your Data
### 2. Install Redis
* For Docker deployments, refer to the latest `docker-compose.yml` file to add Redis configuration. Add a Redis container and configure the `REDIS_URL` environment variable for both `fastgpt` and `fastgpt-pro`.
* For Sealos deployments, create a new `redis` database in the Database section, copy the `internal connection` URL as the Redis connection string, then configure the `REDIS_URL` environment variable for both `fastgpt` and `fastgpt-pro`.
| | | |
| --- | --- | --- |
| ![](/imgs/sealos-redis1.png) | ![](/imgs/sealos-redis2.png) | ![](/imgs/sealos-redis3.png) |
### 3. Update Image Tags
- Update FastGPT image tag: v4.9.4
- Update FastGPT Pro image tag: v4.9.4
- Sandbox: no update required
- AIProxy: no update required
### 4. Run the Upgrade Script
This script only needs to be run by Pro edition users.
From any terminal, send an HTTP request. Replace `{{rootkey}}` with the `rootkey` from your environment variables, and `{{host}}` with your **FastGPT domain**:
```bash
curl --location --request POST 'https://{{host}}/api/admin/initv494' \
--header 'rootkey: {{rootkey}}' \
--header 'Content-Type: application/json'
```
**Script Functions**
1. Updates the site sync scheduler.
## New Features
1. Collection data training status display.
2. SMTP email sending plugin.
3. BullMQ message queue.
4. Partial data caching via Redis.
5. Site sync now supports configuring training parameters and incremental sync.
6. AI chat/tool calls now return the model's `finish_reason` field for easier tracking of output interruption causes.
7. Mobile voice input UI adjustments.
## Improvements
1. Admin template rendering adjustments.
2. Chat file expiration time now configurable via environment variable.
3. MongoDB log database can now be deployed independently.
## Bug Fixes
1. Unable to click into subdirectories when searching apps/knowledge bases.
2. Retraining parameters not properly initialized.
3. Inconsistent requests in package/service across multiple apps.
document/content/docs/upgrading/4-9/494.mdx deleted 100644 → 0
---
title: V4.9.4
description: FastGPT V4.9.4 更新说明
---
## 升级指南
### 1. 做好数据备份
### 2. 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) |
### 3. 更新镜像 tag
- 更新 FastGPT 镜像 tag: v4.9.4
- 更新 FastGPT 商业版镜像 tag: v4.9.4
- Sandbox 无需更新
- AIProxy 无需更新
### 4. 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. 利用 redis 进行部分数据缓存。
5. 站点同步支持配置训练参数和增量同步。
6. AI 对话/工具调用，增加返回模型 finish_reason 字段，便于追踪模型输出中断原因。
7. 移动端语音输入交互调整
## ⚙️ 优化
1. Admin 模板渲染调整。
2. 支持环境变量配置对话文件过期时间。
3. MongoDB log 库可独立部署。
## 🐛 修复
1. 搜索应用/知识库时，无法点击目录进入下一层。
2. 重新训练时，参数未成功初始化。
3. package/service 部分请求在多 app 中不一致。
document/content/docs/upgrading/4-9/495.en.mdx deleted 100644 → 0
---
title: V4.9.5
description: FastGPT V4.9.5 Release Notes
---
## Upgrade Guide
### 1. Back Up Your Data
### 2. Update Image Tags
- Update FastGPT image tag: v4.9.5
- Update FastGPT Pro image tag: v4.9.5
- Sandbox: no update required
- AIProxy: no update required
## New Features
1. Granular team member permissions: separately control whether members can create root-level apps/knowledge bases and API keys.
2. Interactive nodes now work inside nested workflows.
3. Team member operation audit logs.
4. User input node now supports checkboxes.
## Improvements
1. Traditional Chinese translation updates.
2. ARM image builds.
## Bug Fixes
1. Incorrect password validation rules.
2. Share links unable to hide knowledge base search results.
3. Regex compatibility issues on older iOS versions.
4. QA extraction queue counter not resetting after errors, causing the queue to stop working.
5. Debug mode interactive nodes potentially causing infinite loops on next step.
document/content/docs/upgrading/4-9/495.mdx deleted 100644 → 0
---
title: V4.9.5
description: FastGPT V4.9.5 更新说明
---
## 升级指南
### 1. 做好数据备份
### 2. 更新镜像 tag
- 更新 FastGPT 镜像 tag: v4.9.5
- 更新 FastGPT 商业版镜像 tag: v4.9.5
- Sandbox 无需更新
- AIProxy 无需更新
## 🚀 新增内容
1. 团队成员权限细分，可分别控制是否可创建在根目录应用/知识库以及 API Key
2. 支持交互节点在嵌套工作流中使用。
3. 团队成员操作日志。
4. 用户输入节点支持多选框。
## ⚙️ 优化
1. 繁体中文翻译。
2. Arm 镜像打包
## 🐛 修复
1. password 检测规则错误。
2. 分享链接无法隐藏知识库检索结果。
3. IOS 低版本正则兼容问题。
4. 修复问答提取队列错误后，计数器未清零问题，导致问答提取队列失效。
5. Debug 模式交互节点下一步可能造成死循环。
document/content/docs/upgrading/4-9/496.en.mdx deleted 100644 → 0
---
title: V4.9.6
description: FastGPT V4.9.6 Release Notes
---
## New Features
1. Apps can now be called externally via MCP.
2. Support for creating tools using the MCP SSE protocol.
3. Batch execution node now supports interactive nodes, enabling human participation in each loop iteration.
4. Added workspace secondary menu with merged toolbox.
5. Added system configurations for grok3, GPT4.1, o-series, and Gemini 2.5 models.
## Improvements
1. Enhanced workflow data type conversion robustness and compatibility.
2. Python sandbox code now supports large data inputs.
3. Breadcrumb component now supports configuring whether the last step is clickable.
4. Knowledge base tool call results now automatically prepend image domain names.
5. GitHub Action runner upgraded to Ubuntu 24.
6. Removed extra leading/trailing newlines when replying via Lark, WeChat Official Account, and other third-party channels.
7. Adjusted chunking strategy: large tables are now split into independent chunks instead of being merged into oversized blocks.
8. Iframe embed component now includes built-in microphone permission declaration.
## Bug Fixes
1. Sub-workflows with interactive nodes not fully restoring all sub-workflow data.
2. Completion v1 API not accepting the `interactive` parameter, causing API call failures.
3. Consecutive tool calls causing abnormal context truncation.
## Upgrade Guide
### 1. Back Up Your Data
### 2. Deploy the MCP Server Service
#### Docker Deployment
Add the `fastgpt-mcp-server` service to your `docker-compose.yml` file:
```yml
fastgpt-mcp-server:
container_name: fastgpt-mcp-server
image: ghcr.io/labring/fastgpt-mcp_server:v4.9.6
ports:
- 3005:3000
networks:
- fastgpt
restart: always
environment:
- FASTGPT_ENDPOINT=http://fastgpt:3000
```
#### Sealos Deployment
In `App Management`, add a new `fastgpt-mcp-server` app with the image `ghcr.io/labring/fastgpt-mcp_server:v4.9.6` and set the environment variable `FASTGPT_ENDPOINT=<your FastGPT access URL>`.
### 3. Update FastGPT Container Environment Variables
#### Community Edition
Add the following to your `config.json` configuration file: `"feconfigs.mcpServerProxyEndpoint": "<fastgpt-mcp-server access URL>"` (no trailing slash). For example:
```json
{
"feConfigs": {
"lafEnv": "https://laf.dev",
"mcpServerProxyEndpoint": "https://mcp.fastgpt.cn"
}
}
```
#### Pro Edition
In the Admin panel, go to `System Configuration - Basic Settings - System Parameters` and set the `MCP Proxy Server URL` to the public access URL of your `fastgpt-mcp-server`.
