turbopuffer introduces a Fuzzy filter for typo-tolerant search
It allows substring matching with configurable edit distance, enabling accurate searches despite misspellings.
See the latest news and media coverage for turbopuffer. We track all announcements, press releases, and industry mentions in real time, all in one place.
Vector and full-text search database built on object storage
turbopuffer.comLast updated
In short: turbopuffer secured fresh financing and introduced technical updates to its object-storage-native search architecture to improve cost and latency.
It allows substring matching with configurable edit distance, enabling accurate searches despite misspellings.
This allows blending date and numeric values with BM25 scoring using sigmoid functions, improving recall without overfetching.
The search engine uses object storage with SSD caching for 100x cheaper cold storage and 10ms warm latency.
New block-based inverted indexes achieve up to 10x size reduction, improving query performance and compression efficiency.
Plus: Cohere exec pledges AI firm will stay Canadian. Former Shopify engineer Simon Hørup Eskildsen really hopes he isn’t leading Canada’s fastest-growing tech company. The...
Ottawa startup secures funding from Lachy Groom and Joshua Kushner’s Thrive Capital. On the back of a big 2025, Ottawa technology startup Turbopuffer has secured...
Use the Turbopuffer MCP Server to enable AI assistants to interact with this API, allowing them to explore endpoints, make test requests, and use documentation...
Simon Holp Eskildsen, developer of the fast search engine service for object storage 'turbopuffer,' posted a blog about how he made it possible to search...
Track turbopuffer and your other target companies to get real-time alerts and weekly summaries delivered straight to your inbox.
Browse news for competitors to turbopuffer and other trending companies.