> For the complete documentation index, see [llms.txt](https://mariadb.com/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://mariadb.com/docs/tools/mariadb-ai-rag/deployment.md).

# Management

- [Deployment](https://mariadb.com/docs/tools/mariadb-ai-rag/deployment/overview.md): Deploy MariaDB AI RAG as a Docker stack by downloading the compose file and config template, setting a license key and model credentials, then launching with docker compose up.
- [Network and Firewall Requirements](https://mariadb.com/docs/tools/mariadb-ai-rag/deployment/network-and-firewall-requirements.md): MariaDB AI RAG network requirements specify inbound TCP ports for the REST API and MCP server, outbound HTTPS to AI providers and the licensing server, and optional Ollama port access.
- [Architecture](https://mariadb.com/docs/tools/mariadb-ai-rag/deployment/architecture.md): MariaDB AI RAG deploys as a multi-container Docker stack where a FastAPI gateway, Redis queue, Celery workers, and a Docling Ray service handle ingestion, search, and generation.
- [Troubleshooting Guide](https://mariadb.com/docs/tools/mariadb-ai-rag/deployment/troubleshooting-guide.md): MariaDB AI RAG troubleshooting guide diagnoses startup failures from invalid license keys, port conflicts, database timeouts, stuck pending documents, and Docling Ray extraction errors.