Compare commits
64 Commits
v4.8.21-fi
...
v4.9.0-alp
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
081a843d7e | ||
|
|
e53646d13e | ||
|
|
693db35a42 | ||
|
|
9717be8522 | ||
|
|
02685f7a3e | ||
|
|
e1b021af71 | ||
|
|
051b590284 | ||
|
|
60f0c18997 | ||
|
|
6a3bd30add | ||
|
|
2c89752f67 | ||
|
|
139b142293 | ||
|
|
3fadabd28b | ||
|
|
dbf25cef88 | ||
|
|
b2e2fa6b76 | ||
|
|
576c60bd55 | ||
|
|
33617ab5dc | ||
|
|
b4dda6a41b | ||
|
|
e860c56b77 | ||
|
|
efac5312b4 | ||
|
|
4bc7f21182 | ||
|
|
113e8f711f | ||
|
|
abc6dffb41 | ||
|
|
f7b2a57ca3 | ||
|
|
cf0aaa1091 | ||
|
|
ac4255ea0c | ||
|
|
df4d6f86ce | ||
|
|
e697fda82f | ||
|
|
1aa319e7aa | ||
|
|
fc9e614f88 | ||
|
|
1121ea33bd | ||
|
|
9bbee60cde | ||
|
|
9f57ad0017 | ||
|
|
c3d3b30d7e | ||
|
|
fb0eb49196 | ||
|
|
27ebd2e8cf | ||
|
|
81a06718d8 | ||
|
|
3c382d1240 | ||
|
|
747bb303ec | ||
|
|
cf9c8e9f6a | ||
|
|
5d5bee9e41 | ||
|
|
4f0dd96699 | ||
|
|
fb6dbaf2d6 | ||
|
|
ffc1520f4c | ||
|
|
255764400f | ||
|
|
3bfe802c48 | ||
|
|
2bf17dbb87 | ||
|
|
8d766372fe | ||
|
|
ca5717936b | ||
|
|
6762723b10 | ||
|
|
8604cbd021 | ||
|
|
206325bc5f | ||
|
|
5fd520c794 | ||
|
|
09205e4666 | ||
|
|
ccf28d83b8 | ||
|
|
420aaad48e | ||
|
|
8ba2339890 | ||
|
|
e7b8934367 | ||
|
|
3e13397614 | ||
|
|
b14674cc6f | ||
|
|
4d20274a97 | ||
|
|
4447e40364 | ||
|
|
23949230ee | ||
|
|
cd7a897304 | ||
|
|
18aff8b8db |
@@ -26,7 +26,7 @@ jobs:
|
||||
with:
|
||||
driver-opts: network=host
|
||||
- name: Cache Docker layers
|
||||
uses: actions/cache@v2
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: /tmp/.buildx-cache
|
||||
key: ${{ runner.os }}-buildx-${{ github.sha }}
|
||||
@@ -108,7 +108,7 @@ jobs:
|
||||
with:
|
||||
driver-opts: network=host
|
||||
- name: Cache Docker layers
|
||||
uses: actions/cache@v2
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: /tmp/.buildx-cache
|
||||
key: ${{ runner.os }}-buildx-${{ github.sha }}
|
||||
@@ -191,7 +191,7 @@ jobs:
|
||||
with:
|
||||
driver-opts: network=host
|
||||
- name: Cache Docker layers
|
||||
uses: actions/cache@v2
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: /tmp/.buildx-cache
|
||||
key: ${{ runner.os }}-buildx-${{ github.sha }}
|
||||
@@ -68,14 +68,3 @@ jobs:
|
||||
SEALOS_TYPE: 'pr_comment'
|
||||
SEALOS_FILENAME: 'report.md'
|
||||
SEALOS_REPLACE_TAG: 'DEFAULT_REPLACE_DEPLOY'
|
||||
|
||||
helm-check:
|
||||
runs-on: ubuntu-20.04
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v3
|
||||
- name: Helm Check
|
||||
run: |
|
||||
helm dependency update files/helm/fastgpt
|
||||
helm lint files/helm/fastgpt
|
||||
helm package files/helm/fastgpt
|
||||
4
.github/workflows/helm-release.yaml
vendored
@@ -24,6 +24,6 @@ jobs:
|
||||
export APP_VERSION=${{ steps.vars.outputs.tag }}
|
||||
export HELM_VERSION=${{ steps.vars.outputs.tag }}
|
||||
export HELM_REPO=ghcr.io/${{ github.repository_owner }}
|
||||
helm dependency update files/helm/fastgpt
|
||||
helm package files/helm/fastgpt --version ${HELM_VERSION}-helm --app-version ${APP_VERSION} -d bin
|
||||
helm dependency update deploy/helm/fastgpt
|
||||
helm package deploy/helm/fastgpt --version ${HELM_VERSION}-helm --app-version ${APP_VERSION} -d bin
|
||||
helm push bin/fastgpt-${HELM_VERSION}-helm.tgz oci://${HELM_REPO}
|
||||
|
||||
@@ -25,7 +25,7 @@ jobs:
|
||||
with:
|
||||
driver-opts: network=host
|
||||
- name: Cache Docker layers
|
||||
uses: actions/cache@v2
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: /tmp/.buildx-cache
|
||||
key: ${{ runner.os }}-buildx-${{ github.sha }}
|
||||
2
.vscode/nextapi.code-snippets
vendored
@@ -58,7 +58,7 @@
|
||||
"body": [
|
||||
"import '@/pages/api/__mocks__/base';",
|
||||
"import { root } from '@/pages/api/__mocks__/db/init';",
|
||||
"import { getTestRequest } from '@/test/utils';",
|
||||
"import { getTestRequest } from '@fastgpt/service/test/utils'; ;",
|
||||
"import { AppErrEnum } from '@fastgpt/global/common/error/code/app';",
|
||||
"import handler from './demo';",
|
||||
"",
|
||||
|
||||
4
.vscode/settings.json
vendored
@@ -27,7 +27,5 @@
|
||||
},
|
||||
"markdown.copyFiles.destination": {
|
||||
"/docSite/content/**/*": "${documentWorkspaceFolder}/docSite/assets/imgs/"
|
||||
},
|
||||
"markdown.copyFiles.overwriteBehavior": "nameIncrementally",
|
||||
"markdown.copyFiles.transformPath": "const filename = uri.path.split('/').pop(); return `/imgs/${filename}`;"
|
||||
}
|
||||
}
|
||||
24
README.md
@@ -114,16 +114,6 @@ https://github.com/labring/FastGPT/assets/15308462/7d3a38df-eb0e-4388-9250-2409b
|
||||
<img src="https://img.shields.io/badge/-返回顶部-7d09f1.svg" alt="#" align="right">
|
||||
</a>
|
||||
|
||||
## 🏘️ 社区交流群
|
||||
|
||||
扫码加入飞书话题群:
|
||||
|
||||

|
||||
|
||||
<a href="#readme">
|
||||
<img src="https://img.shields.io/badge/-返回顶部-7d09f1.svg" alt="#" align="right">
|
||||
</a>
|
||||
|
||||
## 🏘️ 加入我们
|
||||
|
||||
我们正在寻找志同道合的小伙伴,加速 FastGPT 的发展。你可以通过 [FastGPT 2025 招聘](https://fael3z0zfze.feishu.cn/wiki/P7FOwEmPziVcaYkvVaacnVX1nvg)了解 FastGPT 的招聘信息。
|
||||
@@ -133,17 +123,25 @@ https://github.com/labring/FastGPT/assets/15308462/7d3a38df-eb0e-4388-9250-2409b
|
||||
- [Laf:3 分钟快速接入三方应用](https://github.com/labring/laf)
|
||||
- [Sealos:快速部署集群应用](https://github.com/labring/sealos)
|
||||
- [One API:多模型管理,支持 Azure、文心一言等](https://github.com/songquanpeng/one-api)
|
||||
- [TuShan:5 分钟搭建后台管理系统](https://github.com/msgbyte/tushan)
|
||||
|
||||
<a href="#readme">
|
||||
<img src="https://img.shields.io/badge/-返回顶部-7d09f1.svg" alt="#" align="right">
|
||||
</a>
|
||||
|
||||
|
||||
## 🌿 第三方生态
|
||||
|
||||
- [COW 个人微信/企微机器人](https://doc.tryfastgpt.ai/docs/use-cases/external-integration/onwechat/)
|
||||
- [SiliconCloud (硅基流动) —— 开源模型在线体验平台](https://cloud.siliconflow.cn/i/TR9Ym0c4)
|
||||
- [COW 个人微信/企微机器人](https://doc.tryfastgpt.ai/docs/use-cases/external-integration/onwechat/)
|
||||
|
||||
<a href="#readme">
|
||||
<img src="https://img.shields.io/badge/-返回顶部-7d09f1.svg" alt="#" align="right">
|
||||
</a>
|
||||
|
||||
## 🏘️ 社区交流群
|
||||
|
||||
扫码加入飞书话题群:
|
||||
|
||||

