This commit is contained in:
archer
2023-05-10 18:28:20 +08:00
parent 1c8ce369b6
commit 250399a1aa
9 changed files with 111 additions and 9 deletions

View File

@@ -4,9 +4,10 @@
选择一个即可。
1. [clash 方案](./proxy/clash.md) - 仅需一台服务器(需要有 clash
2. [nginx 方案](./proxy/nginx.md) - 需要一台国外服务器
3. [cloudflare 方案](./proxy/cloudflare.md) - 需要有域名(每日免费 10w 次代理请求)
1. [sealos nginx 方案](./proxy/sealos.md) - 推荐。约等于不用钱,不需要额外准备任何东西。
2. [clash 方案](./proxy/clash.md) - 仅需一台服务器(需要有 clash
3. [nginx 方案](./proxy/nginx.md) - 需要一台国外服务器
4. [cloudflare 方案](./proxy/cloudflare.md) - 需要有域名(每日免费 10w 次代理请求)
### 1. 准备一些内容
@@ -179,7 +180,7 @@ services:
- /root/fastgpt/nginx/ssl/docgpt.key:/ssl/docgpt.key
- /root/fastgpt/nginx/ssl/docgpt.pem:/ssl/docgpt.pem
pg:
image: ankane/pgvector
image: ankane/pgvector:v0.4.1
container_name: pg
restart: always
ports:

View File

@@ -49,7 +49,7 @@ services:
- /root/fastgpt/nginx/ssl/docgpt.key:/ssl/docgpt.key
- /root/fastgpt/nginx/ssl/docgpt.pem:/ssl/docgpt.pem
pg:
image: ankane/pgvector
image: ankane/pgvector:v0.4.1
container_name: pg
restart: always
ports:

Binary file not shown.

After

Width:  |  Height:  |  Size: 2.9 MiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 205 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 152 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 88 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 224 KiB

View File

@@ -1,4 +1,5 @@
# nginx 反向代理 openai 接口
如果你有国外的服务器,可以通过配置 nginx 反向代理,转发 openai 相关的请求,从而让国内的服务器可以通过访问该 nginx 去访问 openai 接口。
```conf
@@ -19,7 +20,7 @@ http {
client_header_buffer_size 32k;
large_client_header_buffers 4 32k;
client_max_body_size 50M;
gzip on;
gzip_min_length 1k;
gzip_buffers 4 8k;
@@ -43,10 +44,10 @@ http {
location ~ /openai/(.*) {
# auth check
if ($http_authkey != "xxxxxx") {
if ($auth != "xxxxxx") {
return 403;
}
proxy_pass https://api.openai.com/$1$is_args$args;
proxy_set_header Host api.openai.com;
proxy_set_header X-Real-IP $remote_addr;
@@ -69,4 +70,4 @@ http {
rewrite ^(.*) https://$server_name$1 permanent;
}
}
```
```

100
docs/deploy/proxy/sealos.md Normal file
View File

@@ -0,0 +1,100 @@
# sealos 部署 openai 中转
## 登录 sealos cloud
[sealos cloud](https://cloud.sealos.io/)
## 创建应用
打开 App Launchpad -> 新建应用
![step1](./imgs//sealos1.png)
![step2](./imgs//sealos2.png)
### 开启外网访问
![step3](./imgs//sealos3.png)
### 添加 configmap 文件
1. 复制下面这段代码,注意 `server_name` 后面的内容替换成上图的地址。
```
user nginx;
worker_processes auto;
worker_rlimit_nofile 51200;
events {
worker_connections 1024;
}
http {
resolver 8.8.8.8;
proxy_ssl_server_name on;
access_log off;
server_names_hash_bucket_size 512;
client_header_buffer_size 64k;
large_client_header_buffers 4 64k;
client_max_body_size 50M;
proxy_connect_timeout 240s;
proxy_read_timeout 240s;
proxy_buffer_size 128k;
proxy_buffers 4 256k;
server {
listen 80;
server_name tgohwtdlrmer.cloud.sealos.io; # 这个地方替换成 sealos 提供的内容
location ~ /openai/(.*) {
# auth check
if ($http_auth != "auth") { # 安全凭证
return 403;
}
proxy_pass https://api.openai.com/$1$is_args$args;
proxy_set_header Host api.openai.com;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
# 如果响应是流式的
proxy_set_header Connection '';
proxy_http_version 1.1;
chunked_transfer_encoding off;
proxy_buffering off;
proxy_cache off;
# 如果响应是一般的
proxy_buffer_size 128k;
proxy_buffers 4 256k;
proxy_busy_buffers_size 256k;
}
}
}
```
2. 点开高级配置
3. 点击新增 configmap
4. 文件名写: `/etc/nginx/nginx.conf`
5. 文件值为刚刚复制的那段代码
6. 点击确认
![step4](./imgs//sealos4.png)
### 部署应用
填写完毕后,点击右上角的 `部署应用`,即可完成。
## 修改 FastGpt 环境变量
1. 进入刚刚部署应用的详情,复制外网地址
![step5](./imgs//sealos5.png)
2. 修改环境变量:
```
OPENAI_BASE_URL=https://tgohwtdlrmer.cloud.sealos.io/openai/v1
OPENAI_BASE_URL_AUTH=auth
```
**Done!**