Alberto Miorin amiorin

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.

node-websocketd

A lightweight node port of websocketd, originally written in go.

Usage

node-websocketd --port=8080 ./count.sh

Clustering: The basics

The trick? pass the file descriptor from a parent process and have the server.listen reuse that descriptor. So multiprocess in their own memory space (but with ENV shared usually)

It does not balance, it leaves it to the kernel.

In the last nodejs > 0.8 there is a cluster module (functional although marked experimental)

http://nodejs.org/api/cluster.html
Simple cluster example:

The apps.berlin.js meetup

apps.berlin.js is a Berlin.js spin-off with a special focus on JavaScript-driven web applications (“HTML5 apps”), desktop browser apps as well as mobile apps and games written in JavaScript. Here you can find the slides and additional links of all past talks. Please fork this Gist to add more info!

First meetup on May 10th 2012

Application frameworks on top of Backbone.js
by Mathias Schäfer
Slides
Chaplin.js on Github

	import os

	import arel
	from fastapi import FastAPI, Request
	from fastapi.templating import Jinja2Templates

	app = FastAPI()
	templates = Jinja2Templates("templates")

	if _debug := os.getenv("DEBUG"):

	##### ##### ##### ##### ##### ##### ##### ##### ##### ##### ##### ##### ##### ##### ##### ##### #####

	### Shell script to download Oracle JDK / JRE / Java binaries from Oracle website using terminal / command / shell prompt using wget.
	### You can download all the binaries one-shot by just giving the BASE_URL.
	### Script might be useful if you need Oracle JDK on Amazon EC2 env.
	### Script is updated for every JDK release.

	### Features:-
	# 1. Resumes a broken / interrupted [previous] download, if any.
	# 2. Renames the file to a proper name with including platform info.

	window.fluid.dockBadge = '';
	setTimeout(updateDockBadge, 1000);
	setTimeout(updateDockBadge, 3000);
	setInterval(updateDockBadge, 5000);

	function updateDockBadge() {

	var navigation = document.querySelector('[role=navigation]')
	var doc = navigation.contentDocument \|\| navigation.ownerDocument;

	$VERBOSE = nil
	require File.expand_path('../rooby', __FILE__)


	Person = Rooby::Class.new 'Person' do
	define :initialize do \|name\|
	@name = name
	end

	define :name do

	;; http://lispyscript.com
	;; LispyScript sequenced callback example
	;; No need for nested callbacks. Just write your callbacks in a sequence and pass "(next)" as
	;; your callback, which will set the next function in the sequence as your callback.
	;;
	;; This example is a simple node server that will serve static plain text file to the browser.
	;;

	(var fs (require "fs"))
	(var http (require "http"))

	apply plugin: "java"
	apply plugin: "eclipse"
	apply plugin: "idea"

	group = "com.mycompany.hadoopproject"
	version = "1.0"

	repositories {
	// Standard Maven
	mavenCentral()