|
||||
|
||||
<a href="#readme">
|
||||
<img src="https://img.shields.io/badge/-返回顶部-7d09f1.svg" alt="#" align="right">
|
||||
|
||||
26
SECURITY.md
Normal file
@@ -0,0 +1,26 @@
|
||||
# 安全策略
|
||||
|
||||
## 漏洞报告
|
||||
|
||||
如果您发现了 FastGPT 的安全漏洞,请按照以下步骤进行报告:
|
||||
|
||||
1. **报告方式**
|
||||
发送邮件至:yujinlong@sealos.io
|
||||
请备注版本以及您的 GitHub 账号
|
||||
|
||||
3. **响应时间**
|
||||
- 我们会在 48 小时内确认收到您的报告
|
||||
- 一般在 3 个工作日内给出初步评估结果
|
||||
|
||||
4. **漏洞处理流程**
|
||||
- 确认漏洞:我们会验证漏洞的存在性和影响范围
|
||||
- 修复开发:针对已确认的漏洞进行修复
|
||||
- 版本发布:在下一个版本更新中发布安全补丁
|
||||
- 公开披露:在修复完成后,我们会在更新日志中公布相关信息
|
||||
|
||||
5. **注意事项**
|
||||
- 在漏洞未修复前,请勿公开披露漏洞详情
|
||||
- 我们欢迎负责任的漏洞披露
|
||||
- 对于重大贡献者,我们会在项目致谢名单中提及
|
||||
|
||||
感谢您为 FastGPT 的安全性做出贡献!
|
||||
@@ -114,15 +114,15 @@ services:
|
||||
# fastgpt
|
||||
sandbox:
|
||||
container_name: sandbox
|
||||
image: ghcr.io/labring/fastgpt-sandbox:v4.8.20-fix2 # git
|
||||
# image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.20-fix2 # 阿里云
|
||||
image: ghcr.io/labring/fastgpt-sandbox:v4.8.23-fix # git
|
||||
# image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.23-fix # 阿里云
|
||||
networks:
|
||||
- fastgpt
|
||||
restart: always
|
||||
fastgpt:
|
||||
container_name: fastgpt
|
||||
image: ghcr.io/labring/fastgpt:v4.8.20-fix2 # git
|
||||
# image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.8.20-fix2 # 阿里云
|
||||
image: ghcr.io/labring/fastgpt:v4.8.23-fix # git
|
||||
# image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.8.23-fix # 阿里云
|
||||
ports:
|
||||
- 3000:3000
|
||||
networks:
|
||||
@@ -133,14 +133,17 @@ services:
|
||||
- sandbox
|
||||
restart: always
|
||||
environment:
|
||||
# 前端访问地址: http://localhost:3000
|
||||
# 前端外部可访问的地址,用于自动补全文件资源路径。例如 https:fastgpt.cn,不能填 localhost。这个值可以不填,不填则发给模型的图片会是一个相对路径,而不是全路径,模型可能伪造Host。
|
||||
- FE_DOMAIN=
|
||||
# root 密码,用户名为: root。如果需要修改 root 密码,直接修改这个环境变量,并重启即可。
|
||||
- DEFAULT_ROOT_PSW=1234
|
||||
# AI模型的API地址哦。务必加 /v1。这里默认填写了OneApi的访问地址。
|
||||
- OPENAI_BASE_URL=http://oneapi:3000/v1
|
||||
# AI模型的API Key。(这里默认填写了OneAPI的快速默认key,测试通后,务必及时修改)
|
||||
- CHAT_API_KEY=sk-fastgpt
|
||||
# AI Proxy 的地址,如果配了该地址,优先使用
|
||||
- AIPROXY_API_ENDPOINT=http://aiproxy:3000
|
||||
# AI Proxy 的 Admin Token,与 AI Proxy 中的环境变量 ADMIN_KEY
|
||||
- AIPROXY_API_TOKEN=aiproxy
|
||||
# 模型中转地址(如果用了 AI Proxy,下面 2 个就不需要了,旧版 OneAPI 用户,使用下面的变量)
|
||||
# - OPENAI_BASE_URL=http://oneapi:3000/v1
|
||||
# - CHAT_API_KEY=sk-fastgpt
|
||||
# 数据库最大连接数
|
||||
- DB_MAX_LINK=30
|
||||
# 登录凭证密钥
|
||||
@@ -170,48 +173,54 @@ services:
|
||||
volumes:
|
||||
- ./config.json:/app/data/config.json
|
||||
|
||||
# oneapi
|
||||
mysql:
|
||||
image: registry.cn-hangzhou.aliyuncs.com/fastgpt/mysql:8.0.36 # 阿里云
|
||||
# image: mysql:8.0.36
|
||||
container_name: mysql
|
||||
restart: always
|
||||
ports:
|
||||
- 3306:3306
|
||||
networks:
|
||||
- fastgpt
|
||||
command: --default-authentication-plugin=mysql_native_password
|
||||
environment:
|
||||
# 默认root密码,仅首次运行有效
|
||||
MYSQL_ROOT_PASSWORD: oneapimmysql
|
||||
MYSQL_DATABASE: oneapi
|
||||
volumes:
|
||||
- ./mysql:/var/lib/mysql
|
||||
oneapi:
|
||||
container_name: oneapi
|
||||
image: ghcr.io/songquanpeng/one-api:v0.6.7
|
||||
# image: registry.cn-hangzhou.aliyuncs.com/fastgpt/one-api:v0.6.6 # 阿里云
|
||||
ports:
|
||||
- 3001:3000
|
||||
# AI Proxy
|
||||
aiproxy:
|
||||
image: 'ghcr.io/labring/sealos-aiproxy-service:latest'
|
||||
container_name: aiproxy
|
||||
restart: unless-stopped
|
||||
depends_on:
|
||||
- mysql
|
||||
aiproxy_pg:
|
||||
condition: service_healthy
|
||||
ports:
|
||||
- '3002:3000'
|
||||
networks:
|
||||
- fastgpt
|
||||
restart: always
|
||||
environment:
|
||||
# mysql 连接参数
|
||||
- SQL_DSN=root:oneapimmysql@tcp(mysql:3306)/oneapi
|
||||
# 登录凭证加密密钥
|
||||
- SESSION_SECRET=oneapikey
|
||||
# 内存缓存
|
||||
- MEMORY_CACHE_ENABLED=true
|
||||
# 启动聚合更新,减少数据交互频率
|
||||
- BATCH_UPDATE_ENABLED=true
|
||||
# 聚合更新时长
|
||||
- BATCH_UPDATE_INTERVAL=10
|
||||
# 初始化的 root 密钥(建议部署完后更改,否则容易泄露)
|
||||
- INITIAL_ROOT_TOKEN=fastgpt
|
||||
# 对应 fastgpt 里的AIPROXY_API_TOKEN
|
||||
- ADMIN_KEY=aiproxy
|
||||
# 错误日志详情保存时间(小时)
|
||||
- LOG_DETAIL_STORAGE_HOURS=1
|
||||
# 数据库连接地址
|
||||
- SQL_DSN=postgres://postgres:aiproxy@aiproxy_pg:5432/aiproxy
|
||||
# 最大重试次数
|
||||
- RetryTimes=3
|
||||
# 不需要计费
|
||||
- BILLING_ENABLED=false
|
||||
# 不需要严格检测模型
|
||||
- DISABLE_MODEL_CONFIG=true
|
||||
healthcheck:
|
||||
test: ['CMD', 'curl', '-f', 'http://localhost:3000/api/status']
|
||||
interval: 5s
|
||||
timeout: 5s
|
||||
retries: 10
|
||||
aiproxy_pg:
|
||||
# image: pgvector/pgvector:0.8.0-pg15 # docker hub
|
||||
image: registry.cn-hangzhou.aliyuncs.com/fastgpt/pgvector:v0.8.0-pg15 # 阿里云
|
||||
restart: unless-stopped
|
||||
container_name: aiproxy_pg
|
||||
volumes:
|
||||
- ./oneapi:/data
|
||||
- ./aiproxy_pg:/var/lib/postgresql/data
|
||||
networks:
|
||||
- fastgpt
|
||||
environment:
|
||||
TZ: Asia/Shanghai
|
||||
POSTGRES_USER: postgres
|
||||
POSTGRES_DB: aiproxy
|
||||
POSTGRES_PASSWORD: aiproxy
|
||||
healthcheck:
|
||||
test: ['CMD', 'pg_isready', '-U', 'postgres', '-d', 'aiproxy']
|
||||
interval: 5s
|
||||
timeout: 5s
|
||||
retries: 10
|
||||
networks:
|
||||
fastgpt:
|
||||
@@ -7,12 +7,12 @@ version: '3.3'
|
||||
services:
|
||||
# db
|
||||
pg:
|
||||
image: pgvector/pgvector:0.7.0-pg15 # docker hub
|
||||
# image: registry.cn-hangzhou.aliyuncs.com/fastgpt/pgvector:v0.7.0 # 阿里云
|
||||
image: pgvector/pgvector:0.8.0-pg15 # docker hub
|
||||
# image: registry.cn-hangzhou.aliyuncs.com/fastgpt/pgvector:v0.8.0-pg15 # 阿里云
|
||||
container_name: pg
|
||||
restart: always
|
||||
ports: # 生产环境建议不要暴露
|
||||
- 5432:5432
|
||||
# ports: # 生产环境建议不要暴露
|
||||
# - 5432:5432
|
||||
networks:
|
||||
- fastgpt
|
||||
environment:
|
||||
@@ -72,15 +72,15 @@ services:
|
||||
# fastgpt
|
||||
sandbox:
|
||||
container_name: sandbox
|
||||
image: ghcr.io/labring/fastgpt-sandbox:v4.8.21 # git
|
||||
# image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.21 # 阿里云
|
||||
image: ghcr.io/labring/fastgpt-sandbox:v4.8.23-fix # git
|
||||
# image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.23-fix # 阿里云
|
||||
networks:
|
||||
- fastgpt
|
||||
restart: always
|
||||
fastgpt:
|
||||
container_name: fastgpt
|
||||
image: ghcr.io/labring/fastgpt:v4.8.21 # git
|
||||
# image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.8.21 # 阿里云
|
||||
image: ghcr.io/labring/fastgpt:v4.8.23-fix # git
|
||||
# image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.8.23-fix # 阿里云
|
||||
ports:
|
||||
- 3000:3000
|
||||
networks:
|
||||
@@ -91,14 +91,17 @@ services:
|
||||
- sandbox
|
||||
restart: always
|
||||
environment:
|
||||
# 前端访问地址: http://localhost:3000
|
||||
# 前端外部可访问的地址,用于自动补全文件资源路径。例如 https:fastgpt.cn,不能填 localhost。这个值可以不填,不填则发给模型的图片会是一个相对路径,而不是全路径,模型可能伪造Host。
|
||||
- FE_DOMAIN=
|
||||
# root 密码,用户名为: root。如果需要修改 root 密码,直接修改这个环境变量,并重启即可。
|
||||
- DEFAULT_ROOT_PSW=1234
|
||||
# AI模型的API地址哦。务必加 /v1。这里默认填写了OneApi的访问地址。
|
||||
- OPENAI_BASE_URL=http://oneapi:3000/v1
|
||||
# AI模型的API Key。(这里默认填写了OneAPI的快速默认key,测试通后,务必及时修改)
|
||||
- CHAT_API_KEY=sk-fastgpt
|
||||
# AI Proxy 的地址,如果配了该地址,优先使用
|
||||
- AIPROXY_API_ENDPOINT=http://aiproxy:3000
|
||||
# AI Proxy 的 Admin Token,与 AI Proxy 中的环境变量 ADMIN_KEY
|
||||
- AIPROXY_API_TOKEN=aiproxy
|
||||
# 模型中转地址(如果用了 AI Proxy,下面 2 个就不需要了,旧版 OneAPI 用户,使用下面的变量)
|
||||
# - OPENAI_BASE_URL=http://oneapi:3000/v1
|
||||
# - CHAT_API_KEY=sk-fastgpt
|
||||
# 数据库最大连接数
|
||||
- DB_MAX_LINK=30
|
||||
# 登录凭证密钥
|
||||
@@ -127,48 +130,54 @@ services:
|
||||
volumes:
|
||||
- ./config.json:/app/data/config.json
|
||||
|
||||
# oneapi
|
||||
mysql:
|
||||
# image: registry.cn-hangzhou.aliyuncs.com/fastgpt/mysql:8.0.36 # 阿里云
|
||||
image: mysql:8.0.36
|
||||
container_name: mysql
|
||||
restart: always
|
||||
ports:
|
||||
- 3306:3306
|
||||
networks:
|
||||
- fastgpt
|
||||
command: --default-authentication-plugin=mysql_native_password
|
||||
environment:
|
||||
# 默认root密码,仅首次运行有效
|
||||
MYSQL_ROOT_PASSWORD: oneapimmysql
|
||||
MYSQL_DATABASE: oneapi
|
||||
volumes:
|
||||
- ./mysql:/var/lib/mysql
|
||||
oneapi:
|
||||
container_name: oneapi
|
||||
image: ghcr.io/songquanpeng/one-api:v0.6.7
|
||||
# image: registry.cn-hangzhou.aliyuncs.com/fastgpt/one-api:v0.6.6 # 阿里云
|
||||
ports:
|
||||
- 3001:3000
|
||||
# AI Proxy
|
||||
aiproxy:
|
||||
image: 'ghcr.io/labring/sealos-aiproxy-service:latest'
|
||||
container_name: aiproxy
|
||||
restart: unless-stopped
|
||||
depends_on:
|
||||
- mysql
|
||||
aiproxy_pg:
|
||||
condition: service_healthy
|
||||
ports:
|
||||
- '3002:3000'
|
||||
networks:
|
||||
- fastgpt
|
||||
restart: always
|
||||
environment:
|
||||
# mysql 连接参数
|
||||
- SQL_DSN=root:oneapimmysql@tcp(mysql:3306)/oneapi
|
||||
# 登录凭证加密密钥
|
||||
- SESSION_SECRET=oneapikey
|
||||
# 内存缓存
|
||||
- MEMORY_CACHE_ENABLED=true
|
||||
# 启动聚合更新,减少数据交互频率
|
||||
- BATCH_UPDATE_ENABLED=true
|
||||
# 聚合更新时长
|
||||
- BATCH_UPDATE_INTERVAL=10
|
||||
# 初始化的 root 密钥(建议部署完后更改,否则容易泄露)
|
||||
- INITIAL_ROOT_TOKEN=fastgpt
|
||||
# 对应 fastgpt 里的AIPROXY_API_TOKEN
|
||||
- ADMIN_KEY=aiproxy
|
||||
# 错误日志详情保存时间(小时)
|
||||
- LOG_DETAIL_STORAGE_HOURS=1
|
||||
# 数据库连接地址
|
||||
- SQL_DSN=postgres://postgres:aiproxy@aiproxy_pg:5432/aiproxy
|
||||
# 最大重试次数
|
||||
- RetryTimes=3
|
||||
# 不需要计费
|
||||
- BILLING_ENABLED=false
|
||||
# 不需要严格检测模型
|
||||
- DISABLE_MODEL_CONFIG=true
|
||||
healthcheck:
|
||||
test: ['CMD', 'curl', '-f', 'http://localhost:3000/api/status']
|
||||
interval: 5s
|
||||
timeout: 5s
|
||||
retries: 10
|
||||
aiproxy_pg:
|
||||
# image: pgvector/pgvector:0.8.0-pg15 # docker hub
|
||||
image: registry.cn-hangzhou.aliyuncs.com/fastgpt/pgvector:v0.8.0-pg15 # 阿里云
|
||||
restart: unless-stopped
|
||||
container_name: aiproxy_pg
|
||||
volumes:
|
||||
- ./oneapi:/data
|
||||
- ./aiproxy_pg:/var/lib/postgresql/data
|
||||
networks:
|
||||
- fastgpt
|
||||
environment:
|
||||
TZ: Asia/Shanghai
|
||||
POSTGRES_USER: postgres
|
||||
POSTGRES_DB: aiproxy
|
||||
POSTGRES_PASSWORD: aiproxy
|
||||
healthcheck:
|
||||
test: ['CMD', 'pg_isready', '-U', 'postgres', '-d', 'aiproxy']
|
||||
interval: 5s
|
||||
timeout: 5s
|
||||
retries: 10
|
||||
networks:
|
||||
fastgpt:
|
||||
@@ -53,15 +53,15 @@ services:
|
||||
wait $$!
|
||||
sandbox:
|
||||
container_name: sandbox
|
||||
image: ghcr.io/labring/fastgpt-sandbox:v4.8.20-fix2 # git
|
||||
# image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.20-fix2 # 阿里云
|
||||
image: ghcr.io/labring/fastgpt-sandbox:v4.8.23-fix # git
|
||||
# image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.23-fix # 阿里云
|
||||
networks:
|
||||
- fastgpt
|
||||
restart: always
|
||||
fastgpt:
|
||||
container_name: fastgpt
|
||||
image: ghcr.io/labring/fastgpt:v4.8.20-fix2 # git
|
||||
# image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.8.20-fix2 # 阿里云
|
||||
image: ghcr.io/labring/fastgpt:v4.8.23-fix # git
|
||||
# image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.8.23-fix # 阿里云
|
||||
ports:
|
||||
- 3000:3000
|
||||
networks:
|
||||
@@ -71,14 +71,17 @@ services:
|
||||
- sandbox
|
||||
restart: always
|
||||
environment:
|
||||
# 前端访问地址: http://localhost:3000
|
||||
# 前端外部可访问的地址,用于自动补全文件资源路径。例如 https:fastgpt.cn,不能填 localhost。这个值可以不填,不填则发给模型的图片会是一个相对路径,而不是全路径,模型可能伪造Host。
|
||||
- FE_DOMAIN=
|
||||
# root 密码,用户名为: root。如果需要修改 root 密码,直接修改这个环境变量,并重启即可。
|
||||
- DEFAULT_ROOT_PSW=1234
|
||||
# AI模型的API地址哦。务必加 /v1。这里默认填写了OneApi的访问地址。
|
||||
- OPENAI_BASE_URL=http://oneapi:3000/v1
|
||||
# AI模型的API Key。(这里默认填写了OneAPI的快速默认key,测试通后,务必及时修改)
|
||||
- CHAT_API_KEY=sk-fastgpt
|
||||
# AI Proxy 的地址,如果配了该地址,优先使用
|
||||
- AIPROXY_API_ENDPOINT=http://aiproxy:3000
|
||||
# AI Proxy 的 Admin Token,与 AI Proxy 中的环境变量 ADMIN_KEY
|
||||
- AIPROXY_API_TOKEN=aiproxy
|
||||
# 模型中转地址(如果用了 AI Proxy,下面 2 个就不需要了,旧版 OneAPI 用户,使用下面的变量)
|
||||
# - OPENAI_BASE_URL=http://oneapi:3000/v1
|
||||
# - CHAT_API_KEY=sk-fastgpt
|
||||
# 数据库最大连接数
|
||||
- DB_MAX_LINK=30
|
||||
# 登录凭证密钥
|
||||
@@ -108,48 +111,54 @@ services:
|
||||
volumes:
|
||||
- ./config.json:/app/data/config.json
|
||||
|
||||
# oneapi
|
||||
mysql:
|
||||
image: registry.cn-hangzhou.aliyuncs.com/fastgpt/mysql:8.0.36 # 阿里云
|
||||
# image: mysql:8.0.36
|
||||
container_name: mysql
|
||||
restart: always
|
||||
ports:
|
||||
- 3306:3306
|
||||
networks:
|
||||
- fastgpt
|
||||
command: --default-authentication-plugin=mysql_native_password
|
||||
environment:
|
||||
# 默认root密码,仅首次运行有效
|
||||
MYSQL_ROOT_PASSWORD: oneapimmysql
|
||||
MYSQL_DATABASE: oneapi
|
||||
volumes:
|
||||
- ./mysql:/var/lib/mysql
|
||||
oneapi:
|
||||
container_name: oneapi
|
||||
image: ghcr.io/songquanpeng/one-api:v0.6.7
|
||||
# image: registry.cn-hangzhou.aliyuncs.com/fastgpt/one-api:v0.6.6 # 阿里云
|
||||
ports:
|
||||
- 3001:3000
|
||||
# AI Proxy
|
||||
aiproxy:
|
||||
image: 'ghcr.io/labring/sealos-aiproxy-service:latest'
|
||||
container_name: aiproxy
|
||||
restart: unless-stopped
|
||||
depends_on:
|
||||
- mysql
|
||||
aiproxy_pg:
|
||||
condition: service_healthy
|
||||
ports:
|
||||
- '3002:3000'
|
||||
networks:
|
||||
- fastgpt
|
||||
restart: always
|
||||
environment:
|
||||
# mysql 连接参数
|
||||
- SQL_DSN=root:oneapimmysql@tcp(mysql:3306)/oneapi
|
||||
# 登录凭证加密密钥
|
||||
- SESSION_SECRET=oneapikey
|
||||
# 内存缓存
|
||||
- MEMORY_CACHE_ENABLED=true
|
||||
# 启动聚合更新,减少数据交互频率
|
||||
- BATCH_UPDATE_ENABLED=true
|
||||
# 聚合更新时长
|
||||
- BATCH_UPDATE_INTERVAL=10
|
||||
# 初始化的 root 密钥(建议部署完后更改,否则容易泄露)
|
||||
- INITIAL_ROOT_TOKEN=fastgpt
|
||||
# 对应 fastgpt 里的AIPROXY_API_TOKEN
|
||||
- ADMIN_KEY=aiproxy
|
||||
# 错误日志详情保存时间(小时)
|
||||
- LOG_DETAIL_STORAGE_HOURS=1
|
||||
# 数据库连接地址
|
||||
- SQL_DSN=postgres://postgres:aiproxy@aiproxy_pg:5432/aiproxy
|
||||
# 最大重试次数
|
||||
- RetryTimes=3
|
||||
# 不需要计费
|
||||
- BILLING_ENABLED=false
|
||||
# 不需要严格检测模型
|
||||
- DISABLE_MODEL_CONFIG=true
|
||||
healthcheck:
|
||||
test: ['CMD', 'curl', '-f', 'http://localhost:3000/api/status']
|
||||
interval: 5s
|
||||
timeout: 5s
|
||||
retries: 10
|
||||
aiproxy_pg:
|
||||
# image: pgvector/pgvector:0.8.0-pg15 # docker hub
|
||||
image: registry.cn-hangzhou.aliyuncs.com/fastgpt/pgvector:v0.8.0-pg15 # 阿里云
|
||||
restart: unless-stopped
|
||||
container_name: aiproxy_pg
|
||||
volumes:
|
||||
- ./oneapi:/data
|
||||
- ./aiproxy_pg:/var/lib/postgresql/data
|
||||
networks:
|
||||
- fastgpt
|
||||
environment:
|
||||
TZ: Asia/Shanghai
|
||||
POSTGRES_USER: postgres
|
||||
POSTGRES_DB: aiproxy
|
||||
POSTGRES_PASSWORD: aiproxy
|
||||
healthcheck:
|
||||
test: ['CMD', 'pg_isready', '-U', 'postgres', '-d', 'aiproxy']
|
||||
interval: 5s
|
||||
timeout: 5s
|
||||
retries: 10
|
||||
networks:
|
||||
fastgpt:
|
||||
@@ -6,6 +6,7 @@ data:
|
||||
"openapiPrefix": "fastgpt",
|
||||
"vectorMaxProcess": 15,
|
||||
"qaMaxProcess": 15,
|
||||
"vlmMaxProcess": 15,
|
||||
"pgHNSWEfSearch": 100
|
||||
},
|
||||
"llmModels": [
|
||||
BIN
docSite/assets/imgs/aiproxy-1.jpg
Normal file
|
After Width: | Height: | Size: 198 KiB |
BIN
docSite/assets/imgs/aiproxy-1.png
Normal file
|
After Width: | Height: | Size: 198 KiB |
BIN
docSite/assets/imgs/aiproxy-10.png
Normal file
|
After Width: | Height: | Size: 229 KiB |
BIN
docSite/assets/imgs/aiproxy-11.png
Normal file
|
After Width: | Height: | Size: 422 KiB |
BIN
docSite/assets/imgs/aiproxy-2.png
Normal file
|
After Width: | Height: | Size: 235 KiB |
BIN
docSite/assets/imgs/aiproxy-3.png
Normal file
|
After Width: | Height: | Size: 341 KiB |
BIN
docSite/assets/imgs/aiproxy-4.png
Normal file
|
After Width: | Height: | Size: 212 KiB |
BIN
docSite/assets/imgs/aiproxy-5.png
Normal file
|
After Width: | Height: | Size: 240 KiB |
BIN
docSite/assets/imgs/aiproxy-6.png
Normal file
|
After Width: | Height: | Size: 342 KiB |
BIN
docSite/assets/imgs/aiproxy-7.png
Normal file
|
After Width: | Height: | Size: 363 KiB |
BIN
docSite/assets/imgs/aiproxy-8.png
Normal file
|
After Width: | Height: | Size: 348 KiB |
BIN
docSite/assets/imgs/aiproxy-9.png
Normal file
|
After Width: | Height: | Size: 222 KiB |
BIN
docSite/assets/imgs/aiproxy1.png
Normal file
|
After Width: | Height: | Size: 135 KiB |
BIN
docSite/assets/imgs/appid.png
Normal file
|
After Width: | Height: | Size: 332 KiB |
BIN
docSite/assets/imgs/image copy.png
Normal file
|
After Width: | Height: | Size: 329 KiB |
BIN
docSite/assets/imgs/marker2.png
Normal file
|
After Width: | Height: | Size: 216 KiB |
BIN
docSite/assets/imgs/marker3.png
Normal file
|
After Width: | Height: | Size: 85 KiB |
@@ -23,8 +23,54 @@ weight: 707
|
||||
"systemEnv": {
|
||||
"vectorMaxProcess": 15, // 向量处理线程数量
|
||||
"qaMaxProcess": 15, // 问答拆分线程数量
|
||||
"vlmMaxProcess": 15, // 图片理解模型最大处理进程
|
||||
"tokenWorkers": 50, // Token 计算线程保持数,会持续占用内存,不能设置太大。
|
||||
"pgHNSWEfSearch": 100 // 向量搜索参数。越大,搜索越精确,但是速度越慢。设置为100,有99%+精度。
|
||||
"pgHNSWEfSearch": 100, // 向量搜索参数。越大,搜索越精确,但是速度越慢。设置为100,有99%+精度。
|
||||
"customPdfParse": { // 4.9.0 新增配置
|
||||
"url": "", // 自定义 PDF 解析服务地址
|
||||
"key": "", // 自定义 PDF 解析服务密钥
|
||||
"doc2xKey": "", // doc2x 服务密钥
|
||||
"price": 0 // PDF 解析服务价格
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## 自定义 PDF 解析配置
|
||||
|
||||
自定义 PDF 服务解析的优先级高于 Doc2x 服务,所以如果使用 Doc2x 服务,请勿配置自定义 PDF 服务。
|
||||
|
||||
### 使用 Sealos PDF 解析服务
|
||||
|
||||
#### 1. 申请 Sealos AI proxy API Key
|
||||
|
||||
[点击打开 Sealos Pdf parser 官网](https://cloud.sealos.run/?uid=fnWRt09fZP&openapp=system-aiproxy),并进行对应 API Key 的申请。
|
||||
|
||||
#### 2. 修改 FastGPT 配置文件
|
||||
|
||||
`systemEnv.customPdfParse.url`填写成`https://aiproxy.hzh.sealos.run/v1/parse/pdf?model=parse-pdf`
|
||||
`systemEnv.customPdfParse.key`填写成在 Sealos AI proxy 中申请的 API Key。
|
||||
|
||||

