// ⌕ RAG & Vector Retrieval
FAISS (Billion-scale GPU Similarity Search)
Meta's library and GPU algorithms for billion-scale vector search.
FAISS GPU 相似度搜索 2017 Intermediate extended
IN PLAIN WORDS
Describes efficient GPU k-selection, IVF and PQ, released as FAISS — the de facto vector search toolkit.
Used in: Under many vector DBs and RAG systems
TIMELINE · prerequisites → this → what builds on it
01Original paper
Billion-scale similarity search with GPUs
Jeff Johnson, Matthijs Douze, Hervé Jégou · 2017
arXiv ↗ ✓ Verified · arXiv API
02Where it sits
Learn the left column first; the right column builds on this one.
FAISS (Billion-scale GPU Similarity Search)
Then you can learn
- Nothing in the atlas builds on it yet
Related:Retrieval-Augmented Generation (RAG)
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
04Where the course teaches it
For AI / data
- Verification: verified, checked 2026-10-21.
- JSON: /api/learn/algorithms.json (id:
faiss)