mirror of
https://github.com/arch3rPro/1Panel-Appstore.git
synced 2026-04-15 00:17:12 +08:00
225 lines
8.0 KiB
Plaintext
225 lines
8.0 KiB
Plaintext
# ChatGPT Adapter 配置示例文件
|
||
# 详细配置请参考官方文档: https://bincooo.github.io/chatgpt-adapter
|
||
|
||
# 基础服务配置
|
||
port: 8080 # 服务端口
|
||
host: "0.0.0.0" # 监听地址,0.0.0.0表示监听所有网卡
|
||
debug: false # 调试模式,开启后会输出详细日志
|
||
timeout: 300 # 请求超时时间(秒)
|
||
cors: true # 是否启用跨域支持
|
||
|
||
# 代理配置(可选) - 某些服务可能需要代理访问
|
||
# proxy: "http://127.0.0.1:7890"
|
||
# proxy: "socks5://127.0.0.1:1080"
|
||
|
||
# ==================== 模型配置 ====================
|
||
|
||
# Coze 国际版配置
|
||
coze:
|
||
websdk:
|
||
model: claude-35-sonnet-200k # 可选: claude-35-sonnet-200k, claude-35-haiku-200k, gpt4o-8k, gpt4o-32k, gpt4o-128k, gpt4-125k, gpt35-16k
|
||
system: "你是一个有用的AI助手"
|
||
bot: custom-128k # 默认bot名称,可自定义
|
||
accounts:
|
||
- email: "your_email@gmail.com"
|
||
password: "your_password"
|
||
validate: "your_email@gmail.com"
|
||
|
||
# Browser-less服务配置 (Coze websdk必需)
|
||
browser-less:
|
||
enabled: true # 启用browser-less服务
|
||
# reversal: "http://your-browser-less-service:8080" # 如果使用外部browser-less服务
|
||
|
||
# 注意:
|
||
# 1. Coze websdk需要browser-less服务来获取cookies,必须配置browser-less.enabled=true或提供reversal URL
|
||
# 2. accounts为gmail登录邮箱,仅限通过输入邮箱验证登录的账户可用,未实现人机验证
|
||
# 3. 对网络要求较高,建议使用稳定的网络环境
|
||
# 4. 也可以自行在coze.com部署websdk后获取bot_id,然后拼接成 coze/{bot_id}-xxxxx-1000-w 字符串作为model参数
|
||
|
||
# Bing Copilot配置 (开发中...)
|
||
bing:
|
||
proxied: true # 是否开启代理
|
||
cookies:
|
||
- scopeId: "your_scope_id" # 从控制台脚本获取
|
||
idToken: "your_id_token" # 从控制台脚本获取
|
||
cookie: "your_bing_cookie" # 从F12网络面板获取
|
||
# 获取方法请参考官方文档中的控制台脚本
|
||
|
||
# Cursor Editor配置
|
||
cursor:
|
||
checksum: 'zo-v9_v2qxRYcau35NDnAHAVxQkLe6IHw8opkpKV4oLyo0PhPeSpj4QTw2VJ20Lngrz7XNTQ/clDRF5FOm3B1uK-mQDyFBRqD8JNj4kLByaAfm4AqK6IMbFYcrqXMMXexubsTRrr1'
|
||
# 注意: checksum为设备id,随机。若不配置将自动生成一个
|
||
# authorization为网页登录后的cookie WorkosCursorSessionToken
|
||
|
||
# ==================== Deepseek配置 ====================
|
||
# Deepseek是一个强大的AI模型,支持中文对话
|
||
deepseek:
|
||
# 必需:从浏览器获取的cookie
|
||
# 获取方法:
|
||
# 1. 访问 https://chat.deepseek.com/ 并登录
|
||
# 2. 打开浏览器开发者工具(F12) -> Network标签
|
||
# 3. 发送一条消息,找到请求头中的Cookie
|
||
# 4. 复制完整的cookie字符串
|
||
cookie: 'intercom-device-id-gxxx .......... xxx'
|
||
|
||
# 可选:自定义User-Agent(海外地区可能需要)
|
||
userAgent: 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/18.3 Safari/605.1.15'
|
||
|
||
# 注意事项:
|
||
# 1. 中国地区通常不需要配置cookie,但如果出现认证失败,仍需要配置
|
||
# 2. 海外地区出现403错误时必须配置cookie和userAgent
|
||
# 3. Cookie有效期有限,失效后需要重新获取
|
||
# 4. 确保浏览器获取cookie时的IP与服务器IP一致(如果使用代理)
|
||
# 5. authorization可通过控制台脚本获取:
|
||
# var token = localStorage.getItem('userToken'); console.log(JSON.parse(token).value);
|
||
|
||
# Windsurf Editor配置
|
||
windsurf:
|
||
proxied: false # 是否使用代理
|
||
# authorization为网页登录后访问 https://codeium.com/profile?referrer=extension
|
||
# F12查看网络面板的 GetAnalytics 请求头x-api-key
|
||
|
||
# You.com配置
|
||
you:
|
||
custom: true # 启动自定义模型,不存在会自动创建
|
||
task: false # 定时器过cf验证
|
||
model:
|
||
- 'custom_model_name' # 自定义模型名称
|
||
cookies:
|
||
- 'your_you_cookie_here' # 完整的cookie字符串
|
||
|
||
# Grok配置
|
||
grok:
|
||
think_reason: false # 是否开启思考模式
|
||
disable_search: false # 是否关闭联网搜索
|
||
cookies:
|
||
- 'your_grok_cookie' # F12打开网络面板抓取cookie
|
||
# authorization = cookie
|
||
|
||