### 4. Update Image Tags
- Update FastGPT image tag: v4.9.6
- Update FastGPT Pro image tag: v4.9.6
- Update Sandbox image tag: v4.9.6
- Add FastGPT MCP Server image tag: v4.9.6
- AIProxy: no update required
document/content/docs/upgrading/4-9/496.mdx deleted 100644 → 0
---
title: V4.9.6
description: FastGPT V4.9.6 更新说明
---
## 🚀 新增内容
1. 以 MCP 方式对外提供应用调用。
2. 支持以 MCP SSE 协议创建工具。
3. 批量执行节点支持交互节点，可实现每一轮循环都人工参与。
4. 增加工作台二级菜单，合并工具箱。
5. 增加 grok3、GPT4.1、o系列、Gemini2.5 模型系统配置。
## ⚙️ 优化
1. 工作流数据类型转化鲁棒性和兼容性增强。
2. Python sandbox 代码，支持大数据输入。
3. 路径组件支持配置最后一步是否可点击。
4. 知识库工具调用结果，自动补充图片域名。
5. Github action runner 升级成 unbuntu24
6. 去除飞书、公众号等三方渠道，回复时，可能前后多一个换行的问题。
7. 调整分块策略，大表格时，不进行超大块合并，而是独立拆块。
8. Iframe 嵌套组件，内置允许麦克风声明。
## 🐛 修复
1. 修复子工作流包含交互节点时，未成功恢复子工作流所有数据。
2. completion v1 接口，未接受 interactive 参数，导致 API 调用失败。
3. 连续工具调用，上下文截断异常
## 升级指南
### 1. 做好数据备份
### 2. 部署 MCP server 服务
#### Docker 部署
在`docker-compose.yml`文件中，加入`fastgpt-mcp-server`服务:
```yml
fastgpt-mcp-server:
container_name: fastgpt-mcp-server
image: ghcr.io/labring/fastgpt-mcp_server:v4.9.6
ports:
- 3005:3000
networks:
- fastgpt
restart: always
environment:
- FASTGPT_ENDPOINT=http://fastgpt:3000
```
#### Sealos 部署
直接在`应用管理`中，增加一个`fastgpt-mcp-server`应用，镜像为`ghcr.io/labring/fastgpt-mcp_server:v4.9.6`，并设置环境变量`FASTGPT_ENDPOINT=fastgpt 的访问地址`。
### 3. 修改 FastGPT 容器环境变量
#### 社区版
修改`config.json`配置文件，增加: `"feconfigs.mcpServerProxyEndpoint": "fastgpt-mcp-server 的访问地址"`， 末尾不要携带/，例如:
```json
{
"feConfigs": {
"lafEnv": "https://laf.dev",
"mcpServerProxyEndpoint": "https://mcp.fastgpt.cn"
}
}
```
#### 商业版
在 Admin 后台，`系统配置-基础配置-系统参数`中的`MCP 转发服务地址`中，设置`fastgpt-mcp-server`的公网访问地址。
### 4. 更新镜像 tag
- 更新 FastGPT 镜像 tag: v4.9.6
- 更新 FastGPT 商业版镜像 tag: v4.9.6
- 更新 Sandbox 镜像 tag: v4.9.6
- 增加 FastGPT mcp server 镜像 tag: v4.9.6
- AIProxy 无需更新
document/content/docs/upgrading/4-9/497.en.mdx deleted 100644 → 0
---
title: V4.9.7
description: FastGPT V4.9.7 Release Notes
---
## Upgrade Guide
### 1. Back Up Your Data
### 2. Update Image Tags
- Update FastGPT image tag: v4.9.7-fix2
- Update FastGPT Pro image tag: v4.9.7
- mcp_server: no update required
- Sandbox: no update required
- Update AIProxy image tag: v0.1.8
## New Features
1. Knowledge base answers now include citations at the end of each referenced paragraph.
2. MCP tools support the HTTP Streamable protocol.
3. MCP Server supports editing tool names to accommodate clients that don't support Chinese characters.
4. Right-click in the workflow editor to auto-align nodes.
5. Support for custom `config.json` path in production environments.
6. API calls support passing a special chatId (`NO_RECORD_HISTORIES`) to prevent the system from storing conversation history.
7. Rerank model usage-based billing support.
8. Subscription plan redemption codes.
9. Alipay payment support.
10. Short link analytics tracking.
11. Added Jina AI model system configuration.
## Improvements
1. Doc2x document parsing: added error message capture and increased timeout duration.
2. Adjusted PG vector query to force vector index usage.
3. Conversation time statistics now accurately return the overall workflow execution time.
4. Audio parsing duration now retrieved from ai_proxy.
5. AI model token counts now prioritize the API usage values for accuracy. If unavailable, falls back to GPT-3.5 estimation.
6. Optimized the chat log list API to handle scenarios with large numbers of messages in a single conversation.
## Bug Fixes
1. File upload chunk size limit to prevent exceeding MongoDB limits.
2. Usage dashboard unable to retrieve statistics for specific members.
3. Dashboard API returning incorrect statistics due to timezone handling issues.
4. LLM model test API unable to test disabled models. Also fixed the issue where model testing would strip custom request URLs.
5. Copy app permission issues.
6. Chat record export now limits individual conversations to 1,000 message pairs to prevent export failures.
7. Workflow variables followed by another workflow variable not triggering rendering.
8. Debugging the knowledge base search module showing "no permission" errors.
9. Text content extraction node default value assignment logic.
10. Share links forcibly returning citation content from nested apps.
11. Knowledge base collection metadata filtering: same-named tags across different knowledge bases returning no results when using `$and` filters.
12. App list permission configuration potentially causing index refresh issues.
document/content/docs/upgrading/4-9/497.mdx deleted 100644 → 0
---
title: V4.9.7
description: FastGPT V4.9.7 更新说明
---
## 升级指南
### 1. 做好数据备份
### 2. 更新镜像 tag
- 更新 FastGPT 镜像 tag: v4.9.7-fix2
- 更新 FastGPT 商业版镜像 tag: v4.9.7
- mcp_server 无需更新
- Sandbox 无需更新
- 更新 AIProxy 镜像 tag: v0.1.8
## 🚀 新增内容
1. 知识库回答时，回答段落末尾增加引用。
2. MCP 工具支持 HTTP Streamable 协议。
3. MCP server 支持编辑工具名，适配部分客户端不支持中文名问题。
4. 工作流右键可自动对齐节点。
5. 支持生产环境自定义`config.json`路径。
6. API 调用，支持传递一个特殊 chatId(`NO_RECORD_HISTORIES`)，使得系统不会进行历史记录存储。
7. 支持 Rerank 模型按量计费。
8. 套餐兑换码功能。
9. 支付宝支付。
10. 短链数据埋点。
11. 新增 Jina AI 模型系统配置。
## ⚙️ 优化
1. Doc2x 文档解析，增加报错信息捕获，增加超时时长。
2. 调整 PG vector 查询语句，强制使用向量索引。
3. 对话时间统计，准确返回工作流整体运行时间。
4. 从 ai_proxy 获取音频解析时长。
5. AI 模型 Token 值均优先采用 API usage，确保 tokens 值准确，若为空，则再采用 GPT3.5 的估算方式。
6. 优化对话日志 list 接口，适配单个对话框，大量对话的场景。
## 🐛 修复
1. 文件上传分块大小限制，避免超出 MongoDB 限制。
2. 使用记录仪表盘，无法获取指定成员的使用统计。
3. 仪表盘接口，因未考虑时区问题，统计异常。
4. LLM 模型测试接口，无法测试未启用的 LLM。同时修复，模型测试接口会把模型自定义请求地址去除问题。
5. Copy app 权限问题。
6. 导出对话记录，限制单条对话记录消息上限 1000 组，避免导出失败。
7. 工作流变量下一段文本仍是工作流变量，不触发渲染。
8. 调试知识库检索模块，提示无权操作知识库。
9. 文本内容提取节点，默认值赋值逻辑。
10. 分享链接中，会强制返回嵌套应用中的引用内容。
11. 知识库集合元数据过滤时，不同知识库的同名标签使用 $and 筛选无法获取结果。
12. 修复应用列表，权限配置可能出现 index 刷新问题。
document/content/docs/upgrading/4-9/498.en.mdx deleted 100644 → 0
---
title: V4.9.8
description: FastGPT V4.9.8 Release Notes
---
## Upgrade Guide
### 1. Back Up Your Data
### 2. Update Image Tags
- Update FastGPT image tag: v4.9.8
- Update FastGPT Pro image tag: v4.9.8
- mcp_server: no update required
- Sandbox: no update required
- AIProxy: no update required
## New Features
1. Support for parallel tool call execution.
2. All built-in tasks switched from non-stream mode to stream mode to avoid compatibility issues with models that don't support non-stream mode. To override, you can force `stream=false` in the model's `Extra Body` parameters.
