使用1panel进行docker部署

安装好1panel之后在应用商店找到openresty和docker compose安装(点容器会有一键安装)

安装好之后点击容器创建编排模板

我是用方法四：
```
## ===================================================
## 「方案四」 ChatGPT + Latex
## ===================================================
version: '3'
services:
gpt_academic_with_latex:
image: ghcr.io/binary-husky/gpt_academic_with_latex:master # (Auto Built by Dockerfile: docs/GithubAction+NoLocal+Latex)
# 对于ARM64设备，请将以上镜像名称替换为 ghcr.io/binary-husky/gpt_academic_with_latex_arm:master
environment:
# 请查阅 `config.py` 以查看所有的配置信息
API_KEY: ' sk-xxx '
DEEPSEEK_API_KEY: 'sk-xxx '
#如果用的官方key API_URL_REDIRECT就可以删掉，中转key就自己填中转服务商
API_URL_REDIRECT: '{"https://api.openai.com/v1/chat/completions": "https://xxx.yyy.zzz/v1/chat/completions", "https://api.deepseek.com/v1/chat/completions": "https://xxx.yyy.zzz/v1/chat/completions"}'

USE_PROXY: ' False '
LLM_MODEL: ' o1-mini '
AVAIL_LLM_MODELS: ' ["qwen-max", "o1-mini", "deepseek-coder", "deepseek-reasoner", "o1-mini-2024-09-12", "o1", "o1-2024-12-17", "o1-preview", "o1-preview-2024-09-12", "gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-preview", "gpt-4o", "gpt-4o-mini", "gpt-4-turbo", "gpt-4-turbo-2024-04-09", "gpt-3.5-turbo-1106", "gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt-3.5", "gpt-4", "gpt-4-32k", "azure-gpt-4", "glm-4", "glm-4v", "glm-3-turbo", "gemini-1.5-pro", "chatglm3", "chatglm4"] '
LOCAL_MODEL_DEVICE: ' cuda '
DEFAULT_WORKER_NUM: ' 16 '
WEB_PORT: ' 22303 '

# 「WEB_PORT暴露方法1: 适用于Linux」与宿主的网络融合
network_mode: "host"

# 启动命令
command: >
bash -c "python3 -u main.py"

```

#编排好之后就可以使用IP:22303进入
#如果要绑定域名可以点击网站

填好就行，域名记得解析到服务器
证书也可以依靠cloudflare申请

Start by reviewing the deployment steps and the referenced config.py and main.py entry points, then verify the Docker Compose example in a 1Panel environment. Done means a clearly located documentation page explains the setup, access on port 22303, domain binding, and certificate configuration without exposing real API keys.

Written by the indexing model from the issue text.