billyct billyct

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.

Monaco Editor and Snowpack Example

Use Snowpack to extract and build JavaScript Modules and run in the browser.

Installation

Download and unzip this gist
npm install
npm run snowpack # optional, should run by default during npm install
npm run serve

About

Theming Ant Design with Sass and Webpack

This is a solution on how to theme/customize Ant Design (which is written in Less) with Sass and webpack. Ant itself offers two solutions and a related article on theming, but these are only applicable if you use Less, the antd-init boilerplate or dva-cli.

What this solution offers:

use a single sass-file to customize (no duplicate variables for your project and Ant)
hot reload compatibility
no dependencies on outdated npm modules
easy integration with your existing webpack setup (webpack 3+ tested)

Semantic Commit Messages

See how a minor change to your commit message style can make you a better programmer.

Format: <type>(<scope>): <subject>

<scope> is optional

Example

Requirements

Minikube requires that VT-x/AMD-v virtualization is enabled in BIOS. To check that this is enabled on OSX / macOS run:

sysctl -a | grep machdep.cpu.features | grep VMX

If there's output, you're good!

	(function (context, trackingId, options) {
	const history = context.history;
	const doc = document;
	const nav = navigator \|\| {};
	const storage = localStorage;
	const encode = encodeURIComponent;
	const pushState = history.pushState;
	const typeException = 'exception';
	const generateId = () => Math.random().toString(36);
	const getId = () => {

	export function magicMethods (clazz) {
	// A toggle switch for the __isset method
	// Needed to control "prop in instance" inside of getters
	let issetEnabled = true

	const classHandler = Object.create(null)

	// Trap for class instantiation
	classHandler.construct = (target, args, receiver) => {
	// Wrapped class instance

	// CSVToMap takes a reader and returns an array of dictionaries, using the header row as the keys
	func CSVToMap(reader io.Reader) []map[string]string {
	r := csv.NewReader(reader)
	rows := []map[string]string{}
	var header []string
	for {
	record, err := r.Read()
	if err == io.EOF {
	break
	}

	// 🔥 Node 7.6 has async/await! Here is a quick run down on how async/await works

	const axios = require('axios'); // promised based requests - like fetch()

	function getCoffee() {
	return new Promise(resolve => {
	setTimeout(() => resolve('☕'), 2000); // it takes 2 seconds to make coffee
	});
	}