3. Qwen3 model presets.
4. Yuque knowledge base now supports setting a root directory.
5. Configurable password expiration — users will be forced to change their password on next login after expiration.
6. Password login now includes preLogin temporary key verification.
7. Admin panel now supports configuring visibility of publishing channels and third-party knowledge bases.
## Improvements
1. Chat log list optimization to prevent memory overflow with large datasets.
2. Token calculation worker is now preloaded to prevent thread blocking from concurrent creation during main tasks.
3. Workflow node version control UI improvements.
4. Web fetch and html2md optimization: now supports video and audio tag conversion.
## Bug Fixes
1. App list / knowledge base list: incorrect permission display for delete row actions.
2. Opening knowledge base search parameters automatically enabling the rerank option.
3. Incorrect API request format for LLM json_schema mode.
4. Expired image indexes not properly cleared during retraining, causing image loss.
5. Retraining permission issues.
6. Documentation link URLs.
7. Claude tool calls failing due to empty index values.
8. Nested workflows with interactive nodes inside tool calls causing abnormal flow behavior.
document/content/docs/upgrading/4-9/498.mdx deleted 100644 → 0
---
title: V4.9.8
description: FastGPT V4.9.8 更新说明
---
## 升级指南
### 1. 做好数据备份
### 2. 更新镜像 tag
- 更新 FastGPT 镜像 tag: v4.9.8
- 更新 FastGPT 商业版镜像 tag: v4.9.8
- mcp_server 无需更新
- Sandbox 无需更新
- AIProxy 无需更新
## 🚀 新增内容
1. 支持 Toolcalls 并行执行。
2. 将所有内置任务，从非 stream 模式调整成 stream 模式，避免部分模型不支持非 stream 模式。如需覆盖，则可以在模型`额外 Body`参数中，强制指定`stream=false`。
3. qwen3 模型预设
4. 语雀知识库支持设置根目录。
5. 可配置密码过期时间，过期后下次登录会强制要求修改密码。
6. 密码登录增加 preLogin 临时密钥校验。
7. 支持 Admin 后台配置发布渠道和第三方知识库的显示隐藏。
## ⚙️ 优化
1. Chat log list 优化，避免大数据时超出内存限制。
2. 预加载 token 计算 worker，避免主任务中并发创建导致线程阻塞。
3. 工作流节点版本控制交互优化。
4. 网络获取以及 html2md 优化，支持视频和音频标签的转换。
## 🐛 修复
1. 应用列表/知识库列表，删除行权限展示问题。
2. 打开知识库搜索参数后，重排选项自动被打开。
3. LLM json_schema 模式 API 请求格式错误。
4. 重新训练时，图片过期索引未成功清除，导致图片会丢失。
5. 重新训练权限问题。
6. 文档链接地址。
7. Claude 工具调用，由于 index 为空，导致工具调用失败。
8. 嵌套工作流，工具调用下包含交互节点时，流程异常。
document/content/docs/upgrading/4-9/499.en.mdx deleted 100644 → 0
---
title: V4.9.9
description: FastGPT V4.9.9 Release Notes
---
## Upgrade Guide
### 1. Back Up Your Data
### 2. Pro Edition Users: Replace Your License
Pro edition users can contact the FastGPT team for a license replacement plan. After replacement, you can upgrade the system directly — the admin panel will prompt you to enter the new license.
### 3. Update Image Tags
- Update FastGPT image tag: v4.9.9
- Update FastGPT Pro image tag: v4.9.9
- mcp_server: no update required
- Sandbox: no update required
- AIProxy: no update required
## New Features
1. Switched from JWT to SessionId-based login authentication, with configurable maximum concurrent client sessions.
2. New Pro edition license management model.
3. WeChat Official Account calls now display and log chat conversation errors for easier troubleshooting.
4. API knowledge base now supports BasePath selection. Requires an additional API endpoint — see [API Knowledge Base Introduction](/docs/introduction/guide/knowledge_base/api_dataset/#4-获取文件详细信息用于获取文件信息) for details.
## Improvements
1. Optimized tool call logic for new tool detection.
2. Adjusted citation prompt text.
## Bug Fixes
1. Unable to retrieve app history save/publish records.
2. Member MCP tool creation permission issues.
3. Source citation display passing incorrect IDs, causing "no permission to access this file" errors.
4. Answer annotation frontend data errors.
document/content/docs/upgrading/4-9/499.mdx deleted 100644 → 0
---
title: V4.9.9
description: FastGPT V4.9.9 更新说明
---
## 升级指南
### 1. 做好数据备份
### 2. 商业版用户替换新 License
商业版用户可以联系 FastGPT 团队支持同学，获取 License 替换方案。替换后，可以直接升级系统，管理后台会提示输入新 License。
### 3. 更新镜像 tag
- 更新 FastGPT 镜像 tag: v4.9.9
- 更新 FastGPT 商业版镜像 tag: v4.9.9
- mcp_server 无需更新
- Sandbox 无需更新
- AIProxy 无需更新
## 🚀 新增内容
1. 切换 SessionId 来替代 JWT 实现登录鉴权，可控制最大登录客户端数量。
2. 新的商业版 License 管理模式。
3. 公众号调用，显示记录 chat 对话错误，方便排查。
4. API 知识库支持 BasePath 选择，需增加 API 接口，具体可见[API 知识库介绍](/docs/introduction/guide/knowledge_base/api_dataset/#4-获取文件详细信息用于获取文件信息)
## ⚙️ 优化
1. 优化工具调用，新工具的判断逻辑。
2. 调整 Cite 引用提示词。
## 🐛 修复
1. 无法正常获取应用历史保存/发布记录。
2. 成员创建 MCP 工具权限问题。
3. 来源引用展示，存在 ID 传递错误，导致提示无权操作该文件。
4. 回答标注前端数据报错。
document/content/docs/upgrading/4-9/meta.en.json deleted 100644 → 0
{
"title": "4.9.x",
"description": "",
"pages": [
"4914",
"4913",
"4912",
"4911",
"4910",
"499",
"498",
"497",
"496",
"495",
"494",
"493",
"492",
"491",
"490"
]
}
document/content/docs/upgrading/4-9/meta.json deleted 100644 → 0
{
"title": "4.9.x",
"description": "",
"pages": [
"4914",
"4913",
"4912",
"4911",
"4910",
"499",
"498",
"497",
"496",
"495",
"494",
"493",
"492",
"491",
"490"
]
}
document/content/docs/upgrading/index.en.mdx deleted 100644 → 0
---
title: Version Upgrade Guide
description: FastGPT version upgrade guide
---
Upgrading FastGPT involves two steps:
1. Update the image
2. Run the upgrade initialization script
## Image Names
**GitHub Container Registry**
- FastGPT main image: ghcr.io/labring/fastgpt:latest
- Plugin image: ghcr.io/labring/fastgpt-plugin
- Code sandbox image: ghcr.io/labring/fastgpt-sandbox
- MCP SSE server image: ghcr.io/labring/fastgpt-mcp_server
- Commercial edition image: ghcr.io/c121914yu/fastgpt-pro:latest
**Alibaba Cloud**
- FastGPT main image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt
- Plugin image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-plugin
- Code sandbox image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox
- MCP SSE server image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server
- Commercial edition image: ghcr:registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-pro
An image consists of the image name and a `Tag`. For example, registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.6.1 refers to the `4.6.3` version image. Check Docker Hub or the GitHub repository for details.
## Updating Images on Sealos
1. Open [Sealos Cloud](https://cloud.sealos.io?uid=fnWRt09fZP) and find App Management on the desktop.
![](/imgs/updateImageSealos1.jpg)
2. Select the corresponding app - click the three dots on the right - Update.
![](/imgs/updateImageSealos2.png)
3. Update the image - Confirm changes.
If you need to modify the configuration file, scroll down to the `Configuration File` section to make changes.
![](/imgs/updateImageSealos3.png)
## Updating Images with Docker Compose
Simply modify the `image:` field in the `yml` file, then run:
```bash
docker-compose pull
docker-compose up -d
```
## Running the Upgrade Initialization Script
After updating the images, check the version notes in the documentation. Versions that require an upgrade script are typically labeled with "includes upgrade script". Open the corresponding documentation and follow the instructions to run the **upgrade script** -- in most cases, you just need to send a `POST` request.
## FAQ
### Why do I need to run an upgrade script?
When there are significant changes to the database schema that cannot be handled through default values, or when the migration logic is complex, an upgrade script is used to update certain database fields.
Following the initialization steps carefully will not cause any data loss. However, if the data volume is large, the initialization may take a while, during which the service may be temporarily unavailable.
### What is `{{host}}`?
`{{}}` denotes a variable. `{{host}}` refers to a variable named "host", which is your server's domain name or IP address.
On Sealos, you can find your domain name as shown below:
![](/imgs/updateImageSealos4.png)
### How to get the rootkey
You can find it in the `environment` section of your `docker-compose.yml` file -- it's the value of `ROOT_KEY`.
On Sealos, you can find it in the environment variables panel shown in the image above.
### How to upgrade across multiple versions
Back up your data first!
You can upgrade to the latest version and then run all the upgrade scripts in order. However, for stability, we recommend upgrading one version at a time. For example, if your current version is 4.4.7 and you need to upgrade to 4.6:
1. Update the image to 4.5, run the upgrade script
2. Update the image to 4.5.1, run the upgrade script
3. Update the image to 4.5.2, run the upgrade script
4. Update the image to 4.6, run the upgrade script
5. .....
