Machine Learning

1 readers

1 users here now

Community Rules:

Be nice. No offensive behavior, insults or attacks: we encourage a diverse community in which members feel safe and have a voice.
Make your post clear and comprehensive: posts that lack insight or effort will be removed. (ex: questions which are easily googled)
Beginner or career related questions go elsewhere. This community is focused in discussion of research and new projects that advance the state-of-the-art.
Limit self-promotion. Comments and posts should be first and foremost about topics of interest to ML observers and practitioners. Limited self-promotion is tolerated, but the sub is not here as merely a source for free advertisement. Such posts will be removed at the discretion of the mods.

founded 10 months ago

MODERATORS

communick@academy.garden

[P] Epsilla: a scalable, fully distributed vector database (alien.top)

submitted 10 months ago by songrenchu@alien.top to c/machinelearning@academy.garden

3 comments fedilink hide all child comments

Hi everyone!

Three months ago we launched Epsilla open source vector database. Since then we have been iterating. Today I'm excited to share the first production oriented launch: Epsilla v0.1 -- a scalable, fully distributed vector database.

The launch focuses scalability and reliability, including sharding vector data for efficient horizontal scaling; Multi-replica configuration for high availability and increased throughput; Dynamic sharding expansion and auto-scaling replicas to meet data growth and traffic demands.

We wanted to get your feedback and work together to shape our vector database features. Let us know what you think and what you'd like to see!

Article: https://blog.epsilla.com/epsilla-v0-1-a-leap-forward-in-distributed-vector-database-technology-b511bb21b603

Github: https://github.com/epsilla-cloud/vectordb

you are viewing a single comment's thread
view the rest of the comments

[–] blackkettle@alien.top 1 points 10 months ago

Why should I use this instead of opensearch or Postgres?

Being faster/more efficient today isn’t enough to put me off the plugins for these two well known workhorses which bake in years or decades of industry use as well as in cloud and onsite feature parity.

I don’t want to be too harsh but it looks like you’re rebuilding basic DB features whereas Postgres is just finetuning a plug-in.