Evaluate Vector Database / Benchmarks?

• ann-benchmarks

  51 4,604 7.7 Python

  Benchmarks of approximate nearest neighbor libraries in Python

By far the most popular benchmark is ANN Benchmark. It evaluates both scientific libraries and vector databases. It can give you a starting point and filter out some clearly unsuitable options, e.g. pgvector. Note that this benchmark is quite harsh and has strong assumptions, e.g. caring only about QPS (Queries Per Second) vs recall, having enough RAM for everything, or using only a single node.

• vector-db-benchmark

  6 227 9.1 Python

  Framework for benchmarking vector search engines

  

Qdrant made their own benchmark. It is quite simple and also takes into consideration more options, so it should be better suited for benchmarking for production purposes.

• InfluxDB

  www.influxdata.com featured

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

• vector-search

  7 245 3.2 Jupyter Notebook

  The definitive guide to using Vector Search to solve your semantic search production workload needs.

i started doing this at http://vectorsearch.dev but it could use some love.

Suggest a related project