|
||||
|
||||
### 使用 Doc2x 解析 PDF 文件
|
||||
|
||||
`Doc2x`是一个国内提供专业 PDF 解析。
|
||||
|
||||
#### 1. 申请 Doc2x 服务
|
||||
|
||||
[点击打开 Doc2x 官网](https://doc2x.noedgeai.com?inviteCode=9EACN2),并进行对应 API Key 的申请。
|
||||
|
||||
#### 2. 修改 FastGPT 配置文件
|
||||
|
||||
开源版用户在 `config.json` 文件中添加 `systemEnv.customPdfParse.doc2xKey` 配置,并填写上申请到的 API Key。并重启服务。
|
||||
|
||||
商业版用户在 Admin 后台根据表单指引填写 Doc2x 服务密钥。
|
||||
|
||||
#### 3. 开始使用
|
||||
|
||||
在知识库导入数据或应用文件上传配置中,可以勾选`PDF 增强解析`,则在对 PDF 解析时候,会使用 Doc2x 服务进行解析。
|
||||
|
||||
### 使用 Marker 解析 PDF 文件
|
||||
|
||||
[点击查看 Marker 接入教程](/docs/development/custom-models/marker)
|
||||
@@ -31,9 +31,9 @@ weight: 920
|
||||
|
||||
3 个模型代码分别为:
|
||||
|
||||
1. [https://github.com/labring/FastGPT/tree/main/python/bge-rerank/bge-reranker-base](https://github.com/labring/FastGPT/tree/main/python/bge-rerank/bge-reranker-base)
|
||||
2. [https://github.com/labring/FastGPT/tree/main/python/bge-rerank/bge-reranker-large](https://github.com/labring/FastGPT/tree/main/python/bge-rerank/bge-reranker-large)
|
||||
3. [https://github.com/labring/FastGPT/tree/main/python/bge-rerank/bge-reranker-v2-m3](https://github.com/labring/FastGPT/tree/main/python/bge-rerank/bge-reranker-v2-m3)
|
||||
1. [https://github.com/labring/FastGPT/tree/main/plugins/rerank-bge/bge-reranker-base](https://github.com/labring/FastGPT/tree/main/plugins/rerank-bge/bge-reranker-base)
|
||||
2. [https://github.com/labring/FastGPT/tree/main/plugins/rerank-bge/bge-reranker-large](https://github.com/labring/FastGPT/tree/main/plugins/rerank-bge/bge-reranker-large)
|
||||
3. [https://github.com/labring/FastGPT/tree/main/plugins/rerank-bge/bge-reranker-v2-m3](https://github.com/labring/FastGPT/tree/main/plugins/rerank-bge/bge-reranker-v2-m3)
|
||||
|
||||
### 3. 安装依赖
|
||||
|
||||
|
||||
@@ -11,15 +11,15 @@ weight: 909
|
||||
|
||||
PDF 是一个相对复杂的文件格式,在 FastGPT 内置的 pdf 解析器中,依赖的是 pdfjs 库解析,该库基于逻辑解析,无法有效的理解复杂的 pdf 文件。所以我们在解析 pdf 时候,如果遇到图片、表格、公式等非简单文本内容,会发现解析效果不佳。
|
||||
|
||||
市面上目前有多种解析 PDF 的方法,比如使用 [Marker](https://github.com/VikParuchuri/marker),该项目使用了 Surya 模型,基于视觉解析,可以有效提取图片、表格、公式等复杂内容。为了可以让 Marker 快速接入 FastGPT,我们做了一个自定义解析的拓展 Demo。
|
||||
市面上目前有多种解析 PDF 的方法,比如使用 [Marker](https://github.com/VikParuchuri/marker),该项目使用了 Surya 模型,基于视觉解析,可以有效提取图片、表格、公式等复杂内容。
|
||||
|
||||
在 FastGPT 4.8.15 版本中,你可以通过增加一个环境变量,来替换掉 FastGPT 系统内置解析器,实现自定义的文档解析服务。该功能只是 Demo 阶段,后期配置模式和交互规则会发生改动。
|
||||
在 `FastGPT v4.9.0` 版本中,开源版用户可以在`config.json`文件中添加`systemEnv.customPdfParse`配置,来使用 Marker 解析 PDF 文件。商业版用户直接在 Admin 后台根据表单指引填写即可。需重新拉取 Marker 镜像,接口格式已变动。
|
||||
|
||||
## 使用教程
|
||||
|
||||
### 1. 按照 Marker
|
||||
### 1. 安装 Marker
|
||||
|
||||
参考文档 [Marker 安装教程](https://github.com/labring/FastGPT/tree/main/python/pdf-marker),安装 Marker 模型。封装的 API 已经适配了 FastGPT 自定义解析服务。
|
||||
参考文档 [Marker 安装教程](https://github.com/labring/FastGPT/tree/main/plugins/model/pdf-marker),安装 Marker 模型。封装的 API 已经适配了 FastGPT 自定义解析服务。
|
||||
|
||||
这里介绍快速 Docker 安装的方法:
|
||||
|
||||
@@ -28,22 +28,35 @@ docker pull crpi-h3snc261q1dosroc.cn-hangzhou.personal.cr.aliyuncs.com/marker11/
|
||||
docker run --gpus all -itd -p 7231:7231 --name model_pdf_v1 crpi-h3snc261q1dosroc.cn-hangzhou.personal.cr.aliyuncs.com/marker11/marker_images:latest
|
||||
```
|
||||
|
||||
### 2. 添加 FastGPT 环境变量
|
||||
### 2. 添加 FastGPT 文件配置
|
||||
|
||||
```
|
||||
CUSTOM_READ_FILE_URL=http://xxxx.com/v1/parse/file
|
||||
CUSTOM_READ_FILE_EXTENSION=pdf
|
||||
```json
|
||||
{
|
||||
xxx
|
||||
"systemEnv": {
|
||||
xxx
|
||||
"customPdfParse": {
|
||||
"url": "http://xxxx.com/v1/parse/file", // 自定义 PDF 解析服务地址
|
||||
"key": "", // 自定义 PDF 解析服务密钥
|
||||
"doc2xKey": "", // doc2x 服务密钥
|
||||
"price": 0 // PDF 解析服务价格
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
* CUSTOM_READ_FILE_URL - 自定义解析服务的地址, host改成解析服务的访问地址,path 不能变动。
|
||||
* CUSTOM_READ_FILE_EXTENSION - 支持的文件后缀,多个文件类型,可用逗号隔开。
|
||||
需要重启服务。
|
||||
|
||||
### 3. 测试效果
|
||||
|
||||
通过知识库上传一个 pdf 文件,并确认上传,可以在日志中看到 LOG (LOG_LEVEL需要设置 info 或者 debug):
|
||||
通过知识库上传一个 pdf 文件,并勾选上 `PDF 增强解析`。
|
||||
|
||||

|
||||
|
||||
确认上传后,可以在日志中看到 LOG (LOG_LEVEL需要设置 info 或者 debug):
|
||||
|
||||
```
|
||||
[Info] 2024-12-05 15:04:42 Parsing files from an external service
|
||||
[Info] 2024-12-05 15:04:42 Parsing files from an external service
|
||||
[Info] 2024-12-05 15:07:08 Custom file parsing is complete, time: 1316ms
|
||||
```
|
||||
|
||||
@@ -51,6 +64,10 @@ CUSTOM_READ_FILE_EXTENSION=pdf
|
||||
|
||||

|
||||
|
||||
同样的,在应用中,你可以在文件上传配置里,勾选上 `PDF 增强解析`。
|
||||
|
||||

|
||||
|
||||
|
||||
## 效果展示
|
||||
|
||||
|
||||
@@ -30,7 +30,7 @@ weight: 707
|
||||
|
||||
### PgVector版本
|
||||
|
||||
非常轻量,适合数据量在 5000 万以下。
|
||||
非常轻量,适合知识库索引量在 5000 万以下。
|
||||
|
||||
{{< table "table-hover table-striped-columns" >}}
|
||||
| 环境 | 最低配置(单节点) | 推荐配置 |
|
||||
@@ -118,7 +118,7 @@ brew install orbstack
|
||||
非 Linux 环境或无法访问外网环境,可手动创建一个目录,并下载配置文件和对应版本的`docker-compose.yml`,在这个文件夹中依据下载的配置文件运行docker,若作为本地开发使用推荐`docker-compose-pgvector`版本,并且自行拉取并运行`sandbox`和`fastgpt`,并在docker配置文件中注释掉`sandbox`和`fastgpt`的部分
|
||||
|
||||
- [config.json](https://raw.githubusercontent.com/labring/FastGPT/refs/heads/main/projects/app/data/config.json)
|
||||
- [docker-compose.yml](https://github.com/labring/FastGPT/blob/main/files/docker) (注意,不同向量库版本的文件不一样)
|
||||
- [docker-compose.yml](https://github.com/labring/FastGPT/blob/main/deploy/docker) (注意,不同向量库版本的文件不一样)
|
||||
|
||||
{{% alert icon="🤖" context="success" %}}
|
||||
|
||||
@@ -134,11 +134,11 @@ cd fastgpt
|
||||
curl -O https://raw.githubusercontent.com/labring/FastGPT/main/projects/app/data/config.json
|
||||
|
||||
# pgvector 版本(测试推荐,简单快捷)
|
||||
curl -o docker-compose.yml https://raw.githubusercontent.com/labring/FastGPT/main/files/docker/docker-compose-pgvector.yml
|
||||
curl -o docker-compose.yml https://raw.githubusercontent.com/labring/FastGPT/main/deploy/docker/docker-compose-pgvector.yml
|
||||
# milvus 版本
|
||||
# curl -o docker-compose.yml https://raw.githubusercontent.com/labring/FastGPT/main/files/docker/docker-compose-milvus.yml
|
||||
# curl -o docker-compose.yml https://raw.githubusercontent.com/labring/FastGPT/main/deploy/docker/docker-compose-milvus.yml
|
||||
# zilliz 版本
|
||||
# curl -o docker-compose.yml https://raw.githubusercontent.com/labring/FastGPT/main/files/docker/docker-compose-zilliz.yml
|
||||
# curl -o docker-compose.yml https://raw.githubusercontent.com/labring/FastGPT/main/deploy/docker/docker-compose-zilliz.yml
|
||||
```
|
||||
|
||||
### 2. 修改环境变量
|
||||
@@ -149,18 +149,14 @@ curl -o docker-compose.yml https://raw.githubusercontent.com/labring/FastGPT/mai
|
||||
{{< tab tabName="PgVector版本" >}}
|
||||
{{< markdownify >}}
|
||||
|
||||
```
|
||||
FE_DOMAIN=你的前端你访问地址,例如 http://192.168.0.1:3000;https://cloud.fastgpt.cn
|
||||
```
|
||||
无需操作
|
||||
|
||||
{{< /markdownify >}}
|
||||
{{< /tab >}}
|
||||
{{< tab tabName="Milvus版本" >}}
|
||||
{{< markdownify >}}
|
||||
|
||||
```
|
||||
FE_DOMAIN=你的前端你访问地址,例如 http://192.168.0.1:3000;https://cloud.fastgpt.cn
|
||||
```
|
||||
无需操作
|
||||
|
||||
{{< /markdownify >}}
|
||||
{{< /tab >}}
|
||||
@@ -174,7 +170,6 @@ FE_DOMAIN=你的前端你访问地址,例如 http://192.168.0.1:3000;https://clo
|
||||
{{% alert icon="🤖" context="success" %}}
|
||||
|
||||
1. 修改`MILVUS_ADDRESS`和`MILVUS_TOKEN`链接参数,分别对应 `zilliz` 的 `Public Endpoint` 和 `Api key`,记得把自己ip加入白名单。
|
||||
2. 修改FE_DOMAIN=你的前端你访问地址,例如 http://192.168.0.1:3000;https://cloud.fastgpt.cn
|
||||
|
||||
{{% /alert %}}
|
||||
|
||||
@@ -189,34 +184,28 @@ FE_DOMAIN=你的前端你访问地址,例如 http://192.168.0.1:3000;https://clo
|
||||
```bash
|
||||
# 启动容器
|
||||
docker-compose up -d
|
||||
# 等待10s,OneAPI第一次总是要重启几次才能连上Mysql
|
||||
sleep 10
|
||||
# 重启一次oneapi(由于OneAPI的默认Key有点问题,不重启的话会提示找不到渠道,临时手动重启一次解决,等待作者修复)
|
||||
docker restart oneapi
|
||||
```
|
||||
|
||||
### 4. 打开 OneAPI 添加模型
|
||||
### 4. 访问 FastGPT
|
||||
|
||||
可以通过`ip:3001`访问OneAPI,默认账号为`root`密码为`123456`。
|
||||
|
||||
在OneApi中添加合适的AI模型渠道。[点击查看相关教程](/docs/development/modelconfig/one-api/)
|
||||
|
||||
### 5. 访问 FastGPT
|
||||
|
||||
目前可以通过 `ip:3000` 直接访问(注意防火墙)。登录用户名为 `root`,密码为`docker-compose.yml`环境变量里设置的 `DEFAULT_ROOT_PSW`。
|
||||
目前可以通过 `ip:3000` 直接访问(注意开放防火墙)。登录用户名为 `root`,密码为`docker-compose.yml`环境变量里设置的 `DEFAULT_ROOT_PSW`。
|
||||
|
||||
如果需要域名访问,请自行安装并配置 Nginx。
|
||||
|
||||
首次运行,会自动初始化 root 用户,密码为 `1234`(与环境变量中的`DEFAULT_ROOT_PSW`一致),日志里会提示一次`MongoServerError: Unable to read from a snapshot due to pending collection catalog changes;`可忽略。
|
||||
首次运行,会自动初始化 root 用户,密码为 `1234`(与环境变量中的`DEFAULT_ROOT_PSW`一致),日志可能会提示一次`MongoServerError: Unable to read from a snapshot due to pending collection catalog changes;`可忽略。
|
||||
|
||||
### 6. 配置模型
|
||||
### 5. 配置模型
|
||||
|
||||
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](/docs/development/modelConfig/intro/)
|
||||
- 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/development/modelconfig/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。
|
||||
|
||||
## FAQ
|
||||
|
||||
### 登录系统后,浏览器无法响应
|
||||
|
||||
无法点击任何内容,刷新也无效。此时需要删除该tab,重新打开一次即可。
|
||||
|
||||
### Mongo 副本集自动初始化失败
|
||||
|
||||
最新的 docker-compose 示例优化 Mongo 副本集初始化,实现了全自动。目前在 unbuntu20,22 centos7, wsl2, mac, window 均通过测试。仍无法正常启动,大部分是因为 cpu 不支持 AVX 指令集,可以切换 Mongo4.x 版本。
|
||||
|
||||
@@ -142,6 +142,10 @@ OneAPI 的 API Key 配置错误,需要修改`OPENAI_API_KEY`环境变量,并
|
||||
3. ....
|
||||
|
||||
|
||||
### Tiktoken 下载失败
|
||||
|
||||
由于 OneAPI 会在启动时从网络下载一个 tiktoken 的依赖,如果网络异常,就会导致启动失败。可以参考[OneAPI 离线部署](https://blog.csdn.net/wanh/article/details/139039216)解决。
|
||||
|
||||
## 四、常见模型问题
|
||||
|
||||
### 如何检查模型可用性问题
|
||||
|
||||
@@ -15,8 +15,8 @@ weight: 705
|
||||
|
||||
- [Git](http://git-scm.com/)
|
||||
- [Docker](https://www.docker.com/)(构建镜像)
|
||||
- [Node.js v18.17 / v20.x](http://nodejs.org)(版本尽量一样,可以使用nvm管理node版本)
|
||||
- [pnpm](https://pnpm.io/) 版本 8.6.0 (目前官方的开发环境)
|
||||
- [Node.js v20.14.0](http://nodejs.org)(版本尽量一样,可以使用nvm管理node版本)
|
||||
- [pnpm](https://pnpm.io/) 推荐版本 9.4.0 (目前官方的开发环境)
|
||||
- make命令: 根据不同平台,百度安装 (官方是GNU Make 4.3)
|
||||
|
||||
## 开始本地开发
|
||||
@@ -70,6 +70,7 @@ Mongo 数据库需要注意,需要注意在连接地址中增加 `directConnec
|
||||
|
||||
- `vectorMaxProcess`: 向量生成最大进程,根据数据库和 key 的并发数来决定,通常单个 120 号,2c4g 服务器设置 10~15。
|
||||
- `qaMaxProcess`: QA 生成最大进程
|
||||
- `vlmMaxProcess`: 图片理解模型最大进程
|
||||
- `pgHNSWEfSearch`: PostgreSQL vector 索引参数,越大搜索精度越高但是速度越慢,具体可看 pgvector 官方说明。
|
||||
|
||||
### 5. 运行
|
||||
@@ -77,8 +78,6 @@ Mongo 数据库需要注意,需要注意在连接地址中增加 `directConnec
|
||||
可参考项目根目录下的 `dev.md`,第一次编译运行可能会有点慢,需要点耐心哦
|
||||
|
||||
```bash
|
||||
# 给自动化脚本代码执行权限(非 linux 系统, 可以手动执行里面的 postinstall.sh 文件内容)
|
||||
chmod -R +x ./scripts/
|
||||
# 代码根目录下执行,会安装根 package、projects 和 packages 内所有依赖
|
||||
# 如果提示 isolate-vm 安装失败,可以参考:https://github.com/laverdet/isolated-vm?tab=readme-ov-file#requirements
|
||||
pnpm i
|
||||
|
||||
@@ -7,9 +7,18 @@ draft: false
|
||||
images: []
|
||||
---
|
||||
|
||||
## Copy文件
|
||||
## 1. 停止服务
|
||||
|
||||
```bash
|
||||
docker-compose down
|
||||
```
|
||||
|
||||
|
||||
## 2. Copy文件夹
|
||||
|
||||
Docker 部署数据库都会通过 volume 挂载本地的目录进入容器,如果要迁移,直接复制这些目录即可。
|
||||
|
||||
`PG 数据`: pg/data
|
||||
`Mongo 数据`: mongo/data
|
||||
`Mongo 数据`: mongo/data
|
||||
|
||||
直接把pg 和 mongo目录全部复制走即可。
|
||||
129
docSite/content/zh-cn/docs/development/modelConfig/ai-proxy.md
Normal file
@@ -0,0 +1,129 @@
|
||||
---
|
||||
title: '通过 AI Proxy 接入模型'
|
||||
description: '通过 AI Proxy 接入模型'
|
||||
icon: 'api'
|
||||
draft: false
|
||||
toc: true
|
||||
weight: 744
|
||||
---
|
||||
|
||||
从 `FastGPT 4.8.23` 版本开始,引入 AI Proxy 来进一步方便模型的配置。
|
||||
|
||||
AI Proxy 与 One API 类似,也是作为一个 OpenAI 接口管理 & 分发系统,可以通过标准的 OpenAI API 格式访问所有的大模型,开箱即用。
|
||||
|
||||
## 部署
|
||||
|
||||
### Docker 版本
|
||||
|
||||
`docker-compose.yml` 文件已加入了 AI Proxy 配置,可直接使用。[点击查看最新的 yml 配置](https://raw.githubusercontent.com/labring/FastGPT/main/deploy/docker/docker-compose-pgvector.yml)
|
||||
|
||||
从旧版升级的用户,可以复制 yml 里,ai proxy 的配置,加入到旧的 yml 文件中。
|
||||
|
||||
## 运行原理
|
||||
|
||||
AI proxy 核心模块:
|
||||
|
||||
1. 渠道管理:管理各家模型提供商的 API Key 和可用模型列表。
|
||||
2. 模型调用:根据请求的模型,选中对应的渠道;根据渠道的 API 格式,构造请求体,发送请求;格式化响应体成标准格式返回。
|
||||
3. 调用日志:详细记录模型调用的日志,并在错误时候可以记录其入参和报错信息,方便排查。
|
||||
|
||||
运行流程:
|
||||
|
||||

|
||||
|
||||
## 在 FastGPT 中使用
|
||||
|
||||
AI proxy 相关功能,可以在`账号-模型提供商`页面找到。
|
||||
|
||||
### 1. 创建渠道
|
||||
|
||||
在`模型提供商`的配置页面,点击`模型渠道`,进入渠道配置页面
|
||||
|
||||

|
||||
|
||||
点击右上角的“新增渠道”,即可进入渠道配置页面
|
||||
|
||||

|
||||
|
||||
以阿里云的模型为例,进行如下配置
|
||||
|
||||

|
||||
|
||||
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/development/modelconfig/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
|
||||
{
|
||||
"gpt-4o-test": "gpt-4o",
|
||||
}
|
||||
```
|
||||
|
||||
FatGPT 中的模型为 `gpt-4o-test`,向 AI Proxy 发起请求时也是 `gpt-4o-test`。AI proxy 在向上游发送请求时,实际的`model`为 `gpt-4o`。
|
||||
|
||||
5. 代理地址:具体请求的地址,系统给每个主流渠道配置了默认的地址,如果无需改动则不用填。
|
||||
6. API 密钥:从模型厂商处获取的 API 凭证。注意部分厂商需要提供多个密钥组合,可以根据提示进行输入。
|
||||
|
||||
最后点击“新增”,就能在“模型渠道”下看到刚刚配置的渠道
|
||||
|
||||