Upgrade one version at a time.
document/content/docs/upgrading/index.mdx deleted 100644 → 0
---
title: 版本升级说明
description: FastGPT 版本升级说明
---
FastGPT 升级包括两个步骤：
1. 镜像升级
2. 执行升级初始化脚本
## 镜像名
**git版**
- FastGPT 主镜像: ghcr.io/labring/fastgpt:latest
- Plugin 镜像: ghcr.io/labring/fastgpt-plugin
- 代码沙箱镜像: ghcr.io/labring/fastgpt-sandbox
- MCP SSE setver 镜像: ghcr.io/labring/fastgpt-mcp_server
- 商业版镜像: ghcr.io/c121914yu/fastgpt-pro:latest
**阿里云**
- FastGPT 主镜像: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt
- Plugin 镜像: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-plugin
- 代码沙箱镜像: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox
- MCP SSE setver 镜像: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server
- 商业版镜像: ghcr:registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-pro
镜像由镜像名和`Tag`组成，例如: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.6.1 代表`4.6.3`版本镜像，具体可以看 docker hub, github 仓库。
## Sealos 修改镜像
1. 打开 [Sealos Cloud](https://cloud.sealos.io?uid=fnWRt09fZP)， 找到桌面上的应用管理
![](/imgs/updateImageSealos1.jpg)
2. 选择对应的应用 - 点击右边三个点 - 变更
![](/imgs/updateImageSealos2.png)
3. 修改镜像 - 确认变更
如果要修改配置文件，可以拉到下面的`配置文件`进行修改。
![](/imgs/updateImageSealos3.png)
## Docker-Compose 修改镜像
直接修改`yml`文件中的`image: `即可。随后执行:
```bash
docker-compose pull
docker-compose up -d
```
## 执行升级初始化脚本
镜像更新完后，可以查看文档中的`版本介绍`，通常需要执行升级脚本的版本都会标明`包含升级脚本`，打开对应的文档，参考说明执行**升级脚本**即可，大部分时候都是需要发送一个`POST`请求。
## QA
### 为什么需要执行升级脚本
数据表出现大幅度变更，无法通过设置默认值，或复杂度较高时，会通过升级脚本来更新部分数据表字段。
严格按初始化步骤进行操作，不会造成旧数据丢失。但在初始化过程中，如果数据量大，需要初始化的时间较长，这段时间可能会造成服务无法正常使用。
### `{{host}}` 是什么
`{{}}` 代表变量， `{{host}}`代表一个名为 host 的变量。指的是你服务器的域名或 IP。
Sealos 中，你可以在下图中找到你的域名：
![](/imgs/updateImageSealos4.png)
### 如何获取 rootkey
从`docker-compose.yml`中的`environment`中获取，对应的是`ROOT_KEY`的值。
sealos 中可以从上图左侧的环境变量中获取。
### 如何跨版本升级！！
先进行数据备份！！！
可以升级至最新版本，然后将所有升级脚本的版本都执行一遍。不过为了稳定，建议逐一版本升级。例如，当前版本是4.4.7，需要升级到4.6。
1. 修改镜像到4.5，执行升级脚本
2. 修改镜像到4.5.1，执行升级脚本
3. 修改镜像到4.5.2，执行升级脚本
4. 修改镜像到4.6，执行升级脚本
5. .....
逐一升级
document/content/docs/upgrading/meta.en.json deleted 100644 → 0
{
"root": true,
"title": "Version Updates & Upgrades",
"description": "FastGPT version updates and upgrade operations",
"pages": [
"index",
"---4.14.x---",
"...4-14",
"---4.13.x---",
"...4-13",
"---4.12.x---",
"...4-12",
"---4.11.x---",
"...4-11",
"---4.10.x---",
"...4-10",
"---4.9.x---",
"...4-9",
"---<4.9.0---",
"...4-8"
]
}
document/content/docs/upgrading/meta.json deleted 100644 → 0
{
"root": true,
"title": "版本更新/升级操作",
"description": "FastGPT 版本更新介绍及升级操作",
"pages": [
"index",
"---4.14.x---",
"...4-14",
"---4.13.x---",
"...4-13",
"---4.12.x---",
"...4-12",
"---4.11.x---",
"...4-11",
"---4.10.x---",
"...4-10",
"---4.9.x---",
"...4-9",
"---<4.9.0---",
"...4-8"
]
}
document/content/docs/use-cases/app-cases/submit_application_template.en.mdx
......@@ -18,7 +18,7 @@ We estimate the final total will be around 50 templates — half from the FastGP
The following operations need to be performed in a dev environment.
Refer to these two guides to run the FastGPT and FastGPT-plugin development environments locally:
- [FastGPT | Quick Start Local Development](/docs/introduction/development/intro/)
- [FastGPT | Quick Start Local Development](/docs/self-host/dev/)
- [How to Develop System Plugins](/docs/introduction/guide/plugins/dev_system_tool/)
### 2. Create an Application Template
......
document/content/docs/use-cases/app-cases/submit_application_template.mdx
......@@ -18,7 +18,7 @@ description: 指南：如何向 FastGPT 提交应用模板
需要在 dev 环境下执行下面的操作。
可参照下面两篇文档在本地运行 FastGPT 开发环境和 FastGPT-plugin 开发环境
- [FastGPT｜快速开始本地开发](/docs/introduction/development/intro/)
- [FastGPT｜快速开始本地开发](/docs/self-host/dev/)
- [如何开发系统插件](/docs/introduction/guide/plugins/dev_system_tool/)
### 2. 创建应用模版
......
document/data/doc-last-modified.json
......@@ -15,64 +15,16 @@
"document/content/docs/faq/other.mdx": "2025-08-04T22:07:52+08:00",
"document/content/docs/faq/points_consumption.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/faq/points_consumption.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/introduction/cloud.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/cloud.mdx": "2026-02-26T00:26:52+08:00",
"document/content/docs/introduction/commercial.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/commercial.mdx": "2025-09-21T23:09:46+08:00",
"document/content/docs/introduction/development/configuration.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/configuration.mdx": "2025-08-05T23:20:39+08:00",
"document/content/docs/introduction/development/custom-models/bge-rerank.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/custom-models/bge-rerank.mdx": "2025-07-23T21:35:03+08:00",
"document/content/docs/introduction/development/custom-models/chatglm2-m3e.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/custom-models/chatglm2-m3e.mdx": "2025-08-05T23:20:39+08:00",
"document/content/docs/introduction/development/custom-models/chatglm2.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/custom-models/chatglm2.mdx": "2025-07-23T21:35:03+08:00",
"document/content/docs/introduction/development/custom-models/m3e.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/custom-models/m3e.mdx": "2025-07-23T21:35:03+08:00",
"document/content/docs/introduction/development/custom-models/marker.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/custom-models/marker.mdx": "2025-08-04T22:07:52+08:00",
"document/content/docs/introduction/development/custom-models/mineru.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/custom-models/mineru.mdx": "2025-09-17T18:33:31+08:00",
"document/content/docs/introduction/development/custom-models/ollama.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/custom-models/ollama.mdx": "2025-08-05T23:20:39+08:00",
"document/content/docs/introduction/development/custom-models/xinference.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/custom-models/xinference.mdx": "2025-08-05T23:20:39+08:00",
"document/content/docs/introduction/development/design/dataset.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/design/dataset.mdx": "2025-07-23T21:35:03+08:00",
"document/content/docs/introduction/development/design/design_plugin.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/design/design_plugin.mdx": "2025-11-06T14:47:55+08:00",
"document/content/docs/introduction/development/docker.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/docker.mdx": "2026-02-13T11:35:13+08:00",
"document/content/docs/introduction/development/faq.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/faq.mdx": "2025-08-12T22:22:18+08:00",
"document/content/docs/introduction/development/intro.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/intro.mdx": "2026-02-12T18:02:02+08:00",
"document/content/docs/introduction/development/migration/docker_db.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/migration/docker_db.mdx": "2025-07-23T21:35:03+08:00",
"document/content/docs/introduction/development/migration/docker_mongo.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/migration/docker_mongo.mdx": "2025-07-23T21:35:03+08:00",
"document/content/docs/introduction/development/modelConfig/ai-proxy.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/modelConfig/ai-proxy.mdx": "2025-08-05T23:20:39+08:00",
"document/content/docs/introduction/development/modelConfig/intro.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/modelConfig/intro.mdx": "2025-12-03T08:36:19+08:00",
"document/content/docs/introduction/development/modelConfig/one-api.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/modelConfig/one-api.mdx": "2025-07-23T21:35:03+08:00",
"document/content/docs/introduction/development/modelConfig/ppio.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/modelConfig/ppio.mdx": "2025-09-29T11:52:39+08:00",
"document/content/docs/introduction/development/modelConfig/siliconCloud.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/modelConfig/siliconCloud.mdx": "2025-08-05T23:20:39+08:00",
"document/content/docs/introduction/development/object-storage.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/object-storage.mdx": "2026-01-09T18:25:02+08:00",
"document/content/docs/introduction/development/proxy/cloudflare.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/proxy/cloudflare.mdx": "2025-07-23T21:35:03+08:00",
"document/content/docs/introduction/development/proxy/http_proxy.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/proxy/http_proxy.mdx": "2025-07-23T21:35:03+08:00",
"document/content/docs/introduction/development/proxy/nginx.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/proxy/nginx.mdx": "2025-07-23T21:35:03+08:00",
"document/content/docs/introduction/development/sealos.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/sealos.mdx": "2026-02-26T16:29:03+08:00",
"document/content/docs/introduction/development/signoz.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/development/signoz.mdx": "2026-02-12T16:37:50+08:00",
"document/content/docs/introduction/cloud/faq.en.mdx": "2026-03-03T14:33:59+08:00",
"document/content/docs/introduction/cloud/faq.mdx": "2026-03-03T14:33:59+08:00",
"document/content/docs/introduction/cloud/intro.en.mdx": "2026-03-03T14:33:59+08:00",
"document/content/docs/introduction/cloud/intro.mdx": "2026-03-03T14:33:59+08:00",
"document/content/docs/introduction/cloud/privacy.en.mdx": "2026-03-03T14:33:59+08:00",
"document/content/docs/introduction/cloud/privacy.mdx": "2026-03-03T14:33:59+08:00",
"document/content/docs/introduction/cloud/terms.en.mdx": "2026-03-03T14:33:59+08:00",
"document/content/docs/introduction/cloud/terms.mdx": "2026-03-03T14:33:59+08:00",
"document/content/docs/introduction/commercial.en.mdx": "2026-03-03T16:24:15+08:00",
"document/content/docs/introduction/commercial.mdx": "2026-03-03T16:24:15+08:00",
"document/content/docs/introduction/guide/DialogBoxes/htmlRendering.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/guide/DialogBoxes/htmlRendering.mdx": "2025-07-23T21:35:03+08:00",
"document/content/docs/introduction/guide/DialogBoxes/quoteList.en.mdx": "2026-02-26T22:14:30+08:00",
......@@ -101,8 +53,8 @@
"document/content/docs/introduction/guide/dashboard/mcp_server.mdx": "2025-07-23T21:35:03+08:00",
"document/content/docs/introduction/guide/dashboard/mcp_tools.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/guide/dashboard/mcp_tools.mdx": "2025-07-23T21:35:03+08:00",
"document/content/docs/introduction/guide/dashboard/workflow/ai_chat.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/guide/dashboard/workflow/ai_chat.mdx": "2025-08-05T23:20:39+08:00",
"document/content/docs/introduction/guide/dashboard/workflow/ai_chat.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/introduction/guide/dashboard/workflow/ai_chat.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/introduction/guide/dashboard/workflow/content_extract.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/guide/dashboard/workflow/content_extract.mdx": "2025-07-23T21:35:03+08:00",
"document/content/docs/introduction/guide/dashboard/workflow/coreferenceResolution.en.mdx": "2026-02-26T22:14:30+08:00",
......@@ -127,8 +79,10 @@
"document/content/docs/introduction/guide/dashboard/workflow/question_classify.mdx": "2025-07-23T21:35:03+08:00",
"document/content/docs/introduction/guide/dashboard/workflow/reply.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/guide/dashboard/workflow/reply.mdx": "2025-07-23T21:35:03+08:00",
"document/content/docs/introduction/guide/dashboard/workflow/sandbox-v2.en.mdx": "2026-02-28T12:36:59+08:00",
"document/content/docs/introduction/guide/dashboard/workflow/sandbox-v2.mdx": "2026-02-28T12:36:59+08:00",
"document/content/docs/introduction/guide/dashboard/workflow/sandbox.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/guide/dashboard/workflow/sandbox.mdx": "2026-02-26T15:08:45+08:00",
"document/content/docs/introduction/guide/dashboard/workflow/sandbox.mdx": "2026-02-28T12:36:59+08:00",
"document/content/docs/introduction/guide/dashboard/workflow/text_editor.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/guide/dashboard/workflow/text_editor.mdx": "2025-07-23T21:35:03+08:00",
"document/content/docs/introduction/guide/dashboard/workflow/tfswitch.en.mdx": "2026-02-26T22:14:30+08:00",
......@@ -159,8 +113,8 @@
"document/content/docs/introduction/guide/knowledge_base/yuque_dataset.mdx": "2025-09-17T22:29:56+08:00",
"document/content/docs/introduction/guide/plugins/bing_search_plugin.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/guide/plugins/bing_search_plugin.mdx": "2025-07-23T21:35:03+08:00",
"document/content/docs/introduction/guide/plugins/dev_system_tool.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/guide/plugins/dev_system_tool.mdx": "2025-11-06T14:47:55+08:00",
"document/content/docs/introduction/guide/plugins/dev_system_tool.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/introduction/guide/plugins/dev_system_tool.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/introduction/guide/plugins/doc2x_plugin_guide.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/guide/plugins/doc2x_plugin_guide.mdx": "2025-07-23T21:35:03+08:00",
"document/content/docs/introduction/guide/plugins/google_search_plugin_guide.en.mdx": "2026-02-26T22:14:30+08:00",
......@@ -177,6 +131,10 @@
"document/content/docs/introduction/guide/team_permissions/team_roles_permissions.mdx": "2025-07-23T21:35:03+08:00",
"document/content/docs/introduction/index.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/introduction/index.mdx": "2026-02-26T00:26:52+08:00",
"document/content/docs/introduction/opensource/intro.en.mdx": "2026-03-03T16:24:15+08:00",
"document/content/docs/introduction/opensource/intro.mdx": "2026-03-03T16:24:15+08:00",
"document/content/docs/introduction/opensource/license.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/introduction/opensource/license.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/openapi/app.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/openapi/app.mdx": "2026-02-12T18:45:30+08:00",
