Wilson Freitas wilsonfreitas

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.

Machine Learning and AI for Finance

Advances in Financial Machine Learning, de Prado: http://www.quantresearch.org/
Machine Learning for Asset Managers, de Prado
Machine Learning for Factor Investing, Guida: http://www.mlfactor.com/
Big Data and Machine Learning in Quantitative Investment, Guida
Artificial Intelligence in Finance, Hilpisch: https://home.tpq.io/

Trading Analytics and Algorithms

Python for Finance 2d ed, Hilpisch
Derivatives Analytics with Python, Hilpisch

	from functools import wraps

	try:
	from functools import lru_cache
	except ImportError:
	def lru_cache(user_function):
	cache = {}
	@wraps(user_function)
	def wrapper(*args):
	key = tuple(args)

	f <- function(x) cos(x*20)
	expi <- function(x) cos(x) + sin(x)*1i
	par(mfrow = c(1,2))
	L <- 40
	medias_Re <- c()
	fs <- c()
	as <- seq(0.01, 1, l = 140)

	animation::saveGIF({
	for(a in as) {

	#!/usr/bin/env python
	# -- coding: utf-8 --
	import requests,json,sys

	# Script simples para consulta de dados na base dados nacional do SUS utilizando o CPF.
	# Jhonathan Davi A.K.A jh00nbr / Insightl4b lab.insightsecurity.com.br
	# Blog: lab.insightsecurity.com.br
	# Github: github.com/jh00nbr
	# Twitter @jh00nbr