You can also read a full explanation of what these parameters do here:

We'll soon update defaults to give everybody improved performance with no effort, but to really get the best performance you should tune to your case. We have made a guide for that:

Join millions who have switched to Grok.

To optimize all parts of the filter space (make all queries efficient), you need to combine different strategies

We have introduced new tuning parameters in Vespa that lets you improve recall and cost, inspired by Acorn and beam search papers. They *really* help.

What you need to test is performance AND recall at various filter strengts. The challenging area is around 80-99% filter strength, and the devil has made it so that this is where most real-world applications live.

In real vector search systems, performance is dominated by combining it efficiently with filters. Few test this properly. 🧵

ACORN-1 and Adaptive Beam Search have been in @vespaengine for a while, but now we have a detailed post about how it works: https://t.co/gUF9vh330j

We made a new video to explain the point of Vespa's architecture

https://t.co/SXQyehPcyy

We just added a guide to creating, embedding, retrieving, ranking and selecting chunks. Probably contains some things you didn't know.

We just did a podcast about the process of migration (trade-offs included) from #Elasticsearch to @vespaengine With @dainius_jocas and @KevinPetrieTech 🙌 https://t.co/BtCGVyzP2U

To support complex RAG workloads at scale, an AI search platform must do far more than basic keyword or vector matching. Thanks to @vespaengine

Using Python and want to get started with Vespa? We just added this simple step by step guide:

Thanks to the @vespaengine team for featuring my guest post! 🙌🏻 At @searchplex, we've doubled down on our Vespa focus: expanding our expertise and services from PoC to migrations to production-grade Al search and recommendation systems. Check out the blog post to learn more.

People are coming up with so many great uses for layered ranking. Nice to see innovation driven by scaled RAG apps benefiting all kinds of use cases.

Announcing: The RAG Blueprint Build RAG like the world's most successful applications. Start from our open source sample app which contains all you need to do to achieve world-class quality at any scale. Sample app: https://t.co/LBR2Uuf7Sl Blog post:

Read it here and judge for yourself:

New Vespa features covered in the June newsletter: - Layered ranking: Rank chunks in documents. - Elementwise bm25 - top, filter_subspaces, and cell_order tensor functions - chunking support in indexing - element-gap: Proximity over chunks - filtering in grouping results -

Read the full announcement blog here:

With layered ranking, you can use Vespa's powerful ranking machinery both to select documents and then to select the right chunks within them.