"document/content/docs/openapi/chat.en.mdx": "2026-02-26T22:14:30+08:00",
......@@ -189,192 +147,234 @@
"document/content/docs/openapi/intro.mdx": "2026-02-12T18:45:30+08:00",
"document/content/docs/openapi/share.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/openapi/share.mdx": "2026-02-12T18:45:30+08:00",
"document/content/docs/protocol/index.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/protocol/index.mdx": "2025-07-30T15:38:30+08:00",
"document/content/docs/protocol/open-source.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/protocol/open-source.mdx": "2025-08-05T23:20:39+08:00",
"document/content/docs/protocol/privacy.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/protocol/privacy.mdx": "2025-12-15T23:36:54+08:00",
"document/content/docs/protocol/terms.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/protocol/terms.mdx": "2025-12-15T23:36:54+08:00",
"document/content/docs/toc.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/toc.mdx": "2026-02-26T15:08:45+08:00",
"document/content/docs/upgrading/4-10/4100.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-10/4100.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-10/4101.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-10/4101.mdx": "2025-09-08T20:07:20+08:00",
"document/content/docs/upgrading/4-11/4110.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-11/4110.mdx": "2026-02-26T00:26:52+08:00",
"document/content/docs/upgrading/4-11/4111.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-11/4111.mdx": "2025-08-07T22:49:09+08:00",
"document/content/docs/upgrading/4-12/4120.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-12/4120.mdx": "2025-09-07T14:41:48+08:00",
"document/content/docs/upgrading/4-12/4121.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-12/4121.mdx": "2025-09-07T14:41:48+08:00",
"document/content/docs/upgrading/4-12/4122.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-12/4122.mdx": "2025-09-07T14:41:48+08:00",
"document/content/docs/upgrading/4-12/4123.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-12/4123.mdx": "2025-09-07T20:55:14+08:00",
"document/content/docs/upgrading/4-12/4124.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-12/4124.mdx": "2025-09-17T22:29:56+08:00",
"document/content/docs/upgrading/4-13/4130.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-13/4130.mdx": "2025-11-04T15:06:39+08:00",
"document/content/docs/upgrading/4-13/4131.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-13/4131.mdx": "2025-09-30T15:47:06+08:00",
"document/content/docs/upgrading/4-13/4132.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-13/4132.mdx": "2025-12-15T11:50:00+08:00",
"document/content/docs/upgrading/4-14/4140.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-14/4140.mdx": "2025-11-06T15:43:00+08:00",
"document/content/docs/upgrading/4-14/4141.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-14/4141.mdx": "2025-12-31T09:54:29+08:00",
"document/content/docs/upgrading/4-14/4142.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-14/4142.mdx": "2025-11-18T19:27:14+08:00",
"document/content/docs/upgrading/4-14/4143.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-14/4143.mdx": "2026-02-04T14:27:58+08:00",
"document/content/docs/upgrading/4-14/4144.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-14/4144.mdx": "2026-02-04T14:27:58+08:00",
"document/content/docs/upgrading/4-14/4145.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-14/4145.mdx": "2026-01-18T23:59:15+08:00",
"document/content/docs/upgrading/4-14/41451.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-14/41451.mdx": "2026-01-20T11:53:27+08:00",
"document/content/docs/upgrading/4-14/4146.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-14/4146.mdx": "2026-02-12T16:37:50+08:00",
"document/content/docs/upgrading/4-14/4147.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-14/4147.mdx": "2026-02-26T18:14:55+08:00",
"document/content/docs/upgrading/4-14/4148.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-14/4148.mdx": "2026-02-25T18:28:16+08:00",
"document/content/docs/upgrading/4-8/40.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/40.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/41.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/41.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/42.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/42.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/421.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/421.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/43.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/43.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/44.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/44.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/441.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/441.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/442.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/442.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/445.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/445.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/446.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/446.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/447.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/447.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/45.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/45.mdx": "2025-08-05T23:20:39+08:00",
"document/content/docs/upgrading/4-8/451.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/451.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/452.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/452.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/46.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/46.mdx": "2025-08-05T23:20:39+08:00",
"document/content/docs/upgrading/4-8/461.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/461.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/462.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/462.mdx": "2025-08-04T22:07:52+08:00",
"document/content/docs/upgrading/4-8/463.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/463.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/464.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/464.mdx": "2026-02-12T18:45:30+08:00",
"document/content/docs/upgrading/4-8/465.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/465.mdx": "2025-08-05T23:20:39+08:00",
"document/content/docs/upgrading/4-8/466.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/466.mdx": "2025-08-05T23:20:39+08:00",
"document/content/docs/upgrading/4-8/467.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/467.mdx": "2026-02-12T18:45:30+08:00",
"document/content/docs/upgrading/4-8/468.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/468.mdx": "2025-08-05T23:20:39+08:00",
"document/content/docs/upgrading/4-8/469.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/469.mdx": "2026-02-12T18:45:30+08:00",
"document/content/docs/upgrading/4-8/47.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/47.mdx": "2025-08-05T23:20:39+08:00",
"document/content/docs/upgrading/4-8/471.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/471.mdx": "2025-08-05T23:20:39+08:00",
"document/content/docs/upgrading/4-8/48.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/48.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/481.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/481.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/4810.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/4810.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/4811.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/4811.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/4812.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/4812.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/4813.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/4813.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/4814.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/4814.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/4815.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/4815.mdx": "2025-08-05T23:20:39+08:00",
"document/content/docs/upgrading/4-8/4816.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/4816.mdx": "2025-08-05T23:20:39+08:00",
"document/content/docs/upgrading/4-8/4817.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/4817.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/4818.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/4818.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/4819.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/4819.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/482.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/482.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/4820.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/4820.mdx": "2025-08-05T23:20:39+08:00",
"document/content/docs/upgrading/4-8/4821.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/4821.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/4822.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/4822.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/4823.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/4823.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/483.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/483.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/484.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/484.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/485.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/485.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/486.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/486.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/487.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/487.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/488.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/488.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-8/489.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-8/489.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-9/490.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-9/490.mdx": "2026-02-12T18:45:30+08:00",
"document/content/docs/upgrading/4-9/491.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-9/491.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-9/4910.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-9/4910.mdx": "2025-08-04T22:07:52+08:00",
"document/content/docs/upgrading/4-9/4911.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-9/4911.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-9/4912.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-9/4912.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-9/4913.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-9/4913.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-9/4914.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-9/4914.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-9/492.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-9/492.mdx": "2026-02-12T18:45:30+08:00",
"document/content/docs/upgrading/4-9/493.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-9/493.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-9/494.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-9/494.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-9/495.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-9/495.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-9/496.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-9/496.mdx": "2025-08-04T22:07:52+08:00",
"document/content/docs/upgrading/4-9/497.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-9/497.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-9/498.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-9/498.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/4-9/499.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/4-9/499.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/upgrading/index.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/upgrading/index.mdx": "2025-08-02T19:38:37+08:00",
"document/content/docs/self-host/config/json.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/config/json.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/config/model/ai-proxy.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/config/model/ai-proxy.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/config/model/intro.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/config/model/intro.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/config/model/one-api.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/config/model/one-api.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/config/model/ppio.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/config/model/ppio.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/config/model/siliconCloud.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/config/model/siliconCloud.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/config/object-storage.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/config/object-storage.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/config/signoz.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/config/signoz.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/custom-models/bge-rerank.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/custom-models/bge-rerank.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/custom-models/chatglm2-m3e.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/custom-models/chatglm2-m3e.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/custom-models/chatglm2.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/custom-models/chatglm2.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/custom-models/m3e.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/custom-models/m3e.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/custom-models/marker.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/custom-models/marker.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/custom-models/mineru.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/custom-models/mineru.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/custom-models/ollama.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/custom-models/ollama.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/custom-models/xinference.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/custom-models/xinference.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/deploy/docker.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/deploy/docker.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/deploy/sealos.en.mdx": "2026-03-03T16:24:15+08:00",
