Johannes Daxböck dingsdax

Ruby NLP resources

ruby stemmer (expose libstemmer_c to Ruby)
stuff classifier (text classifier; naive bayes & tf/idf)
ve linguistic framework (base form of words, sentence detection, POS, tranliterations, 日本語, english, mecab, freeling)
ruby nlp (n-grams extraction, corpus extractor, brown corpus)
lexeme ( simple lexical analyzer)

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

	require "bundler/inline"

	# allows for declaring a Gemfile inline in a ruby script
	# optionally installing any gems that aren't already installed
	gemfile(true) do
	source "https://rubygems.org"

	gem "rails", "6.1.4.1"
	gem "sqlite3"
	gem "graphql", "~> 1.12"

	# Ruby archeology: sources:
	# https://web.archive.org/web/20070226052918/http://codezine.jp/a/article.aspx?aid=461
	# https://web.archive.org/web/20061216170428/http://www.okisoft.co.jp/esc/prolog/in-ruby.html

	# Ruby による簡単な Prolog 処理系 h18.9/8 (鈴)
	# Simple Prolog processing system using Ruby h18.9/8 (Rin)

	# Prolog の述語 (predicate)
	class Pred
	attr_reader :defs

	RACC := racc
	RACCFLAGS := -g

	SOURCES := prolog_parser.ry
	TARGETS := ${patsubst %.ry, %.rb, ${SOURCES}}


	.SUFFIXES : .rb .ry

	%.rb : %.ry

	#!/usr/bin/env ruby
	# frozen_string_literal: true

	# Sentry Queue Time Test Generator
	#
	# USAGE:
	# export SENTRY_DSN='https://your-key@o123.ingest.us.sentry.io/456'
	# export SENTRY_SKIP_SSL_VERIFY=true # if you get SSL errors
	# ruby sentry_queue_test.rb [duration_minutes] [requests_per_minute] [pattern]
	#