Powering your Copilot for Data – with Artem Keydunov of Cube.dev
The ideal solution for AI-native vectorDB would be something that would would be easy to set up and should integrate with existing APIs for rapid prototyping but should be able to scale without additional changes.
LanceDB is designed with this approach. Being server-less, it requires no setup — just import and start using. Persisted in HDD, allowing... See more
LanceDB is designed with this approach. Being server-less, it requires no setup — just import and start using. Persisted in HDD, allowing... See more
Ayush Chaurasia • LLMs, RAG, & the missing storage layer for AI
I went to a ClickHouse meetup here in Dubai.
Never used the tool, but I'm happy to learn.
ClickHouse is:
- a database
- built for analytics
- open source
Furthermore, it:
- can be run on a single node or in a cluster
- stores data in columnar format
- uses both "vectorized query execution" and "runtime code generation" to maximize CPU usage
In the meetup, Cl... See more
Never used the tool, but I'm happy to learn.
ClickHouse is:
- a database
- built for analytics
- open source
Furthermore, it:
- can be run on a single node or in a cluster
- stores data in columnar format
- uses both "vectorized query execution" and "runtime code generation" to maximize CPU usage
In the meetup, Cl... See more
Feed | LinkedIn
The last core data stack tool is the orchestrator. It’s used quickly as a data orchestrator to model dependencies between tasks in complex heterogeneous cloud environments end-to-end. It is integrated with above-mentioned open data stack tools. They are especially effective if you have some glue code that needs to be run on a certain cadence, trigg... See more