"document/content/docs/self-host/deploy/sealos.mdx": "2026-03-03T16:24:15+08:00",
"document/content/docs/self-host/design/dataset.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/design/dataset.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/design/design_plugin.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/design/design_plugin.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/dev.en.mdx": "2026-03-03T16:24:15+08:00",
"document/content/docs/self-host/dev.mdx": "2026-03-03T16:24:15+08:00",
"document/content/docs/self-host/faq.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/faq.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/index.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/index.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/migration/docker_db.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/migration/docker_db.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/migration/docker_mongo.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/migration/docker_mongo.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-12/4120.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-12/4120.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-12/4121.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-12/4121.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-12/4122.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-12/4122.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-12/4123.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-12/4123.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-12/4124.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-12/4124.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-13/4130.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-13/4130.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-13/4131.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-13/4131.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-13/4132.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-13/4132.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-14/4140.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-14/4140.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-14/4141.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-14/4141.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-14/4142.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-14/4142.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-14/4143.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-14/4143.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-14/4144.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-14/4144.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-14/4145.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-14/4145.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-14/41451.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-14/41451.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-14/4146.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-14/4146.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-14/4147.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-14/4147.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-14/4148.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/4-14/4148.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/40.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/40.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/41.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/41.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4100.en.mdx": "2026-03-03T16:24:15+08:00",
"document/content/docs/self-host/upgrading/outdated/4100.mdx": "2026-03-03T16:24:15+08:00",
"document/content/docs/self-host/upgrading/outdated/4101.en.mdx": "2026-03-03T16:24:15+08:00",
"document/content/docs/self-host/upgrading/outdated/4101.mdx": "2026-03-03T16:24:15+08:00",
"document/content/docs/self-host/upgrading/outdated/4110.en.mdx": "2026-03-03T16:24:15+08:00",
"document/content/docs/self-host/upgrading/outdated/4110.mdx": "2026-03-03T16:24:15+08:00",
"document/content/docs/self-host/upgrading/outdated/4111.en.mdx": "2026-03-03T16:24:15+08:00",
"document/content/docs/self-host/upgrading/outdated/4111.mdx": "2026-03-03T16:24:15+08:00",
"document/content/docs/self-host/upgrading/outdated/42.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/42.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/421.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/421.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/43.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/43.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/44.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/44.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/441.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/441.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/442.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/442.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/445.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/445.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/446.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/446.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/447.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/447.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/45.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/45.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/451.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/451.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/452.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/452.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/46.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/46.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/461.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/461.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/462.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/462.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/463.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/463.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/464.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/464.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/465.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/465.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/466.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/466.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/467.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/467.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/468.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/468.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/469.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/469.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/47.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/47.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/471.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/471.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/48.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/48.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/481.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/481.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4810.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4810.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4811.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4811.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4812.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4812.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4813.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4813.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4814.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4814.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4815.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4815.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4816.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4816.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4817.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4817.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4818.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4818.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4819.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4819.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/482.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/482.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4820.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4820.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4821.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4821.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4822.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4822.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4823.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4823.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/483.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/483.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/484.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/484.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/485.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/485.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/486.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/486.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/487.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/487.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/488.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/488.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/489.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/489.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/490.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/490.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/491.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/491.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4910.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4910.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4911.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4911.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4912.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4912.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4913.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4913.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4914.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/4914.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/492.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/492.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/493.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/493.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/494.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/494.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/495.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/495.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/496.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/496.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/497.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/497.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/498.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/498.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/499.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/outdated/499.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/upgrade-intruction.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/self-host/upgrading/upgrade-intruction.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/toc.en.mdx": "2026-03-03T16:24:15+08:00",
"document/content/docs/toc.mdx": "2026-03-03T16:24:15+08:00",
"document/content/docs/use-cases/app-cases/dalle3.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/use-cases/app-cases/dalle3.mdx": "2025-07-23T21:35:03+08:00",
"document/content/docs/use-cases/app-cases/english_essay_correction_bot.en.mdx": "2026-02-26T22:14:30+08:00",
......@@ -389,8 +389,8 @@
"document/content/docs/use-cases/app-cases/lab_appointment.mdx": "2025-12-10T20:07:05+08:00",
"document/content/docs/use-cases/app-cases/multi_turn_translation_bot.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/use-cases/app-cases/multi_turn_translation_bot.mdx": "2025-07-23T21:35:03+08:00",
"document/content/docs/use-cases/app-cases/submit_application_template.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/use-cases/app-cases/submit_application_template.mdx": "2026-01-27T15:19:19+08:00",
"document/content/docs/use-cases/app-cases/submit_application_template.en.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/use-cases/app-cases/submit_application_template.mdx": "2026-03-03T16:00:35+08:00",
"document/content/docs/use-cases/app-cases/translate-subtitle-using-gpt.en.mdx": "2026-02-26T22:14:30+08:00",
"document/content/docs/use-cases/app-cases/translate-subtitle-using-gpt.mdx": "2025-07-23T21:35:03+08:00",
"document/content/docs/use-cases/external-integration/dingtalk.en.mdx": "2026-02-26T22:14:30+08:00",
......
