Do you need a specialized vector database to implement vector search well?
Semantic search and augmenting LLMs have sent everyone turning their text into vectors. But where do you store all that vector data?


Stanimira Vlaeva, Benjamin Flast

Semantic search and augmenting LLMs have sent everyone turning their text into vectors. But where do you store all that vector data?
The benefits that come from serverless computing can be lost if you have to spend your time provisioning hardware for your database.
If you want a fast highway, you should have fewer cars.
We also cover the good kind of database fragmentation.
Databases today are built for Big Data. But what happens when the metadata is bigger?
How Aiven moved from storing metrics in one giant InfluxDB to using horizontally-scalable M3.