|
||||
|
||||
### 2. 渠道测试
|
||||
|
||||
然后可以对渠道进行测试,确保配置的模型有效
|
||||
|
||||

|
||||
|
||||
点击“模型测试”,可以看到配置的模型列表,点击“开始测试”
|
||||
|
||||

|
||||
|
||||
等待模型测试完成后,会输出每个模型的测试结果以及请求时长
|
||||
|
||||

|
||||
|
||||
### 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/development/modelconfig/intro)
|
||||
|
||||

|
||||
|
||||
## 其他功能介绍
|
||||
|
||||
### 优先级
|
||||
|
||||
范围1~100。数值越大,越容易被优先选中。
|
||||
|
||||

|
||||
|
||||
### 启用/禁用
|
||||
|
||||
在渠道右侧的控制菜单中,还可以控制渠道的启用或禁用,被禁用的渠道将无法再提供模型服务
|
||||
|
||||

|
||||
|
||||
### 调用日志
|
||||
|
||||
在 `调用日志` 页面,会展示发送到模型处的请求记录,包括具体的输入输出 tokens、请求时间、请求耗时、请求地址等等。错误的请求,则会详细的入参和错误信息,方便排查,但仅会保留 1 小时(环境变量里可配置)。
|
||||
|
||||

|
||||
|
||||
## 从 OneAPI 迁移到 AI Proxy
|
||||
|
||||
可以从任意终端,发起 1 个 HTTP 请求。其中 `{{host}}` 替换成 AI Proxy 地址,`{{admin_key}}` 替换成 AI Proxy 中 `ADMIN_KEY` 的值。
|
||||
|
||||
Body 参数 `dsn` 为 OneAPI 的 mysql 连接串。
|
||||
|
||||
```bash
|
||||
curl --location --request POST '{{host}}/api/channels/import/oneapi' \
|
||||
--header 'Authorization: Bearer {{admin_key}}' \
|
||||
--header 'Content-Type: application/json' \
|
||||
--data-raw '{
|
||||
"dsn": "mysql://root:s5mfkwst@tcp(dbconn.sealoshzh.site:33123)/mydb"
|
||||
}'
|
||||
```
|
||||
|
||||
执行成功的情况下会返回 "success": true
|
||||
|
||||
脚本目前不是完全准,仅是简单的做数据映射,主要是迁移`代理地址`、`模型`和`API 密钥`,建议迁移后再进行手动检查。
|
||||
@@ -13,9 +13,15 @@ weight: 744
|
||||
|
||||
## 配置模型
|
||||
|
||||
### 1. 使用 OneAPI 对接模型提供商
|
||||
### 1. 对接模型提供商
|
||||
|
||||
可以使用 [OneAPI 接入教程](/docs/development/modelconfig/one-api) 来进行模型聚合,从而可以对接更多模型提供商。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:
|
||||
#### 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/development/modelconfig/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/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:
|
||||
|
||||

|
||||
|
||||
@@ -23,22 +29,12 @@ weight: 744
|
||||
|
||||
{{% alert icon=" " context="info" %}}
|
||||
- [SiliconCloud(硅基流动)](https://cloud.siliconflow.cn/i/TR9Ym0c4): 提供开源模型调用的平台。
|
||||
- [Sealos AIProxy](https://hzh.sealos.run/?openapp=system-aiproxy): 提供国内各家模型代理,无需逐一申请 api。
|
||||
- [Sealos AIProxy](https://cloud.sealos.run/?uid=fnWRt09fZP&openapp=system-aiproxy): 提供国内各家模型代理,无需逐一申请 api。
|
||||
{{% /alert %}}
|
||||
|
||||
在 OneAPI 配置好模型后,你就可以打开 FastGPT 页面,启用对应模型了。
|
||||
|
||||
### 2. 登录 root 用户
|
||||
|
||||
仅 root 用户可以进行模型配置。
|
||||
|
||||
### 3. 进入模型配置页面
|
||||
|
||||
登录 root 用户后,在`账号-模型提供商-模型配置`中,你可以看到所有内置的模型和自定义模型,以及哪些模型启用了。
|
||||
|
||||

|
||||
|
||||
### 4. 配置介绍
|
||||
### 2. 配置介绍
|
||||
|
||||
{{% alert icon="🤖 " context="success" %}}
|
||||
注意:
|
||||
@@ -467,4 +463,4 @@ OneAPI 的语言识别接口,无法正确的识别其他模型(会始终识
|
||||
"charsPointsPrice": 0
|
||||
}
|
||||
}
|
||||
```
|
||||
```
|
||||
|
||||
@@ -20,10 +20,6 @@ FastGPT 目前采用模型分离的部署方案,FastGPT 中只兼容 OpenAI
|
||||
|
||||
## 部署
|
||||
|
||||
### Docker 版本
|
||||
|
||||
`docker-compose.yml` 文件已加入了 OneAPI 配置,可直接使用。默认暴露在 3001 端口。
|
||||
|
||||
### Sealos 版本
|
||||
|
||||
* 北京区: [点击部署 OneAPI](https://hzh.sealos.run/?openapp=system-template%3FtemplateName%3Done-api)
|
||||
|
||||
@@ -35,7 +35,7 @@ CHAT_API_KEY=sk-xxxxxx
|
||||
|
||||

|
||||
|
||||
## 5. 体验测试
|
||||
## 4. 体验测试
|
||||
|
||||
### 测试对话和图片识别
|
||||
|
||||
|
||||
@@ -7,6 +7,12 @@ toc: true
|
||||
weight: 852
|
||||
---
|
||||
|
||||
# 如何获取 AppId
|
||||
|
||||
可在应用详情的路径里获取 AppId。
|
||||
|
||||

