Viewing profile — amallia

More on latency and search: We benchmark against 10 other search APIs on fresh news queries. The median was around 1.2s; we came in around 166ms and scored highest on answer accura…

Hi HN, Antonio here. Founder of Seltz. Seltz is a web search API built for AI agents. We wrote the crawler, the index, and the retrieval models ourselves, in Rust, by a team that's…

Paper can be found here: https://www.pinecone.io/research/unveiling-dime-reproducibil...

Multi-vector retrieval as a fast second-stage reranker to improve ranking quality without hurting latency

Thanks sota_pop. I am looking for contributors to help me integrate new features. Please come and join me!

Double-digit speed-ups over naïve K-Means Parallel by default (Rayon) Balanced & spherical variants in one crate Memory-savvy for multi-GB datasets Builder API that just feels ergo…

We built BMP, a fast and memory-efficient search engine for learned sparse retrieval — written in Rust and with Python bindings. It supports exhaustive (non-approximate) search ove…

Maxime Caron?

Yes, you can index any content as long as it is parsable. You can easily plug a new PDF parser and start indexing your PDF articles...

We rely on different user intents. Search for "PISA engine" or "PISA search" and you will find this tool and not the city. Being found by the keyword `PISA` on Google is not necess…

Thanks for the feedback!

Good to see you Marko!

Interesting! As long as there is no other OS software with the name PISA it should not be too confusing. Thanks for pointing out.

Not yet

Writing some documentation is definitely the first thing to get familiar with the code. Are you a C++ developer?