arroy
Arroy is an open-source library for efficient similarity search and management of vector embeddings, useful in vector database systems.
About this tool
arroy
Source: https://github.com/meilisearch/arroy
Category: open-sources
Tags: open-source, vector-embeddings, similarity-search, vector-search
Description
Arroy is an open-source Rust library for efficient similarity search and management of vector embeddings, designed for use in vector database systems. It provides an interface similar to the Annoy Python library and is optimized for memory usage by leveraging LMDB as its backend storage. This allows multiple processes to share and atomically modify the same data.
Features
- Approximate Nearest Neighbor (ANN) Search: Efficiently finds vectors in high-dimensional space that are close to a target vector.
- Rust Library: Written in Rust for performance and safety.
- LMDB Backend: Utilizes LMDB, a memory-mapped key-value store, allowing concurrent access and modification from multiple processes.
- Low Memory Footprint: Designed to handle millions of high-dimensional vectors efficiently.
- Inspired by Annoy: Offers a similar API and benefits from low memory usage, with the added advantage of persistent storage.
- Multi-threaded Access: The index can be queried by multiple threads or processes simultaneously.
- Configurable Parameters:
n_trees: Number of trees used in the index (affects memory and accuracy).search_k: Number of nodes to inspect during a search (affects speed and recall).- If
search_kis not provided, it defaults ton * n_treeswherenis the number of neighbors to search for.
- Random Projections: Uses random projection trees for splitting the vector space.
- Support for High Dimensionality: Handles vectors with large dimensions (e.g., 768 or 1536).
- Atomic Modifications: Safe concurrent updates to the vector index.
- Open Source: MIT licensed and available on GitHub and crates.io.
Pricing
Arroy is open-source software, free to use under the MIT license.
Links
Loading more......
Information
Categories
Similar Products
6 result(s)KGraph is an open-source library for fast approximate nearest neighbor search in high-dimensional vector spaces, applicable to vector database solutions.
Puck is an open-source vector search engine designed for fast similarity search and retrieval of embedding vectors.
PostgreSQL supports vector indexing and similarity search via the PGVector extension, allowing relational databases to manage and retrieve vector embeddings efficiently.
Qdrant is a dedicated vector database and similarity search engine supporting advanced filtering and efficient retrieval, suitable for faceted search and retrieval-augmented generation. It offers self-hosted and cloud deployment options, making it highly relevant for vector search applications.
RediSearch is a Redis module that provides high-performance vector search and similarity search capabilities on top of Redis, enabling advanced search and retrieval features for AI and data applications.
Bleve is an open-source search library with experimental support for vector search, enabling hybrid search and retrieval in applications.