|
||||
|
||||
# 发起对话
|
||||
|
||||
{{% alert icon="🤖 " context="success" %}}
|
||||
@@ -102,8 +108,8 @@ curl --location --request POST 'http://localhost:3000/api/v1/chat/completions' \
|
||||
{{% alert context="info" %}}
|
||||
- headers.Authorization: Bearer {{apikey}}
|
||||
- chatId: string | undefined 。
|
||||
- 为 `undefined` 时(不传入),不使用 FastGpt 提供的上下文功能,完全通过传入的 messages 构建上下文。 不会将你的记录存储到数据库中,你也无法在记录汇总中查阅到。
|
||||
- 为`非空字符串`时,意味着使用 chatId 进行对话,自动从 FastGpt 数据库取历史记录,并使用 messages 数组最后一个内容作为用户问题。请自行确保 chatId 唯一,长度小于250,通常可以是自己系统的对话框ID。
|
||||
- 为 `undefined` 时(不传入),不使用 FastGpt 提供的上下文功能,完全通过传入的 messages 构建上下文。
|
||||
- 为`非空字符串`时,意味着使用 chatId 进行对话,自动从 FastGpt 数据库取历史记录,并使用 messages 数组最后一个内容作为用户问题,其余 message 会被忽略。请自行确保 chatId 唯一,长度小于250,通常可以是自己系统的对话框ID。
|
||||
- messages: 结构与 [GPT接口](https://platform.openai.com/docs/api-reference/chat/object) chat模式一致。
|
||||
- responseChatItemId: string | undefined 。如果传入,则会将该值作为本次对话的响应消息的 ID,FastGPT 会自动将该 ID 存入数据库。请确保,在当前`chatId`下,`responseChatItemId`是唯一的。
|
||||
- detail: 是否返回中间值(模块状态,响应的完整结果等),`stream模式`下会通过`event`进行区分,`非stream模式`结果保存在`responseData`中。
|
||||
|
||||
@@ -297,7 +297,9 @@ curl --location --request DELETE 'http://localhost:3000/api/core/dataset/delete?
|
||||
| --- | --- | --- |
|
||||
| datasetId | 知识库ID | ✅ |
|
||||
| parentId: | 父级ID,不填则默认为根目录 | |
|
||||
| trainingType | 训练模式。chunk: 按文本长度进行分割;qa: QA拆分;auto: 增强训练 | ✅ |
|
||||
| trainingType | 数据处理方式。chunk: 按文本长度进行分割;qa: 问答对提取 | ✅ |
|
||||
| autoIndexes | 是否自动生成索引(仅商业版支持) | |
|
||||
| imageIndex | 是否自动生成图片索引(仅商业版支持) | |
|
||||
| chunkSize | 预估块大小 | |
|
||||
| chunkSplitter | 自定义最高优先分割符号 | |
|
||||
| qaPrompt | qa拆分提示词 | |
|
||||
@@ -735,7 +737,7 @@ data 为集合的 ID。
|
||||
|
||||
**4.8.19+**
|
||||
```bash
|
||||
curl --location --request POST 'http://localhost:3000/api/core/dataset/collection/listv2' \
|
||||
curl --location --request POST 'http://localhost:3000/api/core/dataset/collection/listV2' \
|
||||
--header 'Authorization: Bearer {{authorization}}' \
|
||||
--header 'Content-Type: application/json' \
|
||||
--data-raw '{
|
||||
@@ -1079,7 +1081,7 @@ curl --location --request POST 'https://api.fastgpt.in/api/core/dataset/data/pus
|
||||
--header 'Content-Type: application/json' \
|
||||
--data-raw '{
|
||||
"collectionId": "64663f451ba1676dbdef0499",
|
||||
"trainingMode": "chunk",
|
||||
"trainingType": "chunk",
|
||||
"prompt": "可选。qa 拆分引导词,chunk 模式下忽略",
|
||||
"billId": "可选。如果有这个值,本次的数据会被聚合到一个订单中,这个值可以重复使用。可以参考 [创建训练订单] 获取该值。",
|
||||
"data": [
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
title: 'Api Key 使用与鉴权'
|
||||
description: 'FastGPT Api Key 使用与鉴权'
|
||||
title: 'OpenAPI 介绍'
|
||||
description: 'FastGPT OpenAPI 介绍'
|
||||
icon: 'key'
|
||||
draft: false
|
||||
toc: true
|
||||
@@ -27,6 +27,7 @@ FastGPT 的 API Key **有 2 类**,一类是全局通用的 key (无法直接
|
||||
| --------------------- | --------------------- |
|
||||
|  |  |
|
||||
|
||||
|
||||
## 基本配置
|
||||
|
||||
OpenAPI 中,所有的接口都通过 Header.Authorization 进行鉴权。
|
||||
@@ -1,5 +1,5 @@
|
||||
---
|
||||
title: 'V4.8.18'
|
||||
title: 'V4.8.18(包含升级脚本)'
|
||||
description: 'FastGPT V4.8.18 更新说明'
|
||||
icon: 'upgrade'
|
||||
draft: false
|
||||
|
||||
@@ -20,7 +20,7 @@ SANDBOX_URL=内网地址
|
||||
|
||||
## Docker 部署
|
||||
|
||||
可以拉取最新 [docker-compose.yml](https://github.com/labring/FastGPT/blob/main/files/docker/docker-compose.yml) 文件参考
|
||||
可以拉取最新 [docker-compose.yml](https://github.com/labring/FastGPT/blob/main/deploy/docker/docker-compose.yml) 文件参考
|
||||
|
||||
1. 新增一个容器 `sandbox`
|
||||
2. fastgpt 和 fastgpt-pro(商业版) 容器新增环境变量: `SANDBOX_URL`
|
||||
|
||||
@@ -13,8 +13,8 @@ weight: 803
|
||||
|
||||
### 2. 更新镜像:
|
||||
|
||||
- 更新 fastgpt 镜像 tag: v4.8.21
|
||||
- 更新 fastgpt-pro 商业版镜像 tag: v4.8.21
|
||||
- 更新 fastgpt 镜像 tag: v4.8.21-fix
|
||||
- 更新 fastgpt-pro 商业版镜像 tag: v4.8.21-fix
|
||||
- Sandbox 镜像无需更新
|
||||
|
||||
## 完整更新内容
|
||||
|
||||
61
docSite/content/zh-cn/docs/development/upgrading/4822.md
Normal file
@@ -0,0 +1,61 @@
|
||||
---
|
||||
title: 'V4.8.22(包含升级脚本)'
|
||||
description: 'FastGPT V4.8.22 更新说明'
|
||||
icon: 'upgrade'
|
||||
draft: false
|
||||
toc: true
|
||||
weight: 802
|
||||
---
|
||||
|
||||
## 🌟更新指南
|
||||
|
||||
### 1. 做好数据库备份
|
||||
|
||||
### 2. 更新镜像:
|
||||
|
||||
- 更新 fastgpt 镜像 tag: v4.8.22
|
||||
- 更新 fastgpt-pro 商业版镜像 tag: v4.8.22
|
||||
- Sandbox 镜像无需更新
|
||||
|
||||
### 3. 运行升级脚本
|
||||
|
||||
仅商业版,并提供 Saas 服务的用户需要运行该升级脚本。
|
||||
|
||||
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/initv4822' \
|
||||
--header 'rootkey: {{rootkey}}' \
|
||||
--header 'Content-Type: application/json'
|
||||
```
|
||||
|
||||
会迁移联系方式到对应用户表中。
|
||||
|
||||
## 🚀 新增内容
|
||||
|
||||
1. AI 对话节点解析 `<think></think>` 标签内容作为思考链,便于各类模型进行思考链输出。需主动开启模型输出思考。
|
||||
2. 对话 API 优化,无论是否传递 chatId,都会保存对话日志。未传递 chatId,则随机生成一个 chatId 来进行存储。
|
||||
3. ppio 模型提供商
|
||||
|
||||
## ⚙️ 优化
|
||||
|
||||
1. 模型未配置时提示,减少冲突提示。
|
||||
2. 使用记录代码。
|
||||
3. 内容提取节点,字段描述过长时换行。同时修改其输出名用 key,而不是 description。
|
||||
4. 团队管理交互。
|
||||
5. 对话接口,非流响应,增加报错字段。
|
||||
|
||||
## 🐛 修复
|
||||
|
||||
1. 思考内容未进入到输出 Tokens.
|
||||
2. 思考链流输出时,有时与正文顺序偏差。
|
||||
3. API 调用工作流,如果传递的图片不支持 Head 检测时,图片会被过滤。已增加该类错误检测,避免被错误过滤。
|
||||
4. 模板市场部分模板错误。
|
||||
5. 免登录窗口无法正常判断语言识别是否开启。
|
||||
6. 对话日志导出,未兼容 sub path。
|
||||
7. 切换团队时未刷新成员列表
|
||||
8. list 接口在联查 member 时,存在空指针可能性。
|
||||
9. 工作流基础节点无法升级。
|
||||
10. 向量检索结果未去重。
|
||||
11. 用户选择节点无法正常连线。
|
||||
12. 对话记录保存时,source 未正常记录。
|
||||
54
docSite/content/zh-cn/docs/development/upgrading/4823.md
Normal file
@@ -0,0 +1,54 @@
|
||||
---
|
||||
title: 'V4.8.23'
|
||||
description: 'FastGPT V4.8.23 更新说明'
|
||||
icon: 'upgrade'
|
||||
draft: false
|
||||
toc: true
|
||||
weight: 802
|
||||
---
|
||||
|
||||
## 更新指南
|
||||
|
||||
### 1. 做好数据库备份
|
||||
|
||||
### 2. 更新镜像:
|
||||
|
||||
- 更新 fastgpt 镜像 tag: v4.8.23-fix
|
||||
- 更新 fastgpt-pro 商业版镜像 tag: v4.8.23-fix
|
||||
- Sandbox 镜像无需更新
|
||||
|
||||
### 3. 运行升级脚本
|
||||
|
||||
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/initv4823' \
|
||||
--header 'rootkey: {{rootkey}}' \
|
||||
--header 'Content-Type: application/json'
|
||||
```
|
||||
|
||||
脚本会清理一些知识库脏数据,主要是多余的全文索引。
|
||||
|
||||
## 🚀 新增内容
|
||||
|
||||
1. 增加默认“知识库文本理解模型”配置
|
||||
2. AI proxy V1版,可替换 OneAPI使用,同时提供完整模型调用日志,便于排查问题。
|
||||
3. 增加工单入口支持。
|
||||
|
||||
## ⚙️ 优化
|
||||
|
||||
1. 模型配置表单,增加必填项校验。
|
||||
2. 集合列表数据统计方式,提高大数据量统计性能。
|
||||
3. 优化数学公式,转义 Latex 格式成 Markdown 格式。
|
||||
4. 解析文档图片,图片太大时,自动忽略。
|
||||
5. 时间选择器,当天开始时间自动设0,结束设置设 23:59:59,避免 UI 与实际逻辑偏差。
|
||||
6. 升级 mongoose 库版本依赖。
|
||||
|
||||
## 🐛 修复
|
||||
|
||||
1. 标签过滤时,子文件夹未成功过滤。
|
||||
2. 暂时移除 md 阅读优化,避免链接分割错误。
|
||||
3. 离开团队时,未刷新成员列表。
|
||||
4. PPTX 编码错误,导致解析失败。
|
||||
5. 删除知识库单条数据时,全文索引未跟随删除。
|
||||
6. 修复 Mongo Dataset text 索引在查询数据时未生效。
|
||||
@@ -15,7 +15,7 @@ weight: 821
|
||||
|
||||
## V4.8.3 更新说明
|
||||
|
||||
1. 新增 - 支持 Milvus 数据库, 可参考最新的 [docker-compose-milvus.yml](https://github.com/labring/FastGPT/blob/main/files/docker/docker-compose-milvus.yml).
|
||||
1. 新增 - 支持 Milvus 数据库, 可参考最新的 [docker-compose-milvus.yml](https://github.com/labring/FastGPT/blob/main/deploy/docker/docker-compose-milvus.yml).
|
||||
2. 新增 - 给 chat 接口 empty answer 增加 log,便于排查模型问题。
|
||||
3. 新增 - ifelse判断器,字符串支持正则。
|
||||
4. 新增 - 代码运行支持 console.log 输出调试。
|
||||
|
||||
56
docSite/content/zh-cn/docs/development/upgrading/490.md
Normal file
@@ -0,0 +1,56 @@
|
||||
---
|
||||
title: 'V4.9.0(进行中)'
|
||||
description: 'FastGPT V4.9.0 更新说明'
|
||||
icon: 'upgrade'
|
||||
draft: false
|
||||
toc: true
|
||||
weight: 801
|
||||
---
|
||||
|
||||
|
||||
## 更新指南
|
||||
|
||||
### 1. 做好数据库备份
|
||||
|
||||
### 2. 更新镜像
|
||||
|
||||
### 3. 运行升级脚本
|
||||
|
||||
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/initv490' \
|
||||
--header 'rootkey: {{rootkey}}' \
|
||||
--header 'Content-Type: application/json'
|
||||
```
|
||||
|
||||
**脚本功能**
|
||||
|
||||
1. 升级 PG Vector 插件版本
|
||||
2. 全量更新知识库集合字段。
|
||||
3. 全量更新知识库数据中,index 的 type 类型。(时间较长)
|
||||
|
||||
## 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/development/configuration/#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/development/openapi/dataset.md)
|
||||
|
||||
## 🚀 新增内容
|
||||
|
||||
1. PDF增强解析交互添加到页面上。同时内嵌 Doc2x 服务,可直接使用 Doc2x 服务解析 PDF 文件。
|
||||
2. 图片自动标注,同时修改知识库文件上传部分数据逻辑和交互。
|
||||
3. pg vector 插件升级 0.8.0 版本,引入迭代搜索,减少部分数据无法被检索的情况。
|
||||
|
||||
## ⚙️ 优化
|
||||
|
||||
1. 知识库数据不再限制索引数量,可无限自定义。同时可自动更新输入文本的索引,不影响自定义索引。
|
||||
2. Markdown 解析,增加链接后中文标点符号检测,增加空格。
|
||||
3. Prompt 模式工具调用,支持思考模型。同时优化其格式检测,减少空输出的概率。
|
||||
4. Mongo 文件读取流合并,减少计算量。同时优化存储 chunks,极大提高大文件读取速度。50M PDF 读取时间提高 3 倍。
|
||||
|
||||
## 🐛 修复
|
||||
|
||||
1. 增加网页抓取安全链接校验。
|
||||
2. 批量运行时,全局变量未进一步传递到下一次运行中,导致最终变量更新错误。
|
||||
@@ -7,11 +7,11 @@ toc: true
|
||||
weight: 102
|
||||
---
|
||||
|
||||
更多使用技巧,[查看视屏教程](https://www.bilibili.com/video/BV1sH4y1T7s9)
|
||||
更多使用技巧,[查看视频教程](https://www.bilibili.com/video/BV1sH4y1T7s9)
|
||||
|
||||
## 知识库
|
||||
|
||||
开始前,请准备一份测试电子文档,WORD,PDF,TXT,excel,markdown 都可以,比如公司休假制度,不涉密的销售说辞,产品知识等等。
|
||||
开始前,请准备一份测试电子文档,WORD、PDF、TXT、excel、markdown 都可以,比如公司休假制度、不涉密的销售说辞、产品知识等等。
|
||||
|
||||
这里使用 FastGPT 中文 README 文件为例。
|
||||
|
||||
@@ -31,7 +31,7 @@ weight: 102
|
||||
|
||||

|
||||
|
||||
点击上传后我们需要等待数据处理完成,等到我们上传的文件状态为可用。
|
||||
点击上传后我们需要等待数据处理完成,直到我们上传的文件状态为可用。
|
||||
|
||||

