Skip to content

New Documentation Site!

We are excited to announce the launch of our enhanced product documentation site for KDB.AI at docs.kx.com. It offers improved search capabilities, organized navigation, and developer-focused content. Please, take a moment to explore the site and share your feedback with us.

KDB.AI Server FAQs

FAQs

Q: How do I access KX Support for KDB.AI Server?

A: Email Support on support@kdb.ai or join our Slack community.

Q: What kind of vector indexes are supported?

A: KDB.AI Server supports Flat, qFlat, IVF, IVFPQ, HSNW, and qHSNW indexes. Read about indexes and how to use indexes in KDB.AI.

Q: What kind of data types are supported?

A: KDB.AI supports the data types listed here.

Q: I've been testing out other platforms, can I migrate my data to KDB.AI?

A: Yes! You can transfer/migrate your data over to KDB.AI. Join our Slack channel or contact Support at support@kdb.ai for detailed instructions on how to do this.

Known Issues

Issues during index training

For CPU instructions on AMD machines we require setting the additional environment variable OPENBLAS_CORETYPE=HASWELL in order to access the full similarity search functionality.