xpost
InspectSearch and tagging on keep.md
Cloudflare Workers has Jev now so I'm putting it to the test on keep.md - 7x faster search rerank compared to the current hybrid - 50x faster tagging of content vs GLM 4.7 Flash with no failures
github·Research and data Featured Pick
typesafe-rag-router: Semantic Hybrid Search Gate
A sub-10ms decision layer that decides whether user queries need dense vector embeddings, BM25 exact match, or direct cache.
Open GitHub (typesafe-ai) ⚡ 9.4 ms routing · 80% embedding cost saved
TypeSafe Community
@typesafeai
Do not waste 200ms calculating 1536-dim vector embeddings on single-keyword lookups. Jev routes queries to BM25 vs Vector search in 9ms.
Which retrieval index is optimal for this query complexity?
Jev sits between the incoming context and the next system action. Rather than generating lengthy, slow natural language that requires brittle regex parsing, Jev returns non-autoregressive, calibrated probabilities that downstream code can immediately execute.
01retrieval_strategyPrimary action
02top_kConfidence score
03skip_rerankFallback route
Related Research and data Builds
xpost
InspectA visual reference finder
I built a visual reference finder with Jev One single prompt → 100 images from Cosmos, NASA, and The Met my new rabbit hole for creative work 🌻
xpost
InspectClassify rows in DuckDB
I made a DuckDB extension where you can use @typesafeai 's Jev to do quick classification of rows in any csv/parquet file or duckdb table about 10sec for 1k rows ~ better than using an LLM, way more ergonomic than a classifier game-changing for data analysis!