document/i18n/en/common.json
......@@ -15,6 +15,7 @@
"api_reference": "API Reference",
"use-cases": "Use Cases",
"api": "API",
"selfHost": "Self-Host",
"protocol": "Protocol",
"upgrading": "Upgrading",
"faq": "FAQ"
......
document/i18n/zh-CN/common.json
......@@ -16,6 +16,7 @@
"use-cases": "使用场景",
"api": "API 手册",
"protocol": "协议",
"selfHost": "自部署",
"upgrading": "更新日志",
"faq": "常见问题"
}
document/lib/schema.ts 0 → 100644
import type { Article, BreadcrumbList, WithContext } from 'schema-dts';
export function generateArticleSchema(params: {
title: string;
description: string;
url: string;
dateModified?: Date;
lang: string;
}): WithContext<Article> {
const { title, description, url, dateModified, lang } = params;
return {
'@context': 'https://schema.org',
'@type': 'Article',
headline: title,
description,
url,
inLanguage: lang,
dateModified: dateModified?.toISOString(),
author: {
'@type': 'Organization',
name: 'Labring',
url: 'https://github.com/labring'
},
publisher: {
'@type': 'Organization',
name: 'FastGPT',
logo: {
'@type': 'ImageObject',
url: 'https://doc.fastgpt.io/logo.svg'
}
}
};
}
export function generateBreadcrumbSchema(params: {
items: Array<{ name: string; url: string }>;
}): WithContext<BreadcrumbList> {
const { items } = params;
return {
'@context': 'https://schema.org',
'@type': 'BreadcrumbList',
itemListElement: items.map((item, index) => ({
'@type': 'ListItem',
position: index + 1,
name: item.name,
item: item.url
}))
};
}
document/middleware.ts
import { createI18nMiddleware } from 'fumadocs-core/i18n';
import { i18n } from '@/lib/i18n';
import { NextRequest, NextResponse } from 'next/server';
import { type NextRequest, NextResponse } from 'next/server';
// Old path redirects mapping
const exactMap: Record<string, string> = {
......@@ -11,18 +11,27 @@ const exactMap: Record<string, string> = {
'/docs/guide/admin/sso_dingtalk':
'/docs/introduction/guide/admin/sso#/docs/introduction/guide/admin/sso#钉钉',
'/docs/guide/knowledge_base/rag': '/docs/introduction/guide/knowledge_base/RAG',
'/docs/commercial/intro/': '/docs/introduction/commercial',
'/docs/upgrading/intro/': '/docs/upgrading',
'/docs/introduction/shopping_cart/intro/': '/docs/introduction/commercial'
'/docs/commercial/intro': '/docs/introduction/commercial',
'/docs/upgrading/intro': '/docs/self-host/upgrading/upgrade-intruction',
'/docs/upgrading': '/docs/self-host/upgrading/upgrade-intruction',
'/docs/introduction/shopping_cart/intro/': '/docs/introduction/commercial',
'/docs/introduction/cloud': '/docs/introduction/cloud/intro',
'/docs/protocol/terms': '/docs/introduction/cloud/terms',
'/docs/protocol/privacy': '/docs/introduction/cloud/privacy',
'/docs/introduction/development/docker': '/docs/self-host/deploy/docker',
'/docs/introduction/development/sealos': '/docs/self-host/deploy/sealos',
'/docs/introduction/development/intro': '/docs/self-host/dev',
'/docs/introduction/development/object-storage': '/docs/self-host/config/object-storage'
};
const prefixMap: Record<string, string> = {
'/docs/development': '/docs/introduction/development',
'/docs/FAQ': '/docs/faq',
'/docs/guide': '/docs/introduction/guide',
'/docs/shopping_cart': '/docs/introduction/shopping_cart',
'/docs/agreement': '/docs/protocol',
'/docs/introduction/development/openapi': '/docs/openapi'
'/docs/upgrading': '/docs/self-host/upgrading',
'/docs/development': '/docs/self-host',
'/docs/introduction/development/openapi': '/docs/openapi',
'/docs/introduction/development': '/docs/self-host'
};
const i18nMiddleware = createI18nMiddleware(i18n);
......@@ -91,5 +100,6 @@ export default function middleware(request: NextRequest) {
}
export const config = {
matcher: ['/((?!api|_next/static|_next/image|favicon.ico|.*\\.svg|.*\\.png|deploy/.*).*)']
matcher: [
'/((?!api|_next/static|_next/image|favicon.ico|robots\\.txt|sitemap.*\\.xml|.*\\.svg|.*\\.png|deploy/.*).*)']
};
document/package-lock.json
......@@ -25,7 +25,8 @@
"remark": "^15.0.1",
"remark-gfm": "^4.0.1",
"remark-mdx": "^3.1.0",
"remark-stringify": "^11.0.0"
"remark-stringify": "^11.0.0",
"schema-dts": "^1.1.5"
},
"devDependencies": {
"@content-collections/core": "^0.10.0",
......@@ -5844,6 +5845,12 @@
"integrity": "sha512-NlHwttCI/l5gCPR3D1nNXtWABUmBwvZpEQiD4IXSbIDq8BzLIK/7Ir5gTFSGZDUu37K5cMNp0hFtzO38sC7gWA==",
"license": "MIT"
},
"node_modules/schema-dts": {
"version": "1.1.5",
"resolved": "https://registry.npmjs.org/schema-dts/-/schema-dts-1.1.5.tgz",
"integrity": "sha512-RJr9EaCmsLzBX2NDiO5Z3ux2BVosNZN5jo0gWgsyKvxKIUL5R3swNvoorulAeL9kLB0iTSX7V6aokhla2m7xbg==",
"license": "Apache-2.0"
},
"node_modules/scroll-into-view-if-needed": {
"version": "3.1.0",
"resolved": "https://registry.npmjs.org/scroll-into-view-if-needed/-/scroll-into-view-if-needed-3.1.0.tgz",
......
document/package.json
......@@ -25,7 +25,8 @@
"remark": "^15.0.1",
"remark-gfm": "^4.0.1",
"remark-mdx": "^3.1.0",
"remark-stringify": "^11.0.0"
"remark-stringify": "^11.0.0",
"schema-dts": "^1.1.5"
},
"devDependencies": {
"@content-collections/core": "^0.10.0",
......
document/public/deploy/docker/cn/docker-compose.milvus.yml
......@@ -12,7 +12,7 @@ x-share-db-config: &x-share-db-config
MONGODB_URI: mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
DB_MAX_LINK: 100
REDIS_URL: redis://default:mypassword@redis:6379
# @see https://doc.fastgpt.cn/docs/introduction/development/object-storage
# @see https://doc.fastgpt.cn/docs/self-host/config/object-storage
STORAGE_VENDOR: minio # minio | aws-s3 | cos | oss
STORAGE_REGION: us-east-1
STORAGE_ACCESS_KEY_ID: minioadmin
......
document/public/deploy/docker/cn/docker-compose.oceanbase.yml
......@@ -12,7 +12,7 @@ x-share-db-config: &x-share-db-config
MONGODB_URI: mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
DB_MAX_LINK: 100
REDIS_URL: redis://default:mypassword@redis:6379
# @see https://doc.fastgpt.cn/docs/introduction/development/object-storage
# @see https://doc.fastgpt.cn/docs/self-host/config/object-storage
STORAGE_VENDOR: minio # minio | aws-s3 | cos | oss
STORAGE_REGION: us-east-1
STORAGE_ACCESS_KEY_ID: minioadmin
......
document/public/deploy/docker/cn/docker-compose.pg.yml
......@@ -12,7 +12,7 @@ x-share-db-config: &x-share-db-config
MONGODB_URI: mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
DB_MAX_LINK: 100
REDIS_URL: redis://default:mypassword@redis:6379
# @see https://doc.fastgpt.cn/docs/introduction/development/object-storage
# @see https://doc.fastgpt.cn/docs/self-host/config/object-storage
STORAGE_VENDOR: minio # minio | aws-s3 | cos | oss
STORAGE_REGION: us-east-1
STORAGE_ACCESS_KEY_ID: minioadmin
......
