xtdb

Chris Chen 2025-12-08T13:41:03.936379Z

Anyone have experience implementing vector similarity search in v1 (either via Lucene or hnswlib)? Is there a recommended way to handle this?

refset 2025-12-08T19:21:25.976059Z

I know @felix hacked on such a thing at one point but I'm not sure if the code is available somewhere

alenk 2025-12-08T19:54:33.460419Z

I’d be interested to know the same answer for v2, or is that no longer possible with the new architecture?

xlfe 2025-12-08T21:29:25.525379Z

It's true - but not open source sorry. We used NGT and fast-text via Coffi, and registered a secondary index in XT

😮 1
šŸ™ 1