ChatGPT/FastGPT
1
0
Fork 0
mirror of https://github.com/labring/FastGPT.git synced 2026-05-02 01:02:05 +08:00
Code Issues Packages Projects Releases Wiki Activity

V4.14.10 dev (#6686)

Browse Source 
* docker

* fix: community version check

* perf: deploy doc

* doc

* doc

* remove invalide md
This commit is contained in:
Archer
2026-03-31 23:15:29 +08:00
committed by GitHub
parent 8a2b321296
commit d5ea3179a0
43 changed files with 2740 additions and 584 deletions
Download Patch File Download Diff File Expand all files Collapse all files
document/content/docs/self-host/deploy/docker.en.mdx
+9 -10
View File
@@ -87,7 +87,7 @@ curl -L https://github.com/docker/compose/releases/download/v2.20.3/docker-compo
chmod +x /usr/local/bin/docker-compose
# Verify installation
docker -v
docker-compose -v
docker compose -v
# If it fails, search online for solutions
```
</Tab>
@@ -173,7 +173,7 @@ Run in the same directory as docker-compose.yml. Ensure `docker-compose` version
```bash
# Start containers
docker-compose up -d
docker compose --profile prepull pull agent-sandbox-image && docker compose up -d
```
### 5. Access FastGPT
@@ -260,8 +260,8 @@ mongo:
3. Restart services:
```bash
docker-compose down
docker-compose up -d
docker compose down
docker compose up -d
```
4. Enter the container and initialize the replica set:
@@ -296,8 +296,8 @@ By default, OneAPI connection address and key are configured. Modify the environ
After modifying, restart:
```bash
docker-compose down
docker-compose up -d
docker compose down
docker compose up -d
```
### How to Update Versions?
@@ -307,15 +307,14 @@ docker-compose up -d
3. Run these commands to pull and restart:
```bash
docker-compose pull
docker-compose up -d
docker compose up -d
```
4. Run initialization scripts (if any)
### 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/self-host/config/json).
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
@@ -326,7 +325,7 @@ Modify `config.json`, then run `docker-compose down` followed by `docker-compose
1. Incorrect mount directory
2. Invalid config file — logs will show `invalid json`. The file must be valid JSON.
3. Didn't run `docker-compose down` then `docker-compose up -d` after changes. A simple restart doesn't remount files.
3. Didn't run `docker compose down` then `docker compose up -d` after changes. A simple restart doesn't remount files.
### How to Check if Environment Variables Loaded
document/content/docs/self-host/deploy/docker.mdx
+10 -10
View File
@@ -87,7 +87,7 @@ curl -L https://github.com/docker/compose/releases/download/v2.20.3/docker-compo
chmod +x /usr/local/bin/docker-compose
# 验证安装
docker -v
docker-compose -v
docker compose -v
# 如失效，自行百度~
```
</Tab>
@@ -173,7 +173,8 @@ bash <(curl -fsSL https://doc.fastgpt.cn/deploy/install.sh)
```bash
# 启动容器
docker-compose up -d
docker compose --profile prepull pull agent-sandbox-image && dockercompose up -d
```
### 5. 访问 FastGPT
@@ -261,8 +262,8 @@ mongo:
3. 重启服务
```bash
docker-compose down
docker-compose up -d
docker compose down
docker compose up -d
```
4. 进入容器执行副本集合初始化
@@ -297,8 +298,8 @@ rs.status()
修改完后重启：
```bash
docker-compose down
docker-compose up -d
docker compose down
docker compose up -d
```
### 如何更新版本？
@@ -308,15 +309,14 @@ docker-compose up -d
3. 执行下面命令会自动拉取镜像：
```bash
docker-compose pull
docker-compose up -d
docker compose up -d
```
4. 执行初始化脚本（如果有）
### 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/self-host/config/json)。
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
@@ -327,7 +327,7 @@ docker-compose up -d
1. 挂载目录不正确
2. 配置文件不正确，日志中会提示`invalid json`，配置文件需要是标准的 JSON 文件。
