# Self-Hosted AI

> Posts about Self-Hosted AI on abchaudary.me.

- [Qdrant and BGE-M3: Hybrid Search Without a Second Model](https://abchaudary.me/blog/qdrant-bge-m3-hybrid-search-rag): BGE-M3 produces dense and sparse vectors from one pass, so Qdrant can run hybrid search for production RAG without a second embedding model: prefetch both, fuse with RRF, filter early.