To support complex RAG workloads at scale, an AI search platform must do far more than basic keyword or vector matching. Thanks to vespa.ai thenewstack.io/a-blueprint-fo…

We just did a podcast about the process of migration (trade-offs included) from #Elasticsearch to vespa.ai With Dainius Jocas and Kevin Petrie 🙌 em360tech.com/podcasts/vinte…

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

ACORN-1 and Adaptive Beam Search have been in vespa.ai for a while, but now we have a detailed post about how it works: blog.vespa.ai/additions-to-h…

Vector search alone isn’t enough. Production-grade AI search needs more: combining semantic, keyword and metadata retrieval, applying machine-learned ranking and handling constantly changing structured and unstructured data, all at scale. Thanks to vespa.ai

Built on Vespa.ai

Two great alternatives, both built on Vespa.ai

Filtered vector search is a massively important and overlooked problem for RAG and vector DBs. Very excited to see this new blog post from vespa.ai detailing its implementation of ACORN, along with many clever extensions to deliver huge speedups for search with filters.

If you want to create your own RAG application with this level of quality, clone the open source RAG Blueprint. github.com/vespa-engine/s…

This hack isn't for everyone, but in some situations it's possible and useful to turn off summary fetching.