|
||||
|
||||
|
||||
@@ -20,7 +20,7 @@ weight: 502
|
||||

|
||||
|
||||
{{% alert icon="🍅" context="success" %}}
|
||||
Tips: 安全起见,你可以设置一个额度或者过期时间,放置 key 被滥用。
|
||||
Tips: 安全起见,你可以设置一个额度或者过期时间,防止 key 被滥用。
|
||||
{{% /alert %}}
|
||||
|
||||
|
||||
|
||||
@@ -7,7 +7,7 @@
|
||||
"format-code": "prettier --config \"./.prettierrc.js\" --write \"./**/src/**/*.{ts,tsx,scss}\"",
|
||||
"format-doc": "zhlint --dir ./docSite *.md --fix",
|
||||
"gen:theme-typings": "chakra-cli tokens packages/web/styles/theme.ts --out node_modules/.pnpm/node_modules/@chakra-ui/styled-system/dist/theming.types.d.ts",
|
||||
"postinstall": "sh ./scripts/postinstall.sh",
|
||||
"postinstall": "pnpm gen:theme-typings",
|
||||
"initIcon": "node ./scripts/icon/init.js",
|
||||
"previewIcon": "node ./scripts/icon/index.js",
|
||||
"api:gen": "tsc ./scripts/openapi/index.ts && node ./scripts/openapi/index.js && npx @redocly/cli build-docs ./scripts/openapi/openapi.json -o ./projects/app/public/openapi/index.html",
|
||||
|
||||
3
packages/README.md
Normal file
@@ -0,0 +1,3 @@
|
||||
# 目录说明
|
||||
|
||||
该目录为 FastGPT 的依赖包,多端复用。
|
||||
@@ -4,6 +4,7 @@ import { ErrType } from '../errorCode';
|
||||
/* dataset: 501000 */
|
||||
export enum DatasetErrEnum {
|
||||
unExist = 'unExistDataset',
|
||||
unExistCollection = 'unExistCollection',
|
||||
unAuthDataset = 'unAuthDataset',
|
||||
unCreateCollection = 'unCreateCollection',
|
||||
unAuthDatasetCollection = 'unAuthDatasetCollection',
|
||||
@@ -28,6 +29,10 @@ const datasetErr = [
|
||||
statusText: DatasetErrEnum.unExist,
|
||||
message: 'core.dataset.error.unExistDataset'
|
||||
},
|
||||
{
|
||||
statusText: DatasetErrEnum.unExistCollection,
|
||||
message: i18nT('common:error_collection_not_exist')
|
||||
},
|
||||
{
|
||||
statusText: DatasetErrEnum.unAuthDataset,
|
||||
message: 'core.dataset.error.unAuthDataset'
|
||||
|
||||
@@ -20,4 +20,4 @@ export const ReadFileBaseUrl = `${process.env.FILE_DOMAIN || process.env.FE_DOMA
|
||||
|
||||
export const documentFileType = '.txt, .docx, .csv, .xlsx, .pdf, .md, .html, .pptx';
|
||||
export const imageFileType =
|
||||
'.jpg, .jpeg, .png, .gif, .bmp, .webp, .svg, .tiff, .tif, .ico, .heic, .heif, .avif';
|
||||
'.jpg, .jpeg, .png, .gif, .bmp, .webp, .svg, .tiff, .tif, .ico, .heic, .heif, .avif, .raw, .cr2, .nef, .arw, .dng, .psd, .ai, .eps, .emf, .wmf, .jfif, .exif, .pgm, .ppm, .pbm, .jp2, .j2k, .jpf, .jpx, .jpm, .mj2, .xbm, .pcx';
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import { detect } from 'jschardet';
|
||||
import { documentFileType, imageFileType } from './constants';
|
||||
import { documentFileType } from './constants';
|
||||
import { ChatFileTypeEnum } from '../../core/chat/constants';
|
||||
import { UserChatItemValueItemType } from '../../core/chat/type';
|
||||
import * as fs from 'fs';
|
||||
@@ -25,6 +25,7 @@ export const detectFileEncodingByPath = async (path: string) => {
|
||||
const fd = await fs.promises.open(path, 'r');
|
||||
try {
|
||||
// Read file head
|
||||
// @ts-ignore
|
||||
const { bytesRead } = await fd.read(buffer, 0, MAX_BYTES, 0);
|
||||
const actualBuffer = buffer.slice(0, bytesRead);
|
||||
|
||||
@@ -37,40 +38,49 @@ export const detectFileEncodingByPath = async (path: string) => {
|
||||
// Url => user upload file type
|
||||
export const parseUrlToFileType = (url: string): UserChatItemValueItemType['file'] | undefined => {
|
||||
if (typeof url !== 'string') return;
|
||||
const parseUrl = new URL(url, 'https://locaohost:3000');
|
||||
|
||||
const filename = (() => {
|
||||
// Check base64 image
|
||||
if (url.startsWith('data:image/')) {
|
||||
const mime = url.split(',')[0].split(':')[1].split(';')[0];
|
||||
return `image.${mime.split('/')[1]}`;
|
||||
}
|
||||
// Old version file url: https://xxx.com/file/read?filename=xxx.pdf
|
||||
const filenameQuery = parseUrl.searchParams.get('filename');
|
||||
if (filenameQuery) return filenameQuery;
|
||||
// Handle base64 image
|
||||
if (url.startsWith('data:')) {
|
||||
const matches = url.match(/^data:([^;]+);base64,/);
|
||||
if (!matches) return;
|
||||
|
||||
// Common file: https://xxx.com/xxx.pdf?xxxx=xxx
|
||||
const pathname = parseUrl.pathname;
|
||||
if (pathname) return pathname.split('/').pop();
|
||||
})();
|
||||
const mimeType = matches[1].toLowerCase();
|
||||
if (!mimeType.startsWith('image/')) return;
|
||||
|
||||
if (!filename) return;
|
||||
|
||||
const extension = filename.split('.').pop()?.toLowerCase() || '';
|
||||
|
||||
if (!extension) return;
|
||||
|
||||
if (documentFileType.includes(extension)) {
|
||||
const extension = mimeType.split('/')[1];
|
||||
return {
|
||||
type: ChatFileTypeEnum.file,
|
||||
name: filename,
|
||||
type: ChatFileTypeEnum.image,
|
||||
name: `image.${extension}`,
|
||||
url
|
||||
};
|
||||
}
|
||||
if (imageFileType.includes(extension)) {
|
||||
|
||||
try {
|
||||
const parseUrl = new URL(url, 'https://localhost:3000');
|
||||
|
||||
// Get filename from URL
|
||||
const filename = parseUrl.searchParams.get('filename') || parseUrl.pathname.split('/').pop();
|
||||
const extension = filename?.split('.').pop()?.toLowerCase() || '';
|
||||
|
||||
// If it's a document type, return as file, otherwise treat as image
|
||||
if (extension && documentFileType.includes(extension)) {
|
||||
return {
|
||||
type: ChatFileTypeEnum.file,
|
||||
name: filename || 'null',
|
||||
url
|
||||
};
|
||||
}
|
||||
|
||||
// Default to image type for non-document files
|
||||
return {
|
||||
type: ChatFileTypeEnum.image,
|
||||
name: filename,
|
||||
name: filename || 'null.png',
|
||||
url
|
||||
};
|
||||
} catch (error) {
|
||||
return {
|
||||
type: ChatFileTypeEnum.image,
|
||||
name: 'invalid.png',
|
||||
url
|
||||
};
|
||||
}
|
||||
|
||||
@@ -1,31 +0,0 @@
|
||||
export const retryRun = <T>(fn: () => T, retry = 2): T => {
|
||||
try {
|
||||
return fn();
|
||||
} catch (error) {
|
||||
if (retry > 0) {
|
||||
return retryRun(fn, retry - 1);
|
||||
}
|
||||
throw error;
|
||||
}
|
||||
};
|
||||
|
||||
export const batchRun = async <T>(arr: T[], fn: (arr: T) => any, batchSize = 10) => {
|
||||
const batchArr = new Array(batchSize).fill(null);
|
||||
const result: any[] = [];
|
||||
|
||||
const batchFn = async () => {
|
||||
const data = arr.shift();
|
||||
if (data) {
|
||||
result.push(await fn(data));
|
||||
return batchFn();
|
||||
}
|
||||
};
|
||||
|
||||
await Promise.all(
|
||||
batchArr.map(async () => {
|
||||
await batchFn();
|
||||
})
|
||||
);
|
||||
|
||||
return result;
|
||||
};
|
||||
@@ -1,4 +1,4 @@
|
||||
import { batchRun } from '../fn/utils';
|
||||
import { batchRun } from '../system/utils';
|
||||
import { getNanoid, simpleText } from './tools';
|
||||
import type { ImageType } from '../../../service/worker/readFile/type';
|
||||
|
||||
@@ -37,6 +37,80 @@ export const simpleMarkdownText = (rawText: string) => {
|
||||
return rawText.trim();
|
||||
};
|
||||
|
||||
export const htmlTable2Md = (content: string): string => {
|
||||
return content.replace(/<table>[\s\S]*?<\/table>/g, (htmlTable) => {
|
||||
try {
|
||||
// Clean up whitespace and newlines
|
||||
const cleanHtml = htmlTable.replace(/\n\s*/g, '');
|
||||
const rows = cleanHtml.match(/<tr>(.*?)<\/tr>/g);
|
||||
if (!rows) return htmlTable;
|
||||
|
||||
// Parse table data
|
||||
let tableData: string[][] = [];
|
||||
let maxColumns = 0;
|
||||
|
||||
// Try to convert to markdown table
|
||||
rows.forEach((row, rowIndex) => {
|
||||
if (!tableData[rowIndex]) {
|
||||
tableData[rowIndex] = [];
|
||||
}
|
||||
let colIndex = 0;
|
||||
const cells = row.match(/<td.*?>(.*?)<\/td>/g) || [];
|
||||
|
||||
cells.forEach((cell) => {
|
||||
while (tableData[rowIndex][colIndex]) {
|
||||
colIndex++;
|
||||
}
|
||||
const colspan = parseInt(cell.match(/colspan="(\d+)"/)?.[1] || '1');
|
||||
const rowspan = parseInt(cell.match(/rowspan="(\d+)"/)?.[1] || '1');
|
||||
const content = cell.replace(/<td.*?>|<\/td>/g, '').trim();
|
||||
|
||||
for (let i = 0; i < rowspan; i++) {
|
||||
for (let j = 0; j < colspan; j++) {
|
||||
if (!tableData[rowIndex + i]) {
|
||||
tableData[rowIndex + i] = [];
|
||||
}
|
||||
tableData[rowIndex + i][colIndex + j] = i === 0 && j === 0 ? content : '^^';
|
||||
}
|
||||
}
|
||||
colIndex += colspan;
|
||||
maxColumns = Math.max(maxColumns, colIndex);
|
||||
});
|
||||
|
||||
for (let i = 0; i < maxColumns; i++) {
|
||||
if (!tableData[rowIndex][i]) {
|
||||
tableData[rowIndex][i] = ' ';
|
||||
}
|
||||
}
|
||||
});
|
||||
const chunks: string[] = [];
|
||||
|
||||
const headerCells = tableData[0]
|
||||
.slice(0, maxColumns)
|
||||
.map((cell) => (cell === '^^' ? ' ' : cell || ' '));
|
||||
const headerRow = '| ' + headerCells.join(' | ') + ' |';
|
||||
chunks.push(headerRow);
|
||||
|
||||
const separator = '| ' + Array(headerCells.length).fill('---').join(' | ') + ' |';
|
||||
chunks.push(separator);
|
||||
|
||||
tableData.slice(1).forEach((row) => {
|
||||
const paddedRow = row
|
||||
.slice(0, maxColumns)
|
||||
.map((cell) => (cell === '^^' ? ' ' : cell || ' '));
|
||||
while (paddedRow.length < maxColumns) {
|
||||
paddedRow.push(' ');
|
||||
}
|
||||
chunks.push('| ' + paddedRow.join(' | ') + ' |');
|
||||
});
|
||||
|
||||
return chunks.join('\n');
|
||||
} catch (error) {
|
||||
return htmlTable;
|
||||
}
|
||||
});
|
||||
};
|
||||
|
||||
/**
|
||||
* format markdown
|
||||
* 1. upload base64
|
||||
|
||||
@@ -7,12 +7,14 @@ import { i18nT } from '../../../web/i18n/utils';
|
||||
dayjs.extend(utc);
|
||||
dayjs.extend(timezone);
|
||||
|
||||
export const formatTime2YMDHMW = (time?: Date) => dayjs(time).format('YYYY-MM-DD HH:mm:ss dddd');
|
||||
export const formatTime2YMDHMS = (time?: Date) =>
|
||||
export const formatTime2YMDHMW = (time?: Date | number) =>
|
||||
dayjs(time).format('YYYY-MM-DD HH:mm:ss dddd');
|
||||
export const formatTime2YMDHMS = (time?: Date | number) =>
|
||||
time ? dayjs(time).format('YYYY-MM-DD HH:mm:ss') : '';
|
||||
export const formatTime2YMDHM = (time?: Date) =>
|
||||
export const formatTime2YMDHM = (time?: Date | number) =>
|
||||
time ? dayjs(time).format('YYYY-MM-DD HH:mm') : '';
|
||||
export const formatTime2YMD = (time?: Date) => (time ? dayjs(time).format('YYYY-MM-DD') : '');
|
||||
export const formatTime2YMD = (time?: Date | number) =>
|
||||
time ? dayjs(time).format('YYYY-MM-DD') : '';
|
||||
export const formatTime2HM = (time: Date = new Date()) => dayjs(time).format('HH:mm');
|
||||
|
||||
/**
|
||||
|
||||
32
packages/global/common/system/types/index.d.ts
vendored
@@ -41,11 +41,16 @@ export type FastGPTConfigFileType = {
|
||||
};
|
||||
|
||||
export type FastGPTFeConfigsType = {
|
||||
show_workorder?: boolean;
|
||||
show_emptyChat?: boolean;
|
||||
isPlus?: boolean;
|
||||
register_method?: ['email' | 'phone' | 'sync'];
|
||||
login_method?: ['email' | 'phone']; // Attention: login method is diffrent with oauth
|
||||
find_password_method?: ['email' | 'phone'];
|
||||
bind_notification_method?: ['email' | 'phone'];
|
||||
googleClientVerKey?: string;
|
||||
|
||||
show_emptyChat?: boolean;
|
||||
show_appStore?: boolean;
|
||||
show_git?: boolean;
|
||||
show_pay?: boolean;
|
||||
@@ -53,17 +58,22 @@ export type FastGPTFeConfigsType = {
|
||||
show_promotion?: boolean;
|
||||
show_team_chat?: boolean;
|
||||
show_compliance_copywriting?: boolean;
|
||||
show_aiproxy?: boolean;
|
||||
concatMd?: string;
|
||||
|
||||
concatMd?: string;
|
||||
docUrl?: string;
|
||||
openAPIDocUrl?: string;
|
||||
systemPluginCourseUrl?: string;
|
||||
appTemplateCourse?: string;
|
||||
customApiDomain?: string;
|
||||
customSharePageDomain?: string;
|
||||
|
||||
systemTitle?: string;
|
||||
systemDescription?: string;
|
||||
googleClientVerKey?: string;
|
||||
isPlus?: boolean;
|
||||
scripts?: { [key: string]: string }[];
|
||||
favicon?: string;
|
||||
|
||||
sso?: {
|
||||
icon?: string;
|
||||
title?: string;
|
||||
@@ -89,13 +99,14 @@ export type FastGPTFeConfigsType = {
|
||||
exportDatasetLimitMinutes?: number;
|
||||
websiteSyncLimitMinuted?: number;
|
||||
};
|
||||
scripts?: { [key: string]: string }[];
|
||||
favicon?: string;
|
||||
customApiDomain?: string;
|
||||
customSharePageDomain?: string;
|
||||
|
||||
uploadFileMaxAmount?: number;
|
||||
uploadFileMaxSize?: number;
|
||||
|
||||
// Compute by systemEnv.customPdfParse
|
||||
showCustomPdfParse?: boolean;
|
||||
customPdfParsePrice?: number;
|
||||
|
||||
lafEnv?: string;
|
||||
navbarItems?: NavbarItemType[];
|
||||
externalProviderWorkflowVariables?: ExternalProviderWorkflowVarType[];
|
||||
@@ -105,9 +116,18 @@ export type SystemEnvType = {
|
||||
openapiPrefix?: string;
|
||||
vectorMaxProcess: number;
|
||||
qaMaxProcess: number;
|
||||
vlmMaxProcess: number;
|
||||
pgHNSWEfSearch: number;
|
||||
tokenWorkers: number; // token count max worker
|
||||
|
||||
oneapiUrl?: string;
|
||||
chatApiKey?: string;
|
||||
|
||||
customPdfParse?: {
|
||||
url?: string;
|
||||
key?: string;
|
||||
|
||||
doc2xKey?: string;
|
||||
price?: number; // n points/1 page
|
||||
};
|
||||
};
|
||||
|
||||
@@ -16,3 +16,24 @@ export const retryFn = async <T>(fn: () => Promise<T>, retryTimes = 3): Promise<
|
||||
return Promise.reject(error);
|
||||
}
|
||||
};
|
||||
|
||||
export const batchRun = async <T>(arr: T[], fn: (arr: T) => any, batchSize = 10) => {
|
||||
const batchArr = new Array(batchSize).fill(null);
|
||||
const result: any[] = [];
|
||||
|
||||
const batchFn = async () => {
|
||||
const data = arr.shift();
|
||||
if (data) {
|
||||
result.push(await fn(data));
|
||||
return batchFn();
|
||||
}
|
||||
};
|
||||
|
||||
await Promise.all(
|
||||
batchArr.map(async () => {
|
||||
await batchFn();
|
||||
})
|
||||
);
|
||||
|
||||
return result;
|
||||
};
|
||||
|
||||
2
packages/global/core/ai/model.d.ts
vendored
@@ -17,6 +17,8 @@ type BaseModelItemType = {
|
||||
isActive?: boolean;
|
||||
isCustom?: boolean;
|
||||
isDefault?: boolean;
|
||||
isDefaultDatasetTextModel?: boolean;
|
||||
isDefaultDatasetImageModel?: boolean;
|
||||
|
||||
// If has requestUrl, it will request the model directly
|
||||
requestUrl?: string;
|
||||
|
||||
@@ -22,7 +22,7 @@ export const defaultQAModels: LLMModelItemType[] = [
|
||||
maxTemperature: 1.2,
|
||||
charsPointsPrice: 0,
|
||||
censor: false,
|
||||
vision: false,
|
||||
vision: true,
|
||||
datasetProcess: true,
|
||||
toolChoice: true,
|
||||
functionCall: false,
|
||||
@@ -59,10 +59,17 @@ export const defaultSTTModels: STTModelType[] = [
|
||||
export const getModelFromList = (
|
||||
modelList: { provider: ModelProviderIdType; name: string; model: string }[],
|
||||
model: string
|
||||
) => {
|
||||
):
|
||||
| {
|
||||
avatar: string;
|
||||
provider: ModelProviderIdType;
|
||||
name: string;
|
||||
model: string;
|
||||
}
|
||||
| undefined => {
|
||||
const modelData = modelList.find((item) => item.model === model) ?? modelList[0];
|
||||
if (!modelData) {
|
||||
throw new Error('No Key model is configured');
