We didn’t include pgvector because we focused on managed services to keep things comparable — TopK is managed/serverless, so the fair match would be a managed Postgres. And pgvector just doesn’t really scale to the kinds of workloads we ran here.
Hi, I'm Jergus, one of the founders of TopK. We cannot share the results publicly but happy to share privately (@jerguslejko on twitter, or [email protected])
We're actually not allowed to post head to head comparison with competitors and share their names, that's why :) Post contains the dataset, the tool and methodology how the data was collected, which hopefully gives confidence in fairness of the benchmark.
not rude at all, it's a common sentiment. TopK gives you all the capabilities under one roof -- text, vectors, filters, embeddings, re-ranking, all behind a single API (so single SDK, single vendor, single bill, single observability plane, etc). This simplifies your integration (less code on your part) and gives you more flexibility to define custom scoring rules (elastic-style) but over text + vectors + any other pre-computed factors. Take a look at [this](https://docs.topk.io/concepts/unified-retrieval#custom-scori...) docs page which goes into detail if you are interested.
I'd be curious to learn about your setup though. Vespa comes with lexical search so what made you choose this combo? Was Elastic already present in your stack before adopting Vespa?