tinyvector
tinyvector is a minimal vector database / ANN engine focused on simplicity and compact implementation for educational and small-scale similarity search uses.
About this tool
tinyvector
Category: Vector Database Engines
Website/Source: https://github.com/0hq/tinyvector
Description
tinyvector is a minimal vector database / approximate nearest neighbor (ANN) engine built with SQLite and PyTorch. It is focused on simplicity and compact implementation for educational use and small-scale similarity search applications. The project is currently in pre-release and still under active development.
Features
- Minimal vector database / ANN engine
- Designed for educational and small-scale similarity search use cases
- Built on top of SQLite for storage
- Uses PyTorch in its implementation
- Provides a server that can be run manually
- Test suite available for validation and development
- Multi-language ecosystem:
- Python implementation:
tinyvector(this repository) - Rust implementation:
tinyvector-rs
- Python implementation:
Development status
- Pre-release, not yet production-ready
- Aiming for production readiness in a future release (timeline indicated as late July in the repository, subject to change)
Usage
Basic commands from the repository:
# Run the server manually
pip install -r requirements.txt
python -m server
# Run tests
pip install pytest pytest-mock
pytest
Pricing
- Open-source project (license present in repository).
No paid pricing plans are listed in the available content.
Loading more......
Information
Categories
Tags
Similar Products
6 result(s)Ruby gem for approximate nearest neighbor search that can integrate with pgvector and other backends to power vector similarity search in Ruby applications.
AiSAQ is an all-in-storage approximate nearest neighbor search system that uses product quantization to enable DRAM-free vector similarity search, serving as a specialized vector search/indexing approach for large-scale information retrieval.
This work by Jingfan Meng is a comprehensive research thesis on efficient locality-sensitive hashing (LSH), covering algorithmic solutions, core primitives, and applications for approximate nearest neighbor search. It is relevant to vector databases because LSH-based indexing is a foundational technique for scalable similarity search over high-dimensional vectors, informing the design of vector indexes, retrieval engines, and similarity search modules in modern vector database systems.
GTS is a GPU-based tree index for fast similarity search over high-dimensional vector data, providing an efficient ANN index structure that can be integrated into or used to build high-performance vector database systems.
iRangeGraph is an ANN indexing approach and accompanying implementation for range-filtering nearest neighbor search. It provides a specialized graph-based index that supports vector similarity search under range constraints, making it directly useful as a component or reference implementation for advanced vector database indexing and retrieval.
NSG is an approximate nearest neighbor search algorithm based on a sparse navigable graph structure designed for high-dimensional vector similarity search. The reference implementation provides a graph-based ANN index that can be integrated into custom vector retrieval systems.