# ==================== 支持的模型列表 ====================
|
||
|
||
# Coze模型:
|
||
# - coze/websdk
|
||
# - coze/{bot_id}-xxxx-1000-w
|
||
|
||
# Bing模型:
|
||
# - bing
|
||
|
||
# Cursor模型:
|
||
# - cursor/claude-3-5-sonnet-20241022
|
||
# - claude-3.7-sonnet
|
||
# - claude-3.7-sonnet-thinking
|
||
# - cursor/claude-3-opus
|
||
# - cursor/claude-3.5-haiku
|
||
# - cursor/claude-3.5-sonnet
|
||
# - cursor/cursor-small
|
||
# - cursor/gpt-3.5-turbo
|
||
# - cursor/gpt-4
|
||
# - cursor/gpt-4-turbo-2024-04-09
|
||
# - cursor/gpt-4o
|
||
# - cursor/gpt-4o-mini
|
||
# - cursor/o1-mini
|
||
# - cursor/o1-prevew
|
||
|
||
# Deepseek模型:
|
||
# - deepseek-chat
|
||
# - deepseek-reasoner
|
||
|
||
# Windsurf模型:
|
||
# - windsurf/claude-3-5-sonnet
|
||
# - claude-3-7-sonnet
|
||
# - claude-3-7-sonnet-think
|
||
# - windsurf/gpt4o
|
||
# - windsurf/deepseek-chat
|
||
# - windsurf/deepseek-reasoner
|
||
# - windsurf/gpt4-o3-mini
|
||
# - windsurf/gemini-2.0-flash
|
||
|
||
# You.com模型:
|
||
# - you/gpt_4
|
||
# - you/gpt_4o
|
||
# - you/gpt_4o_mini
|
||
# - you/gpt_4_turbo
|
||
# - you/openai_o1
|
||
# - you/openai_o1_mini
|
||
# - you/claude_2
|
||
# - you/claude_3_haiku
|
||
# - you/claude_3_sonnet
|
||
# - you/claude_3_5_sonnet
|
||
# - you/claude_3_opus
|
||
# - you/gemini_pro
|
||
# - you/gemini_1_5_pro
|
||
# - you/gemini_1_5_flash
|
||
|
||
# Grok模型:
|
||
# - grok-2
|
||
# - grok-3
|
||
|
||
# ==================== 可选配置 ====================
|
||
|
||
# ==================== 认证配置 ====================
|
||
# API密钥认证 - 为API访问添加安全验证
|
||
auth:
|
||
keys:
|
||
- "sk-chatgpt-adapter-your-custom-key-here" # 自定义API密钥1
|
||
- "sk-another-custom-api-key-for-backup" # 自定义API密钥2(备用)
|
||
- "sk-team-shared-key-for-multiple-users" # 团队共享密钥
|
||
whitelist: # IP白名单(可选) - 只允许特定IP访问
|
||
- "127.0.0.1" # 本地访问
|
||
- "192.168.1.0/24" # 局域网访问
|
||
- "your-server-public-ip" # 您的服务器公网IP
|
||
|
||
# 注意事项:
|
||
# 1. API密钥格式建议以"sk-"开头,但不是强制要求
|
||
# 2. 可以配置多个密钥,支持密钥轮换和备份
|
||
# 3. 如果配置了auth.keys,则所有API请求都必须携带有效的Authorization头
|
||
# 4. IP白名单是可选的,如果配置了则只允许白名单内的IP访问
|
||
# 5. 密钥长度建议至少32位,确保安全性
|
||
|
||
# 日志配置(可选)
|
||
# log:
|
||
# level: "info" # 日志级别: debug/info/warn/error
|
||
# file: "./logs/adapter.log" # 日志文件路径
|
||
# max_size: 100 # 单个日志文件最大大小(MB)
|
||
# max_backups: 5 # 保留的日志文件数量
|
||
# max_age: 30 # 日志文件保留天数
|
||
|
||
# 限流配置(可选) - 防止API滥用
|
||
# rate_limit:
|
||
# requests_per_minute: 60 # 每分钟最大请求数
|
||
# requests_per_hour: 1000 # 每小时最大请求数
|
||
|
||
# 缓存配置(可选) - 提高响应速度
|
||
# cache:
|
||
# type: "memory" # 缓存类型: memory/redis
|
||
# ttl: 3600 # 缓存过期时间(秒)
|
||
# # Redis配置(当type为redis时)
|
||
# # redis:
|
||
# # addr: "localhost:6379"
|
||
# # password: ""
|
||
# # db: 0
|
||
|
||
# ==================== 使用说明 ====================
|
||
# 1. 根据需要启用相应的模型配置
|
||
# 2. Cookie和Token获取方法请参考官方文档: https://bincooo.github.io/chatgpt-adapter
|
||
# 3. 某些服务可能需要代理才能正常访问
|
||
# 4. 建议在生产环境中启用认证和限流配置
|
||
# 5. 调试模式会输出详细日志,生产环境建议关闭
|
||
# 6. 各模型的具体使用方法和参数请参考官方文档对应章节
|
||
|
||
# ==================== API调用示例 ====================
|
||
# curl -i -X POST \
|
||
# -H "Content-Type: application/json" \
|
||
# -H "Authorization: Bearer your_token_here" \
|
||
# -d '{
|
||
# "stream": true,
|
||
# "model": "coze/websdk",
|
||
# "messages": [
|
||
# {
|
||
# "role": "user",
|
||
# "content": "你好"
|
||
# }
|
||
# ]
|
||
# }' \
|
||
# 'http://127.0.0.1:8080/v1/chat/completions'
|