|
||||
return;
|
||||
}
|
||||
const provider = getModelProvider(modelData.provider);
|
||||
return {
|
||||
|
||||
@@ -22,6 +22,7 @@ export type ModelProviderIdType =
|
||||
| 'StepFun'
|
||||
| 'Yi'
|
||||
| 'Siliconflow'
|
||||
| 'PPIO'
|
||||
| 'Ollama'
|
||||
| 'BAAI'
|
||||
| 'FishAudio'
|
||||
@@ -71,11 +72,6 @@ export const ModelProviderList: ModelProviderType[] = [
|
||||
name: 'Groq',
|
||||
avatar: 'model/groq'
|
||||
},
|
||||
{
|
||||
id: 'AliCloud',
|
||||
name: i18nT('common:model_alicloud'),
|
||||
avatar: 'model/alicloud'
|
||||
},
|
||||
{
|
||||
id: 'Qwen',
|
||||
name: i18nT('common:model_qwen'),
|
||||
@@ -86,6 +82,11 @@ export const ModelProviderList: ModelProviderType[] = [
|
||||
name: i18nT('common:model_doubao'),
|
||||
avatar: 'model/doubao'
|
||||
},
|
||||
{
|
||||
id: 'DeepSeek',
|
||||
name: 'DeepSeek',
|
||||
avatar: 'model/deepseek'
|
||||
},
|
||||
{
|
||||
id: 'ChatGLM',
|
||||
name: i18nT('common:model_chatglm'),
|
||||
@@ -96,11 +97,6 @@ export const ModelProviderList: ModelProviderType[] = [
|
||||
name: i18nT('common:model_ernie'),
|
||||
avatar: 'model/ernie'
|
||||
},
|
||||
{
|
||||
id: 'DeepSeek',
|
||||
name: 'DeepSeek',
|
||||
avatar: 'model/deepseek'
|
||||
},
|
||||
{
|
||||
id: 'Moonshot',
|
||||
name: i18nT('common:model_moonshot'),
|
||||
@@ -162,11 +158,21 @@ export const ModelProviderList: ModelProviderType[] = [
|
||||
name: i18nT('common:model_moka'),
|
||||
avatar: 'model/moka'
|
||||
},
|
||||
{
|
||||
id: 'AliCloud',
|
||||
name: i18nT('common:model_alicloud'),
|
||||
avatar: 'model/alicloud'
|
||||
},
|
||||
{
|
||||
id: 'Siliconflow',
|
||||
name: i18nT('common:model_siliconflow'),
|
||||
avatar: 'model/siliconflow'
|
||||
},
|
||||
{
|
||||
id: 'PPIO',
|
||||
name: i18nT('common:model_ppio'),
|
||||
avatar: 'model/ppio'
|
||||
},
|
||||
{
|
||||
id: 'Other',
|
||||
name: i18nT('common:model_other'),
|
||||
|
||||
8
packages/global/core/ai/type.d.ts
vendored
@@ -1,14 +1,12 @@
|
||||
import openai from 'openai';
|
||||
import type {
|
||||
ChatCompletionMessageToolCall,
|
||||
ChatCompletionChunk,
|
||||
ChatCompletionMessageParam as SdkChatCompletionMessageParam,
|
||||
ChatCompletionToolMessageParam,
|
||||
ChatCompletionContentPart as SdkChatCompletionContentPart,
|
||||
ChatCompletionUserMessageParam as SdkChatCompletionUserMessageParam,
|
||||
ChatCompletionToolMessageParam as SdkChatCompletionToolMessageParam,
|
||||
ChatCompletionAssistantMessageParam as SdkChatCompletionAssistantMessageParam,
|
||||
ChatCompletionContentPartText
|
||||
ChatCompletionAssistantMessageParam as SdkChatCompletionAssistantMessageParam
|
||||
} from 'openai/resources';
|
||||
import { ChatMessageTypeEnum } from './constants';
|
||||
import { WorkflowInteractiveResponseType } from '../workflow/template/system/interactive/type';
|
||||
@@ -48,6 +46,7 @@ export type ChatCompletionMessageParam = (
|
||||
| CustomChatCompletionToolMessageParam
|
||||
| CustomChatCompletionAssistantMessageParam
|
||||
) & {
|
||||
reasoning_text?: string;
|
||||
dataId?: string;
|
||||
hideInUI?: boolean;
|
||||
};
|
||||
@@ -71,7 +70,8 @@ export type ChatCompletionMessageFunctionCall =
|
||||
};
|
||||
|
||||
// Stream response
|
||||
export type StreamChatType = Stream<ChatCompletionChunk>;
|
||||
export type StreamChatType = Stream<openai.Chat.Completions.ChatCompletionChunk>;
|
||||
export type UnStreamChatType = openai.Chat.Completions.ChatCompletion;
|
||||
|
||||
export default openai;
|
||||
export * from 'openai';
|
||||
|
||||
1
packages/global/core/app/type.d.ts
vendored
@@ -188,6 +188,7 @@ export type AppAutoExecuteConfigType = {
|
||||
// File
|
||||
export type AppFileSelectConfigType = {
|
||||
canSelectFile: boolean;
|
||||
customPdfParse?: boolean;
|
||||
canSelectImg: boolean;
|
||||
maxFiles: number;
|
||||
};
|
||||
|
||||
@@ -1,8 +1,11 @@
|
||||
import type {
|
||||
AIChatItemValueItemType,
|
||||
ChatItemType,
|
||||
ChatItemValueItemType,
|
||||
RuntimeUserPromptType,
|
||||
UserChatItemType
|
||||
SystemChatItemValueItemType,
|
||||
UserChatItemType,
|
||||
UserChatItemValueItemType
|
||||
} from '../../core/chat/type.d';
|
||||
import { ChatFileTypeEnum, ChatItemValueTypeEnum, ChatRoleEnum } from '../../core/chat/constants';
|
||||
import type {
|
||||
@@ -46,7 +49,16 @@ export const chats2GPTMessages = ({
|
||||
|
||||
messages.forEach((item) => {
|
||||
const dataId = reserveId ? item.dataId : undefined;
|
||||
if (item.obj === ChatRoleEnum.Human) {
|
||||
if (item.obj === ChatRoleEnum.System) {
|
||||
const content = item.value?.[0]?.text?.content;
|
||||
if (content) {
|
||||
results.push({
|
||||
dataId,
|
||||
role: ChatCompletionRequestMessageRoleEnum.System,
|
||||
content
|
||||
});
|
||||
}
|
||||
} else if (item.obj === ChatRoleEnum.Human) {
|
||||
const value = item.value
|
||||
.map((item) => {
|
||||
if (item.type === ChatItemValueTypeEnum.text) {
|
||||
@@ -80,15 +92,6 @@ export const chats2GPTMessages = ({
|
||||
role: ChatCompletionRequestMessageRoleEnum.User,
|
||||
content: simpleUserContentPart(value)
|
||||
});
|
||||
} else if (item.obj === ChatRoleEnum.System) {
|
||||
const content = item.value?.[0]?.text?.content;
|
||||
if (content) {
|
||||
results.push({
|
||||
dataId,
|
||||
role: ChatCompletionRequestMessageRoleEnum.System,
|
||||
content
|
||||
});
|
||||
}
|
||||
} else {
|
||||
const aiResults: ChatCompletionMessageParam[] = [];
|
||||
|
||||
@@ -174,137 +177,24 @@ export const GPTMessages2Chats = (
|
||||
): ChatItemType[] => {
|
||||
const chatMessages = messages
|
||||
.map((item) => {
|
||||
const value: ChatItemType['value'] = [];
|
||||
const obj = GPT2Chat[item.role];
|
||||
|
||||
if (
|
||||
obj === ChatRoleEnum.System &&
|
||||
item.role === ChatCompletionRequestMessageRoleEnum.System
|
||||
) {
|
||||
if (Array.isArray(item.content)) {
|
||||
item.content.forEach((item) => [
|
||||
value.push({
|
||||
type: ChatItemValueTypeEnum.text,
|
||||
text: {
|
||||
content: item.text
|
||||
}
|
||||
})
|
||||
]);
|
||||
} else {
|
||||
value.push({
|
||||
type: ChatItemValueTypeEnum.text,
|
||||
text: {
|
||||
content: item.content
|
||||
}
|
||||
});
|
||||
}
|
||||
} else if (
|
||||
obj === ChatRoleEnum.Human &&
|
||||
item.role === ChatCompletionRequestMessageRoleEnum.User
|
||||
) {
|
||||
if (typeof item.content === 'string') {
|
||||
value.push({
|
||||
type: ChatItemValueTypeEnum.text,
|
||||
text: {
|
||||
content: item.content
|
||||
}
|
||||
});
|
||||
} else if (Array.isArray(item.content)) {
|
||||
item.content.forEach((item) => {
|
||||
if (item.type === 'text') {
|
||||
const value = (() => {
|
||||
if (
|
||||
obj === ChatRoleEnum.System &&
|
||||
item.role === ChatCompletionRequestMessageRoleEnum.System
|
||||
) {
|
||||
const value: SystemChatItemValueItemType[] = [];
|
||||
|
||||
if (Array.isArray(item.content)) {
|
||||
item.content.forEach((item) => [
|
||||
value.push({
|
||||
type: ChatItemValueTypeEnum.text,
|
||||
text: {
|
||||
content: item.text
|
||||
}
|
||||
});
|
||||
} else if (item.type === 'image_url') {
|
||||
value.push({
|
||||
//@ts-ignore
|
||||
type: ChatItemValueTypeEnum.file,
|
||||
file: {
|
||||
type: ChatFileTypeEnum.image,
|
||||
name: '',
|
||||
url: item.image_url.url
|
||||
}
|
||||
});
|
||||
} else if (item.type === 'file_url') {
|
||||
value.push({
|
||||
// @ts-ignore
|
||||
type: ChatItemValueTypeEnum.file,
|
||||
file: {
|
||||
type: ChatFileTypeEnum.file,
|
||||
name: item.name,
|
||||
url: item.url
|
||||
}
|
||||
});
|
||||
}
|
||||
});
|
||||
}
|
||||
} else if (
|
||||
obj === ChatRoleEnum.AI &&
|
||||
item.role === ChatCompletionRequestMessageRoleEnum.Assistant
|
||||
) {
|
||||
if (item.tool_calls && reserveTool) {
|
||||
// save tool calls
|
||||
const toolCalls = item.tool_calls as ChatCompletionMessageToolCall[];
|
||||
value.push({
|
||||
//@ts-ignore
|
||||
type: ChatItemValueTypeEnum.tool,
|
||||
tools: toolCalls.map((tool) => {
|
||||
let toolResponse =
|
||||
messages.find(
|
||||
(msg) =>
|
||||
msg.role === ChatCompletionRequestMessageRoleEnum.Tool &&
|
||||
msg.tool_call_id === tool.id
|
||||
)?.content || '';
|
||||
toolResponse =
|
||||
typeof toolResponse === 'string' ? toolResponse : JSON.stringify(toolResponse);
|
||||
|
||||
return {
|
||||
id: tool.id,
|
||||
toolName: tool.toolName || '',
|
||||
toolAvatar: tool.toolAvatar || '',
|
||||
functionName: tool.function.name,
|
||||
params: tool.function.arguments,
|
||||
response: toolResponse as string
|
||||
};
|
||||
})
|
||||
});
|
||||
} else if (item.function_call && reserveTool) {
|
||||
const functionCall = item.function_call as ChatCompletionMessageFunctionCall;
|
||||
const functionResponse = messages.find(
|
||||
(msg) =>
|
||||
msg.role === ChatCompletionRequestMessageRoleEnum.Function &&
|
||||
msg.name === item.function_call?.name
|
||||
) as ChatCompletionFunctionMessageParam;
|
||||
|
||||
if (functionResponse) {
|
||||
value.push({
|
||||
//@ts-ignore
|
||||
type: ChatItemValueTypeEnum.tool,
|
||||
tools: [
|
||||
{
|
||||
id: functionCall.id || '',
|
||||
toolName: functionCall.toolName || '',
|
||||
toolAvatar: functionCall.toolAvatar || '',
|
||||
functionName: functionCall.name,
|
||||
params: functionCall.arguments,
|
||||
response: functionResponse.content || ''
|
||||
}
|
||||
]
|
||||
});
|
||||
}
|
||||
} else if (item.interactive) {
|
||||
value.push({
|
||||
//@ts-ignore
|
||||
type: ChatItemValueTypeEnum.interactive,
|
||||
interactive: item.interactive
|
||||
});
|
||||
} else if (typeof item.content === 'string') {
|
||||
const lastValue = value[value.length - 1];
|
||||
if (lastValue && lastValue.type === ChatItemValueTypeEnum.text && lastValue.text) {
|
||||
lastValue.text.content += item.content;
|
||||
})
|
||||
]);
|
||||
} else {
|
||||
value.push({
|
||||
type: ChatItemValueTypeEnum.text,
|
||||
@@ -313,8 +203,145 @@ export const GPTMessages2Chats = (
|
||||
}
|
||||
});
|
||||
}
|
||||
return value;
|
||||
} else if (
|
||||
obj === ChatRoleEnum.Human &&
|
||||
item.role === ChatCompletionRequestMessageRoleEnum.User
|
||||
) {
|
||||
const value: UserChatItemValueItemType[] = [];
|
||||
|
||||
if (typeof item.content === 'string') {
|
||||
value.push({
|
||||
type: ChatItemValueTypeEnum.text,
|
||||
text: {
|
||||
content: item.content
|
||||
}
|
||||
});
|
||||
} else if (Array.isArray(item.content)) {
|
||||
item.content.forEach((item) => {
|
||||
if (item.type === 'text') {
|
||||
value.push({
|
||||
type: ChatItemValueTypeEnum.text,
|
||||
text: {
|
||||
content: item.text
|
||||
}
|
||||
});
|
||||
} else if (item.type === 'image_url') {
|
||||
value.push({
|
||||
//@ts-ignore
|
||||
type: ChatItemValueTypeEnum.file,
|
||||
file: {
|
||||
type: ChatFileTypeEnum.image,
|
||||
name: '',
|
||||
url: item.image_url.url
|
||||
}
|
||||
});
|
||||
} else if (item.type === 'file_url') {
|
||||
value.push({
|
||||
// @ts-ignore
|
||||
type: ChatItemValueTypeEnum.file,
|
||||
file: {
|
||||
type: ChatFileTypeEnum.file,
|
||||
name: item.name,
|
||||
url: item.url
|
||||
}
|
||||
});
|
||||
}
|
||||
});
|
||||
}
|
||||
return value;
|
||||
} else if (
|
||||
obj === ChatRoleEnum.AI &&
|
||||
item.role === ChatCompletionRequestMessageRoleEnum.Assistant
|
||||
) {
|
||||
const value: AIChatItemValueItemType[] = [];
|
||||
|
||||
if (typeof item.reasoning_text === 'string') {
|
||||
value.push({
|
||||
type: ChatItemValueTypeEnum.reasoning,
|
||||
reasoning: {
|
||||
content: item.reasoning_text
|
||||
}
|
||||
});
|
||||
}
|
||||
if (item.tool_calls && reserveTool) {
|
||||
// save tool calls
|
||||
const toolCalls = item.tool_calls as ChatCompletionMessageToolCall[];
|
||||
value.push({
|
||||
//@ts-ignore
|
||||
type: ChatItemValueTypeEnum.tool,
|
||||
tools: toolCalls.map((tool) => {
|
||||
let toolResponse =
|
||||
messages.find(
|
||||
(msg) =>
|
||||
msg.role === ChatCompletionRequestMessageRoleEnum.Tool &&
|
||||
msg.tool_call_id === tool.id
|
||||
)?.content || '';
|
||||
toolResponse =
|
||||
typeof toolResponse === 'string' ? toolResponse : JSON.stringify(toolResponse);
|
||||
|
||||
return {
|
||||
id: tool.id,
|
||||
toolName: tool.toolName || '',
|
||||
toolAvatar: tool.toolAvatar || '',
|
||||
functionName: tool.function.name,
|
||||
params: tool.function.arguments,
|
||||
response: toolResponse as string
|
||||
};
|
||||
})
|
||||
});
|
||||
}
|
||||
if (item.function_call && reserveTool) {
|
||||
const functionCall = item.function_call as ChatCompletionMessageFunctionCall;
|
||||
const functionResponse = messages.find(
|
||||
(msg) =>
|
||||
msg.role === ChatCompletionRequestMessageRoleEnum.Function &&
|
||||
msg.name === item.function_call?.name
|
||||
) as ChatCompletionFunctionMessageParam;
|
||||
|
||||
if (functionResponse) {
|
||||
value.push({
|
||||
//@ts-ignore
|
||||
type: ChatItemValueTypeEnum.tool,
|
||||
tools: [
|
||||
{
|
||||
id: functionCall.id || '',
|
||||
toolName: functionCall.toolName || '',
|
||||
toolAvatar: functionCall.toolAvatar || '',
|
||||
functionName: functionCall.name,
|
||||
params: functionCall.arguments,
|
||||
response: functionResponse.content || ''
|
||||
}
|
||||
]
|
||||
});
|
||||
}
|
||||
}
|
||||
if (item.interactive) {
|
||||
value.push({
|
||||
//@ts-ignore
|
||||
type: ChatItemValueTypeEnum.interactive,
|
||||
interactive: item.interactive
|
||||
});
|
||||
}
|
||||
if (typeof item.content === 'string') {
|
||||
const lastValue = value[value.length - 1];
|
||||
if (lastValue && lastValue.type === ChatItemValueTypeEnum.text && lastValue.text) {
|
||||
lastValue.text.content += item.content;
|
||||
} else {
|
||||
value.push({
|
||||
type: ChatItemValueTypeEnum.text,
|
||||
text: {
|
||||
content: item.content
|
||||
}
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
return value;
|
||||
}
|
||||
}
|
||||
|
||||
return [];
|
||||
})();
|
||||
|
||||
return {
|
||||
dataId: item.dataId,
|
||||
@@ -349,7 +376,7 @@ export const chatValue2RuntimePrompt = (value: ChatItemValueItemType[]): Runtime
|
||||
};
|
||||
value.forEach((item) => {
|
||||
if (item.type === 'file' && item.file) {
|
||||
prompt.files?.push(item.file);
|
||||
prompt.files.push(item.file);
|
||||
} else if (item.text) {
|
||||
prompt.text += item.text.content;
|
||||
}
|
||||
|
||||
1
packages/global/core/chat/type.d.ts
vendored
@@ -77,6 +77,7 @@ export type AIChatItemValueItemType = {
|
||||
| ChatItemValueTypeEnum.reasoning
|
||||
| ChatItemValueTypeEnum.tool
|
||||
| ChatItemValueTypeEnum.interactive;
|
||||
|
||||
text?: {
|
||||
content: string;
|
||||
};
|
||||
|
||||
19
packages/global/core/dataset/api.d.ts
vendored
@@ -1,5 +1,5 @@
|
||||
import { DatasetDataIndexItemType, DatasetSchemaType } from './type';
|
||||
import { TrainingModeEnum, DatasetCollectionTypeEnum } from './constants';
|
||||
import { DatasetCollectionTypeEnum, DatasetCollectionDataProcessModeEnum } from './constants';
|
||||
import type { LLMModelItemType } from '../ai/model.d';
|
||||
