← Library← 内容库LIBRARY · DEPLOYMENT GUIDES内容库 · 部署指南

Build it. Check it. Keep it running.搭建、验证,然后稳定运行。

Step-by-step guides with prerequisites, commands, validation checks and the limitations you need to know before production.包含前置要求、操作命令、验证方法和上线前必须了解的限制。

Browse guides浏览指南View the full library查看完整内容库
AI Application DeploymentAI 应用部署D
●●○○○ · 20 min

Deploy Open WebUI with Docker and Persistent Storage使用 Docker 和持久化存储部署 Open WebUI

Run Open WebUI in Docker, persist application data, connect it to Ollama and add the production safeguards recommended by the project documentation.使用 Docker 运行 Open WebUI、持久化应用数据、连接 Ollama,并补充官方文档建议的生产环境安全措施。

Environment
Linux with Docker; 2 CPU cores and 4 GB RAM is a practical UI starting point, excluding model inferenceLinux 与 Docker;仅运行界面可从 2 核 4GB 起步,不包含模型推理资源
Steps
5
Read deployment guide →阅读部署教程 →
AI Application DeploymentAI 应用部署I
●●●○○ · 25 min

Install Ollama on Linux and Expose It Safely在 Linux 上安装 Ollama 并安全提供服务

Install Ollama on Linux, run a first model, verify the local API and understand why port 11434 should not be exposed to the public internet without authentication.在 Linux 上安装 Ollama、运行首个模型、验证本地 API,并理解为什么不能在没有认证的情况下把 11434 端口直接暴露到公网。

Environment
64-bit Linux; model-specific RAM, disk and optional GPU capacity64 位 Linux;内存、硬盘和可选 GPU 容量取决于具体模型
Steps
5
Read deployment guide →阅读部署教程 →