faiss

Name: faiss
Availability: InStock
Author: nelohenriq

Build and query FAISS vector indexes for scalable similarity search.

1|Updated Mar 22, 2026

Search Tags:#indexing #gpu #similarity #vector-search #machine-learning #faiss

Ready to run

npx skills add https://github.com/nelohenriq/hermes-agent-plus --skill faiss-nelohenriq

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: faiss
Source: https://github.com/nelohenriq/hermes-agent-plus/tree/main/skills/mlops/vector-databases/faiss
Command: npx skills add https://github.com/nelohenriq/hermes-agent-plus --skill faiss-nelohenriq

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

FAISS enables fast and scalable vector similarity search and retrieval across large datasets.

Core Features & Use Cases

Multiple index types: Flat, IVF, HNSW, and PQ for varying trade-offs between speed, memory, and accuracy.
GPU acceleration: Leverage GPUs for large-scale vector search workloads.
Python bindings and ecosystem: Integrates with common ML tooling and libraries for seamless experimentation.

Quick Start

Index a sample dataset and perform a k-nearest neighbors search to retrieve the top matches.

Frequently Asked Questions about faiss

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

FAQPage Schema

How do I build a high-dimensional vector store for similarity search at scale?▼

To build a high-dimensional vector store for similarity search at scale, you can index datasets ranging from thousands to billions of vectors using multiple index types like Flat, IVF, HNSW, and PQ for varying speed and accuracy trade-offs.

What is the best way to perform nearest-neighbor retrieval on a large dataset?▼

Performing nearest-neighbor retrieval on large datasets is best handled by querying a scalable vector index, allowing you to execute k-nearest neighbors searches to retrieve the top matching vectors efficiently.

Can I use GPU acceleration for machine learning vector search workloads?▼

Yes, you can leverage GPU acceleration for machine learning vector search workloads to handle large-scale retrieval tasks, provided you have the appropriate GPU environment setup for high-speed processing.

Do I need numpy to run semantic search indexing with Python bindings?▼

Yes, you need numpy along with either faiss-cpu or faiss-gpu installations to run semantic search indexing, as the Python bindings integrate with common machine learning tooling for vector manipulation.

When should I use different index types like IVF, HNSW, or PQ for vector retrieval?▼

You should use different index types like IVF, HNSW, or PQ for vector retrieval when you need specific trade-offs between search speed, memory usage, and accuracy across datasets ranging from thousands to billions of vectors.