The article also provides a quick start guide for using Epsilla. Users can run the backend in Docker and interact with the Python client. The guide includes instructions on how to load and use a database, create a table with specific fields, insert records into the table, and query the table. The example provided demonstrates how to insert and query vector data related to different cities.
Key takeaways:
- Epsilla is an open-source vector database that focuses on scalability, high performance, and cost-effectiveness of vector search.
- It provides high performance and production-scale similarity search for embedding vectors and a full-fledged database management system with familiar database, table, and field concepts.
- Epsilla's core is written in C++ and uses advanced academic parallel graph traversal techniques for vector indexing, achieving 10 times faster vector search than HNSW while maintaining precision levels of over 99.9%.
- The platform provides native Python support and a REST API interface, and can be easily set up and interacted with using Docker and Python.