3. 修改后，没有`docker-compose down`再`docker-compose up -d`，restart是不会重新挂载文件的。
3. 修改后，没有`docker compose down`再`docker compose up -d`，restart是不会重新挂载文件的。
### 如何检查环境变量是否正常加载
document/content/docs/self-host/upgrading/4-14/41410.en.mdx
+76
View File
@@ -0,0 +1,76 @@
---
title: 'V4.14.10'
description: 'FastGPT V4.14.10 Release Notes'
---
## Upgrade Guide
### 1. Add agent-sandbox related configurations
The following configuration adjustments are for `docker compose` deployments. `sealos` commercial users can contact support for an online sandbox service solution.
Open the [latest yml deployment file](https://github.com/labring/FastGPT/blob/main/deploy/docker/global/docker-compose.pg.yml) and add the following:
1. Add the `x-volume-manager-auth-token: &x-volume-manager-auth-token 'vmtoken'` variable configuration at the top of the file.
2. Add 3 new services: `opensandbox-server`, `volume-manager`, and `agent-sandbox-image`.
3. Add `configs` (you can find this content at the bottom of the file, just copy and append it directly).
4. Modify the `fastgpt` environment variables to include the following:
```bash
# ==================== Agent sandbox config ====================
AGENT_SANDBOX_PROVIDER: opensandbox
# OpenSandbox config (effective when PROVIDER: opensandbox)
AGENT_SANDBOX_OPENSANDBOX_BASEURL: http://opensandbox-server:8090
AGENT_SANDBOX_OPENSANDBOX_API_KEY:
AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: ghcr.io/labring/fastgpt/fastgpt-agent-sandbox
AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.0.2
# Volume persistence config (optional under opensandbox provider)
AGENT_SANDBOX_ENABLE_VOLUME: true
AGENT_SANDBOX_VOLUME_MANAGER_URL: http://volume-manager:3000
AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
```
### 2. Modify the sandbox image name
The image name under the original `sandbox` services needs to be changed from `fastgpt-sandbox` to `fastgpt-code-sandbox`.
### 3. Update image tags
- Update FastGPT image tag to: `v4.14.10`
- Update FastGPT commercial image tag to: `v4.14.10`
- Update fastgpt-plugin image tag to: `v0.5.6`
- Update code-sandbox image tag to: `v4.14.10`
Restart the service after updating.
### 4. Update system tools and refresh icons
Some system tool icons have been removed and replaced with image links, so some tool icons will be lost. You can update the system tools again (uninstall and reinstall, or directly import the pkg to overwrite).
## 🚀 Features
1. Added OpenSandbox docker deployment and adaptation, with support for data persistence via mounted volumes.
2. Added sandbox file link reading tool, allowing AI to directly return file access links.
3. Added WeChat Personal Account publishing channel.
4. Added streaming output support for Lark publishing channel.
5. The maximum directory limit can now be configured via environment variables.
6. Added max limit configuration for rerank models to prevent rerank failures caused by exceeding the single document limit.
7. Added tiered billing mode for LLMs and unified the billing push method.
## ⚙️ Optimizations
1. Optimized workflow runtime to reduce computational complexity.
2. Added calculation limits for large variables to prevent thread blocking caused by high computational complexity.
3. Removed configurations like "Used for knowledge base file processing" and "Used for question classification" from model settings, and unified them with a "Test Model" flag. Test models will have a special identifier and can only be used in AI chat; they will be filtered out in other scenarios.
## 🐛 Bug Fixes
1. Fixed an issue where the default values of global variables in sub-workflows were not taking effect.
