june changelog turbopuffer.com/docs/roadmap

new GCP regions. now puffin' in Toronto and Singapore turbopuffer.com/docs/regions

"turbopuffer makes it too easy to build state-of-the-art AI apps" – Notion turbopuffer.com/customers/noti…

by popular demand, now introducing one-dimensional vectors 🎈

our ruby client just dropped 💎

ripgrep on object storage?

july changelog turbopuffer.com/changelog

new: native facet support with group_by

"Having our data in turbopuffer makes us feel ready for whatever comes next in AI-enabled software. It gives us the confidence to adapt quickly." — Tristan Homsi, co-founder of Readwise turbopuffer.com/customers/read…

august changelog turbopuffer.com/docs/roadmap

it was driving us mad that a 96 core box could only drive 13 Gbps from S3 turns out eBPF probes from our network monitoring imposed more overhead than anyone expected 5-10x improvement in network throughput → faster puffin'

tpuf ANN v3 can search 100 billion vectors with a p99 of 200ms simplicity scales [v3 in beta, unfiltered search, 1024D, k=10, 92% recall]

september changelog turbopuffer.com/docs/roadmap

new: rank by filter! boost scores when docs match a condition (e.g. scale > 1pib). plugs straight into rank_by, and works alongside full-text search