菜单
Plan and execute a minimal OpenRAG installation with requirement drafting, task tracking, configuration guidance, and local verification
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/langflow-ai/openrag --skill openrag-install命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | openrag_install |
| description | Plan and execute a minimal OpenRAG installation with requirement drafting, task tracking, configuration guidance, and local verification |
When the user asks to install OpenRAG, follow this workflow in order.
Before starting installation, check for an existing OpenRAG installation:
~/.openrag/tui/.env existsdocker compose ps for the generated OpenRAG compose file, or by filtering on the compose project/labels instead of docker ps --filter "name=openrag"requirements.mdtodo.mdhttp://localhost:3000 launches without startup errors and http://localhost:5001/docs is reachableFirst, create or update requirements.md using the official OpenRAG installation documentation:
https://docs.openr.ag/install-options as the source of truthREQ-001, REQ-002, and so onInclude the following specific requirement in the spec:
docling-serve on port 5001uvx or uvuvx openraghttp://localhost:5001/docslsof -i :5001 or curl http://localhost:5001/docshttp://localhost:5001/docs is not ready right after startup; wait and re-check because docling-serve may come up after the main OpenRAG servicesAfter drafting requirements.md:
After requirements.md is stable:
requirements.mdtodo.md that breaks the work into concrete taskstodo.md only after they pass validationMost agent shell tools cannot drive interactive terminal applications that require user input. This includes any command that renders a TUI, prompts for passwords, or expects arrow-key navigation.
When the installation reaches the point where uvx openrag needs to be run:
uvx openrag through the agent's shell tool expecting to interact with ituvx --python 3.13 openragdocker ps --filter "name=openrag"lsof -i :3000 and lsof -i :5001curl http://localhost:3000 and curl http://localhost:5001/docsThe next step requires running an interactive command that I cannot control directly.
Please open a NEW terminal window (separate from this agent session) and run:
uvx --python 3.13 openrag
You will see a menu. Follow these steps:
1. Type '2' and press Enter (Reconfigure)
2. Enter a STRONG OpenSearch Admin password (write it down!)
3. Enter Langflow Admin password (or autogenerate)
4. Press 'N' or skip for other prompts
5. Type '1' and press Enter (Start services)
6. Wait for "Services are running" message
Once complete, come back here and confirm: "Configuration and services started successfully"
When a task requires user input, secret values, or interactive terminal control:
uvx openrag in a separate terminal outside the agent's shelluvx openrag interactively through the agent's shellBefore considering the installation complete:
requirements.mdhttp://localhost:3000 firstdocling-serve is reachable at http://localhost:5001/docshttp://localhost:3000 and http://localhost:5001/docs is reachablerequirements.md and todo.md as new validated information is discovered