Samuel imolorhe

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.

Comprehensive Introduction to @ngrx/store

By: @BTroncone

Also check out my lesson @ngrx/store in 10 minutes on egghead.io!

Update: Non-middleware examples have been updated to ngrx/store v2. More coming soon!

Table of Contents

Service Worker - offline support for the web

Progressive apps - high-res icon, splash screen, no URL bar, etc.

Progressive Web Apps: Escaping Tabs Without Losing Our Soul

	import { BehaviorSubject, Observable } from 'rxjs';

	/**
	* Observes the specified property and returns a stream that emits all values which are assigned to the property. When subscribing to the
	* resulting stream it will always first emit the current value of the property, followed by all new values that are assigned to it.
	*
	* @param target Object containing the property.
	* @param key Key of the property that is to be observed.
	* @returns A stream of all values that are assigned to the specified property, starting with the current value of the property.
	*/

	const functions = require('firebase-functions');
	const gcs = require('@google-cloud/storage')();
	const sharp = require('sharp')
	const _ = require('lodash');
	const path = require('path');
	const os = require('os');

	exports.generateThumbnail = functions.storage.object('uploads/{imageId}').onChange(event => {

	const object = event.data; // The Storage object.


	import { Injectable } from '@angular/core';
	import { AngularFireDatabaseModule, AngularFireDatabase, FirebaseListObservable } from 'angularfire2/database';
	import { AngularFireAuth } from 'angularfire2/auth';
	import { Router } from "@angular/router";
	import * as firebase from 'firebase';


	@Injectable()
	export class AuthService {

	import { Pipe, PipeTransform } from '@angular/core';

	// Epochs
	const epochs: any = [
	['year', 31536000],
	['month', 2592000],
	['day', 86400],
	['hour', 3600],
	['minute', 60],
	['second', 1]

	:root {
	--ease-in-quad: cubic-bezier(.55, .085, .68, .53);
	--ease-in-cubic: cubic-bezier(.550, .055, .675, .19);
	--ease-in-quart: cubic-bezier(.895, .03, .685, .22);
	--ease-in-quint: cubic-bezier(.755, .05, .855, .06);
	--ease-in-expo: cubic-bezier(.95, .05, .795, .035);
	--ease-in-circ: cubic-bezier(.6, .04, .98, .335);

	--ease-out-quad: cubic-bezier(.25, .46, .45, .94);
	--ease-out-cubic: cubic-bezier(.215, .61, .355, 1);


	query IntrospectionQuery {
	__schema {
	queryType { name }
	mutationType { name }
	subscriptionType { name }
	types {
	...FullType
	}
	directives {

	<!DOCTYPE html>
	<html>
	<body>
	<p>The dog <span id="edit" contenteditable="true">sleeps on</span> the sofa</p>
	<script type="text/javascript">

	var handler = {
	onBackspace: function() {
	console.log("backspace");
	},