skills.rest
AlexiosBluffMara
AlexiosBluffMaraCOMMUNITY
Explore all skills by this author →
GitHub

faiss

Perform scalable vector similarity search with multiple index types and GPU acceleration.

2|Updated Apr 25, 2026
Search Tags:#large-scale#embedding#vector-search#gpu-acceleration#faiss#similarity-search#nearest-neighbors
One-click install
npx skills add https://github.com/AlexiosBluffMara/mercury --skill faiss-alexiosbluffmara
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: faiss
Source: https://github.com/AlexiosBluffMara/mercury/tree/main/optional-skills/mlops/faiss
Command: npx skills add https://github.com/AlexiosBluffMara/mercury --skill faiss-alexiosbluffmara

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

FAISS enables scalable, high-performance vector similarity search across large datasets by providing multiple index types and GPU acceleration.

Core Features & Use Cases

  • Supports multiple index types (Flat, IVF, HNSW, PQ) for exact and approximate search
  • GPU acceleration and CPU variants for flexible deployment
  • Use cases include embedding-based retrieval, nearest-neighbor search, and large-scale recommender systems

Quick Start

Use FAISS to build and query a vector index quickly on your embedding dataset.

Frequently Asked Questions about faiss

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

FAQPage Schema
How do I scale vector similarity search across billion-scale embedding datasets?▼

Vector similarity search scales to billion-scale datasets by using approximate index types like IVF, HNSW, and PQ, which partition embeddings to avoid exhaustive comparisons while maintaining high retrieval accuracy.

What's the best way to build a nearest-neighbor search index for large-scale recommender systems?▼

Building a nearest-neighbor search index for large-scale recommender systems is best handled by using an indexFactory, which provides an easy configuration string to assemble exact Flat or approximate indexes tailored to your embedding dataset.

Can I use GPU acceleration for embedding-based retrieval?▼

GPU acceleration is fully supported for embedding-based retrieval, offering GPU-accelerated index variants alongside standard CPU options to significantly speed up vector search queries across large datasets.

When should I use exact versus approximate vector search indexes?▼

Exact vector search using Flat indexes provides perfect accuracy but scans the entire dataset, whereas approximate search using IVF, HNSW, or PQ indexes trades slight accuracy for significantly faster querying on large-scale embeddings.

Do I need GPU hardware to run large-scale vector similarity search?▼

GPU hardware is not required to run large-scale vector similarity search, as flexible CPU variants are fully supported alongside GPU-accelerated options for deployment environments without specialized hardware.

Related Skills

Explore More Data & Analytics Skills→
qcmuuqcmuu

faiss

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

Community
Intermediate
justrachjustrach

emdb-search

Search EmergentDB for similar vectors and rank documents by similarity.

Community
Intermediate
nahtonajnahtonaj

agentdb-advanced-features

Synchronize distributed AgentDB nodes with QUIC-based cross-node updates.

Community
Advanced
ricablericable

faiss

Build fast nearest-neighbor search over dense vectors with FAISS indexes.

Community
Intermediate