Jose jsmsalt

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.

Install an Encrypted Arch Linux (LVM-LUKS) 🔒

As always and for everything, read the wiki.

Boot the live environment

Load keyboard layout (latin-america)

# loadkeys la-latin1

How to use Hexo and deploy to GitHub Pages

1. Install Hexo

$ sudo npm install -g hexo-cli

$ hexo -v
hexo-cli: 0.1.9

	#! /usr/bin/env python3

	#
	# GlSurface example code for VLC Python bindings
	# Copyright (C) 2020 Daniël van Adrichem <daniel5gh@spiet.nl>

	#
	# This program is free software; you can redistribute it and/or modify
	# it under the terms of the GNU General Public License as published by
	# the Free Software Foundation; either version 2 of the License, or

	# Copyright (C) 2020 Daniël van Adrichem <daniel5gh@spiet.nl>

	# This program is free software; you can redistribute it and/or modify
	# it under the terms of the GNU General Public License as published by
	# the Free Software Foundation; either version 2 of the License, or
	# (at your option) any later version.
	#
	# This program is distributed in the hope that it will be useful,
	# but WITHOUT ANY WARRANTY; without even the implied warranty of
	# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the


	const AWS = require('aws-sdk');

	//In the test file
	const mockDynamodbGetItem = jest.fn();
	const mockS3GetObject = jest.fn();

	//mock aws sdk
	jest.mock('aws-sdk', () => {
	return {

	TypeScript 21 hrs 47 mins ████████████████▒░░░ 67.1%
	Vue.js 6 hrs 21 mins ██████▓░░░░░░░░░░░░░ 19.6%
	JSON 2 hrs 10 mins ████▒░░░░░░░░░░░░░░░ 6.7%
	JavaScript 46 mins ███▒░░░░░░░░░░░░░░░░ 2.4%

	server {
	listen 80;

	server_name domain.com.br;

	location / {
	proxy_set_header X-Real-IP $remote_addr;
	proxy_set_header Host $host;
	proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
	proxy_pass http://127.0.0.1:8181;

	class _HomePageState extends State<HomePage> {
	final GlobalKey<ScaffoldState> _scaffoldKey = new GlobalKey<ScaffoldState>();

	@override
	Widget build(BuildContext context) {
	return new Scaffold(
	key: _scaffoldKey,
	appBar: new AppBar(
	title: new Text("App"),
	leading: new IconButton(

	#stop all containers:
	docker kill $(docker ps -q)

	#remove all containers
	docker rm $(docker ps -a -q)

	#remove all docker images
	docker rmi $(docker images -q)