Skip to content
View laputski's full-sized avatar
13 followers · 15 following

Block or report laputski

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
laputski/README.md

Alexander Laputski

I build the instruments AI systems are missing.

RAG World — a self-updating registry of retrieval-augmented generation technologies. Every maturity level is derived from collected evidence by a deterministic rule. No language model takes part, so the same evidence always yields the same level. Open data, CC BY 4.0, DOI 10.5281/zenodo.21943978.

Causa RAG — a diagnostic bench. It scores every question in a golden set separately, names the pipeline stage that failed, and compares two runs question by question, so the blast radius of a change is visible instead of assumed. Nothing leaves the machine it runs on. Citable at DOI 10.5281/zenodo.22117626.

Writing at laputski.ai.

Open to architecture work on retrieval and AI systems: LinkedIn · laputski@gmail.com

Pinned Loading

  1. rag-world rag-world Public

    A self-updating registry of retrieval-augmented generation technologies.

    Python

  2. causa-rag causa-rag Public

    A diagnostic bench for RAG. Scores every question separately, names the pipeline stage that failed, and diffs two runs question by question. Runs entirely on your own machine.

    Python 1

  3. book-python book-python Public

    Advanced Python Tutorial for RAG

    HTML

  4. book-fde book-fde Public

    Forward Deployed Engineering textbook

    HTML