faiss ☆
« Back to VersTracker
Description:
Efficient similarity search and clustering of dense vectors
Type: Formula  |  Latest Version: 1.13.1@0  |  Tracked Since: Dec 17, 2025
Links: Homepage  |  formulae.brew.sh
Category: Ai ml
Tags: machine-learning vector-search clustering gpu c++
Install: brew install faiss
About:
Faiss is a library for efficient similarity search and clustering of dense vectors. It contains algorithms for searching in sets of vectors of any size, as well as support for optional indexes and GPU acceleration. It is particularly effective for finding nearest neighbors in high-dimensional spaces, which is a core operation in many machine learning applications.
Key Features:
  • Supports exact and approximate nearest neighbor search
  • Efficient implementation of indexing structures like IVF and HNSW
  • Full GPU acceleration for significant performance gains
  • Python and C++ APIs for flexible integration
Use Cases:
  • Recommendation systems for finding similar items
  • Image and audio retrieval based on feature embeddings
  • Large-scale document clustering and semantic search
Alternatives:
  • Annoy – Annoy is a C++ library with Python bindings focused on approximate nearest neighbors, often used for smaller-scale applications.
  • ScaNN – ScaNN (Scalable Nearest Neighbors) is a TensorFlow-based library optimized for performance on modern accelerators and large datasets.
Version History
Detected Version Rev Change Commit
Dec 3, 2025 2:35am 0 VERSION_BUMP 42ba0d9a
Sep 12, 2025 6:11am 0 VERSION_BUMP 1f902b0a
Oct 4, 2024 10:21pm 0 VERSION_BUMP 0c1c01df
Oct 4, 2024 9:33pm 0 VERSION_BUMP 552073a5
Sep 13, 2024 4:01am 0 VERSION_BUMP 7325a79d
« Back to VersTracker  |  Browse Packages  |  About