Voyager
Voyager is a Spotify open-source vector search library and service for efficient nearest neighbor search on large-scale vector datasets.
About this tool
Voyager
Brand: Spotify
Category: SDKs & Libraries
Website: https://github.com/spotify/voyager
License: Apache-2.0
Type: Open-source approximate nearest-neighbor (ANN) search library and service
Overview
Voyager is an open-source vector search library for Python and Java, designed for efficient approximate nearest-neighbor search on large-scale vector datasets. It focuses on ease of use, simplicity, and deployability, and can be used both as an embedded library and as a service.
Features
- Approximate nearest-neighbor search for high-dimensional vectors.
- Large-scale vector dataset support, suitable for production-scale search workloads.
- Multi-language support:
- Python bindings
- Java bindings
- Core C++ implementation (in
cppdirectory)
- Library and service modes:
- Usable as a library within Python/Java applications
- Can be deployed as a standalone service for vector search
- Performance and benchmarking:
- Dedicated
benchmarksdirectory for performance tests and comparisons - Designed for efficient query performance on large indexes
- Dedicated
- Documentation:
docsdirectory with project documentation and usage guidance
- Project governance and contribution:
CODE_OF_CONDUCT.mddefining contributor behaviorCONTRIBUTING.mdwith contribution guidelinesOWNERS.mddocumenting project ownership/maintainers
- Configuration and tooling:
- C++ formatting via
.clang-format - Git submodules defined in
.gitmodules
- C++ formatting via
(Note: The GitHub page content snippet does not list detailed APIs or algorithms; those would be found in the repository’s README and docs.)
Technology Stack
- Core: C++
- Language bindings: Python, Java
- Repository structure:
cpp/,python/,java/,benchmarks/,docs/
Pricing
- Open Source – Free to use under the Apache-2.0 license.
- No commercial pricing plans are listed in the provided content.
Loading more......
Information
Categories
Tags
Similar Products
6 result(s)An open-source library for approximate nearest neighbor search in high-dimensional spaces, often used as a backend for vector databases and search engines.
HNSWLIB is a C++ library with Python bindings for fast approximate nearest neighbor search using Hierarchical Navigable Small World (HNSW) graphs, commonly used in vector database backends.
A library by Google Research for efficient vector similarity search, suitable for large-scale nearest neighbor applications in AI.
KGraph is an open-source library for fast approximate nearest neighbor search in high-dimensional vector spaces, applicable to vector database solutions.
MRPT (Multi-Resolution Proximity Trees) is an open-source library for fast approximate nearest neighbor search in high-dimensional vector spaces, applicable to vector database backends.
NGT (Neighborhood Graph and Tree) is an open-source vector search engine designed for fast and scalable approximate nearest neighbor search.