skills.rest
GregsGreyCode
GregsGreyCodeCOMMUNITY
Explore all skills by this author →
GitHub

faiss

Perform scalable vector similarity search over embeddings with FAISS indices.

6|2|Updated Mar 19, 2026
Search Tags:#embedding#vector-search#gpu-acceleration#faiss#nearest-neighbors#k-nn
One-click install
npx skills add https://github.com/GregsGreyCode/Logos --skill faiss-gregsgreycode
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: faiss
Source: https://github.com/GregsGreyCode/Logos/tree/main/skills/mlops/vector-databases/faiss
Command: npx skills add https://github.com/GregsGreyCode/Logos --skill faiss-gregsgreycode

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

FAISS provides fast, scalable vector similarity search for embedding datasets, enabling efficient nearest-neighbor retrieval for large-scale ML deployments.

Core Features & Use Cases

  • Supports Flat (exact), IVF (approximate), HNSW (high-quality) and PQ (memory-efficient) indices.
  • GPU-accelerated search and compatibility with Python, NumPy arrays, and common ML pipelines.
  • Use cases include building large-scale recommender systems, semantic search over document collections, and offline vector indexing for retrieval-augmented generation.

Quick Start

Run a simple Python script to create an index, train if required, add vectors, and perform a k-NN search.

Frequently Asked Questions about faiss

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

FAQPage Schema
How do I perform scalable vector similarity search over billions of embeddings?▼

Scalable vector similarity search over billions of embeddings is enabled by configuring FAISS with approximate indices like IVF or memory-efficient PQ to retrieve nearest neighbors quickly without exhausting system resources.

What is the best way to build a high-performance nearest-neighbor index for large-scale ML pipelines?▼

Building a high-performance nearest-neighbor index for ML pipelines involves selecting the appropriate FAISS index type (Flat, IVF, HNSW, or PQ), training the index on your dataset, adding vectors, and querying via Python NumPy arrays.

Can I use GPU acceleration for vector search and k-NN queries?▼

GPU acceleration for vector search and k-NN queries is fully supported, allowing you to significantly speed up indexing and retrieval operations for large embedding datasets deployed in machine learning environments.

When should I choose approximate search over exact search for embedding retrieval?▼

You should choose approximate search (IVF, HNSW, PQ) over exact search (Flat) when querying massive datasets where memory efficiency and search latency are prioritized over perfect retrieval accuracy.

Do I need to train my FAISS index before adding vectors for semantic search?▼

Training your FAISS index before adding vectors is required for approximate indices like IVF or PQ to build their internal clustering structures, whereas exact Flat indices can ingest vectors directly without prior training.

Why does FAISS offer different index types like IVF and HNSW for vector search?▼

FAISS offers different index types like IVF and HNSW to balance trade-offs between search speed, memory usage, and recall quality, allowing configurations ranging from memory-efficient PQ to high-quality HNSW retrieval.

Related Skills

Explore More Data & Analytics Skills→
zechenzhangAGIzechenzhangAGI
11.5k

faiss

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

Community
Intermediate
AissenLiuAissenLiu

faiss

Perform vector similarity search across billions of vectors using FAISS index types.

Community
Advanced
nelohenriqnelohenriq
1

faiss

Build and query FAISS vector indexes for scalable similarity search.

Community
Advanced
zli5460zli5460
2

faiss

Create FAISS indexes and perform nearest neighbor searches on large vector datasets.

Community
Intermediate