# NAS RAG Stack: Storage, Embeddings, Vector Database and Local LLM

> Keep original documents on a protected NAS share, use SSD/NVMe for vector indexes and RAG application databases, and run embedding/LLM services on the best available compute host. Track document identity and permissions through ingestion so removing or restricting a source also removes or isolates its derived chunks and embeddings.

Canonical: https://cloudzat.com/nas-rag-stack/

Use the canonical page for live hardware availability and current deployment guidance.

## Related Cloudzat guidance
- [Ollama on NAS](https://cloudzat.com/ollama-on-nas/)
- [Open WebUI on NAS](https://cloudzat.com/openwebui-on-nas/)
- [AnythingLLM on NAS](https://cloudzat.com/anythingllm-on-nas/)
- [n8n on NAS with Local AI](https://cloudzat.com/n8n-on-nas-local-ai/)