corpus.blog
41554 blogs · 4,417,066 posts Claim your blog
Record · corpus.blog/posts/01a07d5d-aa60-7171-bf9f-ded1976a8f40

Mixing numeric attributes into text search for better first-stage relevance

turbopuffer · published 27 April 2026

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at turbopuffer.com Wayback capture
1blogs citing
First cited
30 Apr 2026
Most recent
30 Apr 2026
Rank this month
not ranked
Links from this post
11
Words captured
1,851

Cited by

Blog
In the post
Date
emschwartz.me
Scour - April Update Read at the source ↗
30 Apr 2026

Links from this post

Link
Host
https://turbopuffer.com/docs/query
turbopuffer.com
Why BM25 queries with more terms can be faster (and other scaling surprises) Read at the source ↗
turbopuffer.com
https://en.wikipedia.org/wiki/PageRank
en.wikipedia.org
https://huggingface.co/datasets/Hellisotherpeople/enron_emails_parsed
huggingface.co
https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/craswell_sigir05.pdf
microsoft.com
https://en.wikipedia.org/wiki/Stephen_Robertson_(computer_scientist
en.wikipedia.org
https://en.wikipedia.org/wiki/Sigmoid_function
en.wikipedia.org
Vectorized MAXSCORE over WAND, especially for long LLM-generated queries Read at the source ↗
turbopuffer.com
FTS v2: up to 20x faster full-text search Read at the source ↗
turbopuffer.com
https://turbopuffer.com/docs/fts
turbopuffer.com
https://turbopuffer.com/join
turbopuffer.com