You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Support on-premise deployment and connect to self-hosted AI model #94
changed the title [-]我想部署在离线内网服务器上,所以能支持其他离线ai模型吗?GPT需要联网,支持自定义AI模型吗[/-][+]Support on-premise deployment and connect to self-hosted AI model[/+]on May 18, 2023
Activity
[-]我想部署在离线内网服务器上,所以能支持其他离线ai模型吗?GPT需要联网,支持自定义AI模型吗[/-][+]Support on-premise deployment and connect to self-hosted AI model[/+]502647092 commentedon Jul 4, 2024
可以自己本地部署 Ollama
通过 ollama cp 模型名称 gpt-4 复制一个模型
502647092 commentedon Jul 17, 2024
直接 docker compose 起一个 ollama
然后
docker exec -it ollama bash终端拉取 glm4 或者 qwen2 模型
然后复制模型到 gpt4
之后就可以用了
unstoppbale9527 commentedon Aug 21, 2025
ollama启动模型成功后需要 sqlcaht怎么连接ollama
docker run --name sqlchat --platform linux/amd64 --env NEXTAUTH_SECRET="$(openssl rand -hex 5)" -p 3000:3000 --hostname 0.0.0.0 sqlchat/sqlchat:latest