skills.rest
SethyPagna
SethyPagnaCOMMUNITY
Explore all skills by this author →
GitHub

faiss

Build fast similarity search and clustering indexes for dense vector embeddings across Flat, IVF, HNSW, and PQ families.

Updated May 14, 2026
Search Tags:#embeddings#vector search#similarity search#hnsw#faiss#ivf#nearest neighbors
One-click install
npx skills add https://github.com/SethyPagna/Secretary-Jarvis --skill faiss-sethypagna
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: faiss
Source: https://github.com/SethyPagna/Secretary-Jarvis/tree/main/src/capabilities/optional-skills/mlops/faiss
Command: npx skills add https://github.com/SethyPagna/Secretary-Jarvis --skill faiss-sethypagna

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

FAISS removes the bottleneck of searching huge embedding collections by giving you fast similarity lookup and clustering for dense vectors, including workloads that are too large or too latency-sensitive for naïve brute-force search.

Core Features & Use Cases

  • Large-scale vector search: Run nearest-neighbor retrieval over millions or billions of embeddings.
  • Multiple index strategies: Choose Flat for exact search, IVF for fast approximate search, HNSW for high-quality graph search, and PQ for memory-efficient compression.
  • GPU acceleration: Speed up heavy retrieval workloads with single-GPU or multi-GPU execution.
  • Practical use cases: Semantic search, recommendation engines, RAG retrieval layers, batch embedding analysis, and offline vector clustering.

Quick Start

Use the faiss skill to choose the right vector index, build it from your embeddings, and search for nearest neighbors efficiently.

Frequently Asked Questions about faiss

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run nearest-neighbor search over millions of dense vector embeddings?▼

To run nearest-neighbor search over millions of embeddings, you can build fast similarity indexes using FAISS. It supports large-scale retrieval across Flat, IVF, HNSW, and PQ index families to optimize search performance and latency.

What is the best way to choose between IVF, HNSW, and PQ indexes for similarity search?▼

Choosing between IVF, HNSW, and PQ indexes depends on your requirements: IVF provides fast approximate search, HNSW offers high-quality graph search, and PQ delivers memory-efficient compression for dense vectors, while Flat ensures exact search accuracy.

Can I use GPU acceleration for large-scale vector retrieval workloads?▼

Yes, you can use GPU acceleration for large-scale vector retrieval. FAISS supports single-GPU and multi-GPU backends to speed up heavy similarity search and clustering workloads for dense vector embeddings.

Do I need to train my IVF or PQ vector index before searching?▼

Yes, IVF and PQ vector indexes require training before you can search them. Training calibrates the index structure to your dense vector embeddings, enabling fast approximate nearest-neighbor lookup and memory-efficient compression.

How does FAISS handle semantic search and RAG retrieval layers?▼

FAISS handles semantic search and RAG retrieval layers by building fast similarity indexes for your dense vector embeddings. It retrieves the most relevant nearest neighbors from massive-scale collections to ground your generation models.

Related Skills

Explore More Software Engineering Skills→
zechenzhangAGIzechenzhangAGI
11.5k

faiss

Perform billion-scale k-NN similarity search with FAISS index types and GPU acceleration.

Community
Intermediate
LynxLabVNLynxLabVN

qdrant-vector-search

Perform vector similarity search with Qdrant for nearest neighbor retrieval.

Official
Advanced
qcmuuqcmuu

faiss

Build FAISS indexes and run k-nearest-neighbor queries over dense embeddings.

Community
Intermediate
twjarviszyra-webtwjarviszyra-web
3

faiss

Build exact and approximate FAISS similarity search indexes for dense vectors.

Community
Intermediate