2. Fixed an issue where the configured rerank model was not displaying in agent mode.
3. Fixed an issue where the output of the bge-m3 embedding vector model was always 0.
4. Fixed a call failure caused by connection exceptions during concurrent MCP calls.
5. Fixed security vulnerabilities in the login API.
6. Fixed MCP SSRF security vulnerabilities.
7. Fixed an issue where workflow tool errors were not properly caught.
8. Fixed an issue where the default values of global variables in sub-workflows were not taking effect.
document/content/docs/self-host/upgrading/4-14/41410.mdx
+57 -10
View File
@@ -1,21 +1,64 @@
---
title: 'V4.14.10(进行中)'
title: 'V4.14.10'
description: 'FastGPT V4.14.10 更新说明'
---
## 注意
## 升级指南
1. 代码沙盒镜像名变更: `{{hub}}/fastgpt-sandbox` -> `{{hub}}/fastgpt-code-sandbox`
2. 系统工具部分头像，移除了 icon，都转用图片链接，如果丢失了头像，可以重新更新一次系统工具（卸载再安装，或者直接导入 pkg 覆盖）
### 1. 增加 agent-sandbox 相关配置
以下针对的是 `docker compose` 部署方案的配置调整，使用`sealos`的商业版用户，可私信支持人员，提供在线的沙盒服务方案。
打开[最新 yml 部署文件](https://github.com/labring/FastGPT/blob/main/deploy/docker/cn/docker-compose.pg.yml)，调整以下内容：
1. 在文件顶部增加 `x-volume-manager-auth-token: &x-volume-manager-auth-token 'vmtoken'` 变量配置。
2. 增加 3 组 services: `opensandbox-server`,`volume-manager`,`agent-sandbox-image`
3. 增加 `configs`, 文件底部可找到该内容，直接复制添加。
4. 修改 `fastgpt` 环境变量， 增加以下变量：
```bash
# ==================== Agent sandbox 配置 ====================
AGENT_SANDBOX_PROVIDER: opensandbox
# OpenSandbox 配置（PROVIDER: opensandbox 时生效）
AGENT_SANDBOX_OPENSANDBOX_BASEURL: http://opensandbox-server:8090
AGENT_SANDBOX_OPENSANDBOX_API_KEY:
AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox
AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.0.2
# Volume 持久化配置（opensandbox provider 下可选）
AGENT_SANDBOX_ENABLE_VOLUME: true
AGENT_SANDBOX_VOLUME_MANAGER_URL: http://volume-manager:3000
AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
```
### 2. 修改 sandbox 镜像名
原先的 `sandbox` 服务的镜像名，需要从`fastgpt-sandbox`改成`fastgpt-code-sandbox`。
目的是为了区分 agent-sandbox 和 code-sandbox。
### 3. 更新镜像 tag
- 更新 FastGPT 镜像 tag: v4.14.10
- 更新 FastGPT 商业版镜像 tag: v4.14.10
- 更新 code-sandbox 镜像 tag: v4.14.10
- 更新 fastgpt-plugin 镜像 tag: v0.5.6
更新完后即可重启服务。
### 4. 更新系统工具，刷新头像
系统工具部分头像，移除了 icon，都转用图片链接，所以会丢失一部分工具的头像。可以重新更新一次系统工具（卸载再安装，或者直接导入 pkg 覆盖）。
## 🚀 新增内容
1. 增加 OpenSandbox docker 部署方案及适配，并支持通过挂载 volumn 进行数据持久化。
1. 增加 OpenSandbox docker 部署方案及适配，并支持通过挂载 volume 进行数据持久化。
2. 新增沙盒读取文件链接工具，可以直接让 AI 返回文件的访问链接。
3. 飞书发布渠道，支持流输出。
4. 目录最大上限，可通过环境变量配置。
5. rerank 模型上限配置，避免超出单条 document 上限导致 rerank 失败。
6. 增加 LLM 梯度计量计费模式，同时统一计费推送方式。
3. 新增微信个人号发布渠道
4. 飞书发布渠道，支持流输出。
5. 目录最大上限，可通过环境变量配置。
6. rerank 模型上限配置，避免超出单条 document 上限导致 rerank 失败。
7. 增加 LLM 梯度计量计费模式，同时统一计费推送方式。
## ⚙️ 优化
@@ -28,4 +71,8 @@ description: 'FastGPT V4.14.10 更新说明'
1. 子工作流的全局变量默认值未生效。
2. agent 模式下已配的 rerank 模型不显示。
3. bge-m3 embedding 向量模型输出都为 0 的问题。
4. MCP 并发调用时，连接异常导致调用失败。
4. MCP 并发调用时，连接异常导致调用失败。
5. 修复登录接口安全问题
6. 修复 MCP SSRF 安全问题
7. 修复工作流工具错误未成功捕获问题
8. 修复子工作流全局变量默认值未生效
document/content/docs/self-host/upgrading/4-14/meta.en.json
+1 -1
View File
@@ -1,5 +1,5 @@
{
"title": "4.14.x",
"description": "",
"pages": ["4149", "4148", "4147", "4146", "41451", "4145", "4144", "4143", "4142", "4141", "4140"]
"pages": ["41410", "4149", "4148", "4147", "4146", "41451", "4145", "4144", "4143", "4142", "4141", "4140"]
}
document/content/docs/toc.en.mdx
+1
View File
@@ -113,6 +113,7 @@ description: FastGPT Toc
- [/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/4-14/41410](/en/docs/self-host/upgrading/4-14/41410)
- [/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)