document/public/deploy/docker/cn/docker-compose.seekdb.yml
......@@ -12,7 +12,7 @@ x-share-db-config: &x-share-db-config
MONGODB_URI: mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
DB_MAX_LINK: 100
REDIS_URL: redis://default:mypassword@redis:6379
# @see https://doc.fastgpt.cn/docs/introduction/development/object-storage
# @see https://doc.fastgpt.cn/docs/self-host/config/object-storage
STORAGE_VENDOR: minio # minio | aws-s3 | cos | oss
STORAGE_REGION: us-east-1
STORAGE_ACCESS_KEY_ID: minioadmin
......
document/public/deploy/docker/cn/docker-compose.zilliz.yml
......@@ -12,7 +12,7 @@ x-share-db-config: &x-share-db-config
MONGODB_URI: mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
DB_MAX_LINK: 100
REDIS_URL: redis://default:mypassword@redis:6379
# @see https://doc.fastgpt.cn/docs/introduction/development/object-storage
# @see https://doc.fastgpt.cn/docs/self-host/config/object-storage
STORAGE_VENDOR: minio # minio | aws-s3 | cos | oss
STORAGE_REGION: us-east-1
STORAGE_ACCESS_KEY_ID: minioadmin
......
document/public/deploy/docker/global/docker-compose.milvus.yml
......@@ -12,7 +12,7 @@ x-share-db-config: &x-share-db-config
MONGODB_URI: mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
DB_MAX_LINK: 100
REDIS_URL: redis://default:mypassword@redis:6379
# @see https://doc.fastgpt.cn/docs/introduction/development/object-storage
# @see https://doc.fastgpt.cn/docs/self-host/config/object-storage
STORAGE_VENDOR: minio # minio | aws-s3 | cos | oss
STORAGE_REGION: us-east-1
STORAGE_ACCESS_KEY_ID: minioadmin
......
document/public/deploy/docker/global/docker-compose.oceanbase.yml
......@@ -12,7 +12,7 @@ x-share-db-config: &x-share-db-config
MONGODB_URI: mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
DB_MAX_LINK: 100
REDIS_URL: redis://default:mypassword@redis:6379
# @see https://doc.fastgpt.cn/docs/introduction/development/object-storage
# @see https://doc.fastgpt.cn/docs/self-host/config/object-storage
STORAGE_VENDOR: minio # minio | aws-s3 | cos | oss
STORAGE_REGION: us-east-1
STORAGE_ACCESS_KEY_ID: minioadmin
......
document/public/deploy/docker/global/docker-compose.pg.yml
......@@ -12,7 +12,7 @@ x-share-db-config: &x-share-db-config
MONGODB_URI: mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
DB_MAX_LINK: 100
REDIS_URL: redis://default:mypassword@redis:6379
# @see https://doc.fastgpt.cn/docs/introduction/development/object-storage
# @see https://doc.fastgpt.cn/docs/self-host/config/object-storage
STORAGE_VENDOR: minio # minio | aws-s3 | cos | oss
STORAGE_REGION: us-east-1
STORAGE_ACCESS_KEY_ID: minioadmin
......
document/public/deploy/docker/global/docker-compose.seekdb.yml
......@@ -12,7 +12,7 @@ x-share-db-config: &x-share-db-config
MONGODB_URI: mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
DB_MAX_LINK: 100
REDIS_URL: redis://default:mypassword@redis:6379
# @see https://doc.fastgpt.cn/docs/introduction/development/object-storage
# @see https://doc.fastgpt.cn/docs/self-host/config/object-storage
STORAGE_VENDOR: minio # minio | aws-s3 | cos | oss
STORAGE_REGION: us-east-1
STORAGE_ACCESS_KEY_ID: minioadmin
......
document/public/deploy/docker/global/docker-compose.ziliiz.yml
......@@ -12,7 +12,7 @@ x-share-db-config: &x-share-db-config
MONGODB_URI: mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
DB_MAX_LINK: 100
REDIS_URL: redis://default:mypassword@redis:6379
# @see https://doc.fastgpt.cn/docs/introduction/development/object-storage
# @see https://doc.fastgpt.cn/docs/self-host/config/object-storage
STORAGE_VENDOR: minio # minio | aws-s3 | cos | oss
STORAGE_REGION: us-east-1
STORAGE_ACCESS_KEY_ID: minioadmin
......
document/public/deploy/install.sh
......@@ -264,4 +264,4 @@ echo " 3. 访问服务: http://localhost:3000"
echo " 4. 登录服务: 默认账号为 'root', 密码为: '1234'"
echo " 5. 配置模型: 在 '账号-模型提供商' 页面，进行模型配置"
echo ""
echo "详细文档: https://doc.fastgpt.cn/docs/introduction/development/docker"
echo "详细文档: https://doc.fastgpt.cn/docs/self-host/deploy/docker"
document/public/favicon/site.webmanifest
......@@ -3,12 +3,12 @@
"short_name": "FastGPT",
"icons": [
{
"src": "/android-chrome-192x192.png",
"src": "/favicon/android-chrome-192x192.png",
"sizes": "192x192",
"type": "image/png"
},
{
"src": "/android-chrome-512x512.png",
"src": "/favicon/android-chrome-512x512.png",
"sizes": "512x512",
"type": "image/png"
}
......
plugins/model/rerank-bge/README.md
......@@ -111,4 +111,4 @@ services:
## 接入 FastGPT
参考 [ReRank模型接入](https://doc.fastgpt.io/docs/introduction/development/configuration/#rerank-接入)
参考 [ReRank模型接入](/docs/self-host/config/model/intro/#rerank-模型接入)
projects/app/next.config.ts
......@@ -19,6 +19,8 @@ const nextConfig: NextConfig = {
// 开发环境关闭 strict mode，避免第三方库的双重渲染问题
reactStrictMode: !isDev,
productionBrowserSourceMaps: false,
// 启用 SWC 压缩
swcMinify: true,
async headers() {
return [
{
......@@ -99,7 +101,19 @@ const nextConfig: NextConfig = {
if (isDev && !isServer) {
config.watchOptions = {
...config.watchOptions,
ignored: ['**/node_modules', '**/.git', '**/dist', '**/coverage']
ignored: [
'**/node_modules',
'**/.git',
'**/dist',
'**/coverage',
'../../packages/**/node_modules',
'../../packages/**/dist',
'**/.next',
'**/out'
],
// 减少轮询频率，降低 CPU 和内存占用
poll: 1000,
aggregateTimeout: 300
};
}
......@@ -127,7 +141,9 @@ const nextConfig: NextConfig = {
'@emotion/styled'
],
// 按页面拆分 CSS chunk，减少首屏 CSS 体积
cssChunking: 'strict'
cssChunking: 'strict',
// 减少内存占用
memoryBasedWorkersCount: true
},
outputFileTracingRoot: path.join(__dirname, '../../')
};
......
projects/app/package.json
......@@ -3,7 +3,7 @@
"version": "4.14.7",
"private": false,
"scripts": {
"dev": "npm run build:workers && next dev",
"dev": "NODE_OPTIONS='--max-old-space-size=8192' npm run build:workers && next dev",
"build": "npm run build:workers && npm run lint && npm run typecheck && next build --debug",
"start": "next start",
"lint": "next lint",
......
projects/app/src/pageComponents/login/LoginForm/PolicyTip.tsx
......@@ -24,14 +24,14 @@ const PolicyTip = ({ isCenter }: { isCenter: boolean }) => {
div: <Flex justifyContent={'center'} />,
termsLink: (
<Link
href={getDocPath('/docs/protocol/terms/')}
href={getDocPath('/docs/introduction/cloud/terms/')}
target={'_blank'}
color={'primary.700'}
/>
),
privacyLink: (
<Link
href={getDocPath('/docs/protocol/privacy/')}
href={getDocPath('/docs/introduction/cloud/privacy/')}
target={'_blank'}
color={'primary.700'}
/>
......
projects/app/src/pageComponents/login/index.tsx
......@@ -75,7 +75,7 @@ const CookiesModal = () => {
textDecorationLine={'underline'}
cursor={'pointer'}
w={'fit-content'}
onClick={() => window.open(getDocPath('/docs/protocol/privacy/'), '_blank')}
onClick={() => window.open(getDocPath('/docs/introduction/cloud/privacy/'), '_blank')}
>
{t('login:privacy_policy')}
</Box>
......
projects/app/tsconfig.json
......@@ -8,6 +8,12 @@
"@t3-oss/env-core": ["../../packages/service/node_modules/@t3-oss/env-core/dist/index.d.ts"]
}
},
"include": ["next-env.d.ts", "**/*.ts", "**/*.tsx", "../../packages/**/*.ts"],
"exclude": ["**/*.test.ts"]
"include": [
"next-env.d.ts",
"**/*.ts",
"**/*.tsx",
"../../packages/**/*.ts",
"../../packages/**/*.tsx"
],
"exclude": ["**/*.test.ts", "**/*.test.tsx", ".next", "dist", "coverage"]
}
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or sign in to comment