Jeronimo Avelar Filho jeroavf

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.

How to install Ubuntu 14.04.05 on Alienware 15 R3

Tiny guide to install Ubuntu 14.04.05 on a brand new Alienware 15 R3.

Let windows 10 install

Just next, next, next filling up your data.

You should get a BIOS update alert from the Alienware Update widget. If not, right click on the Down arrow icon in the bottom right extra icons ^ thing and right click, then click Check for Updates.

Procedures used to configure a new fresh installed Ubuntu 16.04.5 LTS with support for OpenCV4 + Python 3.6 + Nvidia GTX 1060 + Tensorflow + Keras.

Installing GPU drivers

Open the link https://www.geforce.com/drivers and under the Manual Driver Search select the appropriated values, make sure to select Recommended/Certified option, and click search.

Search for the latest version in the list. While writing this gist the latest version was 410.78.

Definitely not comprehensive. This is meant to be a basic memory aid with links to get more details. I'll add to it over time.

Install

$ npm install mongoose --save

Connect

const mongoose = require('mongoose');

Resize a Hard Disk for a Virtual Machine

Our Virtual Machines are provisioned using Vagrant from a Linux base box to run using VirutalBox. If the Hard Disk space runs out and you cannot remove files to free-up space, you can resize the Hard Disk using some VirtualBox and Linux commands.

Some assumptions

The following steps assume you've got a set-up like mine, where:

	minikube stop; minikube delete &&
	docker stop $(docker ps -aq) &&
	rm -rf ~/.kube ~/.minikube &&
	sudo rm -rf /usr/local/bin/localkube /usr/local/bin/minikube &&
	launchctl stop 'kubelet.mount' &&
	launchctl stop localkube.service &&
	launchctl disable localkube.service &&
	sudo rm -rf /etc/kubernetes/ &&
	docker system prune -af --volumes

	class MyStreamListener(tweepy.StreamListener):
	def __init__(self, api=None):
	super(MyStreamListener, self).__init__()
	self.num_tweets = 0
	self.file = open("tweets.txt", "w")

	def on_status(self, status):
	tweet = status._json
	self.file.write( json.dumps(tweet) + '\n' )
	self.num_tweets += 1

	sudo apt-get install -y supervisor

	sudo mkdir /usr/share/elasticsearch
	cd /usr/share/elasticsearch

	sudo wget https://download.elasticsearch.org/kibana/kibana/kibana-4.0.1-linux-x64.tar.gz
	sudo wget https://download.elasticsearch.org/elasticsearch/elasticsearch/elasticsearch-1.4.4.tar.gz
	sudo wget https://download.elasticsearch.org/logstash/logstash/logstash-1.4.2.tar.gz

	sudo tar -zxvf elasticsearch-0.90.0.tar.gz

	#!/bin/bash
	#####################################################
	# Name: Bash CheatSheet for Mac OSX
	#
	# A little overlook of the Bash basics
	#
	# Usage:
	#
	# Author: J. Le Coupanec
	# Date: 2014/11/04

	/* The API controller
	Exports 3 methods:
	* post - Creates a new thread
	* list - Returns a list of threads
	* show - Displays a thread and its posts
	*/


	var Thread = require('../models/thread.js');
	var Post = require('../models/post.js');