# Faiss

> A library for efficient similarity search and clustering of dense vectors

- **Canonical URI:** https://www.vioscale.ai/software/faiss
- **Category:** Vector Databases
- **Homepage:** https://faiss.ai
- **Also known as:** faiss
- **Profile claimed by vendor:** no
- **Last updated:** 2026-08-03T13:14:40.710Z

## Vioscale score

**50 / 100**, confidence 3% (low).

Composite of weighted, independently-sourced signals (no user reviews, no vendor payment).

| Signal | Score | Weight | Contribution | Evidence present |
|---|--:|--:|--:|:--:|
| price_level | 0 | 6 | 0 | - |
| reliability | 50 | 10 | 500 | ✓ |
| capabilities | 0 | 17 | 0 | - |
| integrations | 0 | 8 | 0 | - |
| security_posture | 0 | 18 | 0 | - |
| pricing_transparency | 0 | 8 | 0 | - |

## About

Faiss is a library for efficient similarity search and clustering of dense vectors. It contains algorithms that search in sets of vectors of any size, up to ones that possibly do not fit in RAM.

_Independently observed._

## Platform & deployment

- **Platforms:** macOS, Linux, Windows
- **Deployment:** Self-hosted

## Capabilities

_The capabilities that matter for Vector Databases. "-" = undocumented, not absent._

| Capability | Supported |
|---|:--:|
| **Deployment** | |
| Deployment | Embedded |
| **Index** | |
| ANN index (HNSW / IVF / DiskANN / ScaNN / flat) | - |
| Distance metrics (cosine / dot / Euclidean) | Euclidean, dot product, L1, Linf |
| **Query** | |
| Metadata filtering | - |
| Hybrid search (dense + sparse fusion) | - |
| Built-in BM25 / lexical | - |
| **Storage** | |
| Quantization | - |
| **Scale** | |
| Multi-tenancy (namespaces / collections / tenants) | - |
| Horizontal scale | Single-node |
| **Consistency** | |
| Consistency | - |
| **Deployment** | |
| Serverless / consumption pricing | ✗ |
| **Storage** | |
| On-disk vs in-memory | Disk-backed |
| **Licensing** | |
| Licence class | - |
| **Classification** | |
| Purpose-built vs feature-of-parent | Extension |

## Facts

Every value below carries its source and our confidence. Facts are re-crawled on a freshness schedule.

### pricing

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| pricing.model | commercial | [link](https://faiss.ai) | 2026-08-03 | 60% (medium) |

### reliability

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| reliability.status_page | yes | [link](https://faiss.ai/status) | 2026-08-03 | 60% (medium) |

---
*Source: Vioscale (https://www.vioscale.ai/software/faiss). Independent, evidence-based software intelligence. Cite the canonical URI.*