LynseDB is a vector database implemented purely in Python, designed to be lightweight, server-optional, and easy to deploy locally or remotely. It offers straightforward and clear Python APIs, aiming to lower the entry barrier for using vector databases.
It focuses on achieving 100% recall, prioritizing recall accuracy over high-speed search performance. This approach ensures that users can reliably retrieve all relevant vector data, making LynseDB particularly suitable for applications that require responses within hundreds of milliseconds.
⚡ Server-optional, simple parameters, simple API.
⚡ Fast, memory-efficient, easily scales to millions of vectors.
⚡ Based on a generic Python software stack, platform-independent, highly versatile.
⚡ Recall-prioritized design, lifecycle search caching technology, FieldExpression fast filtering, Field multi-type indexing, and other user-centric features
LynseDB is actively being updated, and API backward compatibility is not guaranteed. You should use version numbers as a strong constraint during deployment to avoid unnecessary feature conflicts and errors.
Although our goal is to enable brute force search or inverted indexing on billion-scale vectors, we currently still recommend using it on a scale of millions of vectors or less for the best experience.
The Python native API is recommended for use in single-process environments, whether single-threaded or multi-threaded; for ensuring process safety in multi-process environments, please use the HTTP API.
pip install LynseDB
You must first install Docker on the host machine.
After installing the Client API package:
docker pull birchkwok/lynsedb:latest