import { ParentIdType } from 'common/parentFolder/type';
|
||||
|
||||
@@ -10,9 +10,11 @@ export type DatasetUpdateBody = {
|
||||
name?: string;
|
||||
avatar?: string;
|
||||
intro?: string;
|
||||
agentModel?: LLMModelItemType;
|
||||
status?: DatasetSchemaType['status'];
|
||||
|
||||
agentModel?: string;
|
||||
vlmModel?: string;
|
||||
|
||||
websiteConfig?: DatasetSchemaType['websiteConfig'];
|
||||
externalReadUrl?: DatasetSchemaType['externalReadUrl'];
|
||||
defaultPermission?: DatasetSchemaType['defaultPermission'];
|
||||
@@ -27,7 +29,10 @@ export type DatasetUpdateBody = {
|
||||
/* ================= collection ===================== */
|
||||
export type DatasetCollectionChunkMetadataType = {
|
||||
parentId?: string;
|
||||
trainingType?: TrainingModeEnum;
|
||||
customPdfParse?: boolean;
|
||||
trainingType?: DatasetCollectionDataProcessModeEnum;
|
||||
imageIndex?: boolean;
|
||||
autoIndexes?: boolean;
|
||||
chunkSize?: number;
|
||||
chunkSplitter?: string;
|
||||
qaPrompt?: string;
|
||||
@@ -131,9 +136,15 @@ export type PostWebsiteSyncParams = {
|
||||
export type PushDatasetDataProps = {
|
||||
collectionId: string;
|
||||
data: PushDatasetDataChunkProps[];
|
||||
trainingMode: TrainingModeEnum;
|
||||
trainingType?: DatasetCollectionDataProcessModeEnum;
|
||||
autoIndexes?: boolean;
|
||||
imageIndex?: boolean;
|
||||
prompt?: string;
|
||||
|
||||
billId?: string;
|
||||
|
||||
// Abandon
|
||||
trainingMode?: DatasetCollectionDataProcessModeEnum;
|
||||
};
|
||||
export type PushDatasetDataResponse = {
|
||||
insertLen: number;
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
import { DatasetCollectionTypeEnum, TrainingModeEnum, TrainingTypeMap } from '../constants';
|
||||
import { DatasetCollectionTypeEnum } from '../constants';
|
||||
import { DatasetCollectionSchemaType } from '../type';
|
||||
|
||||
export const getCollectionSourceData = (collection?: DatasetCollectionSchemaType) => {
|
||||
@@ -16,9 +16,3 @@ export const getCollectionSourceData = (collection?: DatasetCollectionSchemaType
|
||||
export const checkCollectionIsFolder = (type: DatasetCollectionTypeEnum) => {
|
||||
return type === DatasetCollectionTypeEnum.folder || type === DatasetCollectionTypeEnum.virtual;
|
||||
};
|
||||
|
||||
export const getTrainingTypeLabel = (type?: TrainingModeEnum) => {
|
||||
if (!type) return '';
|
||||
if (!TrainingTypeMap[type]) return '';
|
||||
return TrainingTypeMap[type].label;
|
||||
};
|
||||
|
||||
@@ -109,6 +109,26 @@ export const DatasetCollectionSyncResultMap = {
|
||||
}
|
||||
};
|
||||
|
||||
export enum DatasetCollectionDataProcessModeEnum {
|
||||
chunk = 'chunk',
|
||||
qa = 'qa',
|
||||
auto = 'auto' // abandon
|
||||
}
|
||||
export const DatasetCollectionDataProcessModeMap = {
|
||||
[DatasetCollectionDataProcessModeEnum.chunk]: {
|
||||
label: i18nT('common:core.dataset.training.Chunk mode'),
|
||||
tooltip: i18nT('common:core.dataset.import.Chunk Split Tip')
|
||||
},
|
||||
[DatasetCollectionDataProcessModeEnum.qa]: {
|
||||
label: i18nT('common:core.dataset.training.QA mode'),
|
||||
tooltip: i18nT('common:core.dataset.import.QA Import Tip')
|
||||
},
|
||||
[DatasetCollectionDataProcessModeEnum.auto]: {
|
||||
label: i18nT('common:core.dataset.training.Auto mode'),
|
||||
tooltip: i18nT('common:core.dataset.training.Auto mode Tip')
|
||||
}
|
||||
};
|
||||
|
||||
/* ------------ data -------------- */
|
||||
|
||||
/* ------------ training -------------- */
|
||||
@@ -124,28 +144,11 @@ export enum ImportDataSourceEnum {
|
||||
|
||||
export enum TrainingModeEnum {
|
||||
chunk = 'chunk',
|
||||
qa = 'qa',
|
||||
auto = 'auto',
|
||||
qa = 'qa'
|
||||
image = 'image'
|
||||
}
|
||||
|
||||
export const TrainingTypeMap = {
|
||||
[TrainingModeEnum.chunk]: {
|
||||
label: i18nT('common:core.dataset.training.Chunk mode'),
|
||||
tooltip: i18nT('common:core.dataset.import.Chunk Split Tip'),
|
||||
openSource: true
|
||||
},
|
||||
[TrainingModeEnum.auto]: {
|
||||
label: i18nT('common:core.dataset.training.Auto mode'),
|
||||
tooltip: i18nT('common:core.dataset.training.Auto mode Tip'),
|
||||
openSource: false
|
||||
},
|
||||
[TrainingModeEnum.qa]: {
|
||||
label: i18nT('common:core.dataset.training.QA mode'),
|
||||
tooltip: i18nT('common:core.dataset.import.QA Import Tip'),
|
||||
openSource: true
|
||||
}
|
||||
};
|
||||
|
||||
/* ------------ search -------------- */
|
||||
export enum DatasetSearchModeEnum {
|
||||
embedding = 'embedding',
|
||||
|
||||
25
packages/global/core/dataset/controller.d.ts
vendored
@@ -20,9 +20,22 @@ export type UpdateDatasetDataProps = {
|
||||
})[];
|
||||
};
|
||||
|
||||
export type PatchIndexesProps = {
|
||||
type: 'create' | 'update' | 'delete' | 'unChange';
|
||||
index: Omit<DatasetDataIndexItemType, 'dataId'> & {
|
||||
dataId?: string;
|
||||
};
|
||||
};
|
||||
export type PatchIndexesProps =
|
||||
| {
|
||||
type: 'create';
|
||||
index: Omit<DatasetDataIndexItemType, 'dataId'> & {
|
||||
dataId?: string;
|
||||
};
|
||||
}
|
||||
| {
|
||||
type: 'update';
|
||||
index: DatasetDataIndexItemType;
|
||||
}
|
||||
| {
|
||||
type: 'delete';
|
||||
index: DatasetDataIndexItemType;
|
||||
}
|
||||
| {
|
||||
type: 'unChange';
|
||||
index: DatasetDataIndexItemType;
|
||||
};
|
||||
|
||||
42
packages/global/core/dataset/data/constants.ts
Normal file
@@ -0,0 +1,42 @@
|
||||
import { i18nT } from '../../../../web/i18n/utils';
|
||||
|
||||
export enum DatasetDataIndexTypeEnum {
|
||||
default = 'default',
|
||||
custom = 'custom',
|
||||
summary = 'summary',
|
||||
question = 'question',
|
||||
image = 'image'
|
||||
}
|
||||
|
||||
export const DatasetDataIndexMap: Record<
|
||||
`${DatasetDataIndexTypeEnum}`,
|
||||
{
|
||||
label: any;
|
||||
color: string;
|
||||
}
|
||||
> = {
|
||||
[DatasetDataIndexTypeEnum.default]: {
|
||||
label: i18nT('dataset:data_index_default'),
|
||||
color: 'gray'
|
||||
},
|
||||
[DatasetDataIndexTypeEnum.custom]: {
|
||||
label: i18nT('dataset:data_index_custom'),
|
||||
color: 'blue'
|
||||
},
|
||||
[DatasetDataIndexTypeEnum.summary]: {
|
||||
label: i18nT('dataset:data_index_summary'),
|
||||
color: 'green'
|
||||
},
|
||||
[DatasetDataIndexTypeEnum.question]: {
|
||||
label: i18nT('dataset:data_index_question'),
|
||||
color: 'red'
|
||||
},
|
||||
[DatasetDataIndexTypeEnum.image]: {
|
||||
label: i18nT('dataset:data_index_image'),
|
||||
color: 'purple'
|
||||
}
|
||||
};
|
||||
export const defaultDatasetIndexData = DatasetDataIndexMap[DatasetDataIndexTypeEnum.custom];
|
||||
export const getDatasetIndexMapData = (type: `${DatasetDataIndexTypeEnum}`) => {
|
||||
return DatasetDataIndexMap[type] || defaultDatasetIndexData;
|
||||
};
|
||||
20
packages/global/core/dataset/training/type.d.ts
vendored
Normal file
@@ -0,0 +1,20 @@
|
||||
import { PushDatasetDataChunkProps } from '../api';
|
||||
import { TrainingModeEnum } from '../constants';
|
||||
|
||||
export type PushDataToTrainingQueueProps = {
|
||||
teamId: string;
|
||||
tmbId: string;
|
||||
datasetId: string;
|
||||
collectionId: string;
|
||||
|
||||
mode?: TrainingModeEnum;
|
||||
data: PushDatasetDataChunkProps[];
|
||||
prompt?: string;
|
||||
|
||||
agentModel: string;
|
||||
vectorModel: string;
|
||||
vlmModel?: string;
|
||||
|
||||
billId?: string;
|
||||
session?: ClientSession;
|
||||
};
|
||||
46
packages/global/core/dataset/type.d.ts
vendored
@@ -2,6 +2,7 @@ import type { LLMModelItemType, EmbeddingModelItemType } from '../../core/ai/mod
|
||||
import { PermissionTypeEnum } from '../../support/permission/constant';
|
||||
import { PushDatasetDataChunkProps } from './api';
|
||||
import {
|
||||
DatasetCollectionDataProcessModeEnum,
|
||||
DatasetCollectionTypeEnum,
|
||||
DatasetStatusEnum,
|
||||
DatasetTypeEnum,
|
||||
@@ -12,6 +13,7 @@ import { DatasetPermission } from '../../support/permission/dataset/controller';
|
||||
import { Permission } from '../../support/permission/controller';
|
||||
import { APIFileServer, FeishuServer, YuqueServer } from './apiDataset';
|
||||
import { SourceMemberType } from 'support/user/type';
|
||||
import { DatasetDataIndexTypeEnum } from './data/constants';
|
||||
|
||||
export type DatasetSchemaType = {
|
||||
_id: string;
|
||||
@@ -23,11 +25,14 @@ export type DatasetSchemaType = {
|
||||
|
||||
avatar: string;
|
||||
name: string;
|
||||
vectorModel: string;
|
||||
agentModel: string;
|
||||
intro: string;
|
||||
type: `${DatasetTypeEnum}`;
|
||||
status: `${DatasetStatusEnum}`;
|
||||
|
||||
vectorModel: string;
|
||||
agentModel: string;
|
||||
vlmModel?: string;
|
||||
|
||||
websiteConfig?: {
|
||||
url: string;
|
||||
selector: string;
|
||||
@@ -52,26 +57,22 @@ export type DatasetCollectionSchemaType = {
|
||||
parentId?: string;
|
||||
name: string;
|
||||
type: DatasetCollectionTypeEnum;
|
||||
createTime: Date;
|
||||
updateTime: Date;
|
||||
forbid?: boolean;
|
||||
|
||||
trainingType: TrainingModeEnum;
|
||||
chunkSize: number;
|
||||
chunkSplitter?: string;
|
||||
qaPrompt?: string;
|
||||
ocrParse?: boolean;
|
||||
|
||||
tags?: string[];
|
||||
|
||||
createTime: Date;
|
||||
updateTime: Date;
|
||||
|
||||
// Status
|
||||
forbid?: boolean;
|
||||
nextSyncTime?: Date;
|
||||
|
||||
// Collection metadata
|
||||
fileId?: string; // local file id
|
||||
rawLink?: string; // link url
|
||||
externalFileId?: string; //external file id
|
||||
apiFileId?: string; // api file id
|
||||
externalFileUrl?: string; // external import url
|
||||
|
||||
nextSyncTime?: Date;
|
||||
|
||||
rawTextLength?: number;
|
||||
hashRawText?: string;
|
||||
metadata?: {
|
||||
@@ -80,6 +81,16 @@ export type DatasetCollectionSchemaType = {
|
||||
|
||||
[key: string]: any;
|
||||
};
|
||||
|
||||
// Parse settings
|
||||
customPdfParse?: boolean;
|
||||
// Chunk settings
|
||||
autoIndexes?: boolean;
|
||||
imageIndex?: boolean;
|
||||
trainingType: DatasetCollectionDataProcessModeEnum;
|
||||
chunkSize: number;
|
||||
chunkSplitter?: string;
|
||||
qaPrompt?: string;
|
||||
};
|
||||
|
||||
export type DatasetCollectionTagsSchemaType = {
|
||||
@@ -90,7 +101,7 @@ export type DatasetCollectionTagsSchemaType = {
|
||||
};
|
||||
|
||||
export type DatasetDataIndexItemType = {
|
||||
defaultIndex: boolean;
|
||||
type: `${DatasetDataIndexTypeEnum}`;
|
||||
dataId: string; // pg data id
|
||||
text: string;
|
||||
};
|
||||
@@ -141,6 +152,7 @@ export type DatasetTrainingSchemaType = {
|
||||
chunkIndex: number;
|
||||
weight: number;
|
||||
indexes: Omit<DatasetDataIndexItemType, 'dataId'>[];
|
||||
retryCount: number;
|
||||
};
|
||||
|
||||
export type CollectionWithDatasetType = DatasetCollectionSchemaType & {
|
||||
@@ -169,9 +181,10 @@ export type DatasetListItemType = {
|
||||
sourceMember?: SourceMemberType;
|
||||
};
|
||||
|
||||
export type DatasetItemType = Omit<DatasetSchemaType, 'vectorModel' | 'agentModel'> & {
|
||||
export type DatasetItemType = Omit<DatasetSchemaType, 'vectorModel' | 'agentModel' | 'vlmModel'> & {
|
||||
vectorModel: EmbeddingModelItemType;
|
||||
agentModel: LLMModelItemType;
|
||||
vlmModel?: LLMModelItemType;
|
||||
permission: DatasetPermission;
|
||||
};
|
||||
|
||||
@@ -192,6 +205,7 @@ export type DatasetCollectionItemType = CollectionWithDatasetType & {
|
||||
sourceId?: string;
|
||||
file?: DatasetFileSchema;
|
||||
permission: DatasetPermission;
|
||||
indexAmount: number;
|
||||
};
|
||||
|
||||
/* ================= data ===================== */
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
import { TrainingModeEnum, DatasetCollectionTypeEnum } from './constants';
|
||||
import { getFileIcon } from '../../common/file/icon';
|
||||
import { strIsLink } from '../../common/string/tools';
|
||||
import { DatasetDataIndexTypeEnum } from './data/constants';
|
||||
|
||||
export function getCollectionIcon(
|
||||
type: DatasetCollectionTypeEnum = DatasetCollectionTypeEnum.file,
|
||||
@@ -38,14 +39,23 @@ export function getSourceNameIcon({
|
||||
}
|
||||
|
||||
/* get dataset data default index */
|
||||
export function getDefaultIndex(props?: { q?: string; a?: string; dataId?: string }) {
|
||||
const { q = '', a, dataId } = props || {};
|
||||
const qaStr = `${q}\n${a}`.trim();
|
||||
return {
|
||||
defaultIndex: true,
|
||||
text: a ? qaStr : q,
|
||||
dataId
|
||||
};
|
||||
export function getDefaultIndex(props?: { q?: string; a?: string }) {
|
||||
const { q = '', a } = props || {};
|
||||
|
||||
return [
|
||||
{
|
||||
text: q,
|
||||
type: DatasetDataIndexTypeEnum.default
|
||||
},
|
||||
...(a
|
||||
? [
|
||||
{
|
||||
text: a,
|
||||
type: DatasetDataIndexTypeEnum.default
|
||||
}
|
||||
]
|
||||
: [])
|
||||
];
|
||||
}
|
||||
|
||||
export const predictDataLimitLength = (mode: TrainingModeEnum, data: any[]) => {
|
||||
|
||||
@@ -10,6 +10,7 @@ import { FlowNodeOutputItemType, ReferenceValueType } from '../type/io';
|
||||
import { ChatItemType, NodeOutputItemType } from '../../../core/chat/type';
|
||||
import { ChatItemValueTypeEnum, ChatRoleEnum } from '../../../core/chat/constants';
|
||||
import { replaceVariable, valToStr } from '../../../common/string/tools';
|
||||
import { ChatCompletionChunk } from 'openai/resources';
|
||||
|
||||
export const getMaxHistoryLimitFromNodes = (nodes: StoreNodeItemType[]): number => {
|
||||
let limit = 10;
|
||||
|
||||
@@ -55,7 +55,7 @@ export const AiChatModule: FlowNodeTemplateType = {
|
||||
showStatus: true,
|
||||
isTool: true,
|
||||
courseUrl: '/docs/guide/workbench/workflow/ai_chat/',
|
||||
version: '4813',
|
||||
version: '490',
|
||||
inputs: [
|
||||
Input_Template_SettingAiModel,
|
||||
// --- settings modal
|
||||
|
||||
@@ -58,6 +58,13 @@ export const ToolModule: FlowNodeTemplateType = {
|
||||
valueType: WorkflowIOValueTypeEnum.boolean,
|
||||
value: true
|
||||
},
|
||||
{
|
||||
key: NodeInputKeyEnum.aiChatReasoning,
|
||||
renderTypeList: [FlowNodeInputTypeEnum.hidden],
|
||||
label: '',
|
||||
valueType: WorkflowIOValueTypeEnum.boolean,
|
||||
value: true
|
||||
},
|
||||
{
|
||||
key: NodeInputKeyEnum.aiChatTopP,
|
||||
renderTypeList: [FlowNodeInputTypeEnum.hidden],
|
||||
|
||||
10
packages/global/support/user/api.d.ts
vendored
@@ -1,5 +1,9 @@
|
||||
import { MemberGroupSchemaType, MemberGroupType } from 'support/permission/memberGroup/type';
|
||||
import { OAuthEnum } from './constant';
|
||||
import { TrackRegisterParams } from './login/api';
|
||||
import { TeamMemberStatusEnum } from './team/constant';
|
||||
import { OrgType } from './team/org/type';
|
||||
import { TeamMemberItemType } from './team/type';
|
||||
|
||||
export type PostLoginProps = {
|
||||
username: string;
|
||||
@@ -21,3 +25,9 @@ export type FastLoginProps = {
|
||||
token: string;
|
||||
code: string;
|
||||
};
|
||||
|
||||
export type SearchResult = {
|
||||
members: Omit<TeamMemberItemType, 'teamId' | 'permission'>[];
|
||||
orgs: Omit<OrgType, 'permission' | 'members'>[];
|
||||
groups: MemberGroupSchemaType[];
|
||||
};
|
||||
|
||||