Skip to content

Instantly share code, notes, and snippets.

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.

@faustomilletari
faustomilletari / covid19challenge_Eisen_starter_kit.py
Created June 9, 2020 08:14
Covid19Challenge.eu Eisen starter kit
"""
Eisen EU COVID-19 challenge starter kit
NOTE: you need to register to the challenge, download and unpack the data in
order to be able to run the following example.
Find more info here: https://www.covid19challenge.eu
Information about Eisen can be found at http://eisen.ai -- Join the community on Slack https://bit.ly/2L7i6OL
// The core app code
var myApp = (function () {
'use strict';
// Create a public methods object
var methods = {};
/**
* Extend the public methods object
@KevinAst
KevinAst / article.md
Last active April 12, 2025 07:55
Integrating GitBook with JSDoc to Document Your Open Source Project

Integrating GitBook with JSDoc to Document Your Open Source Project

Introduction

Good documentation should include two distinct elements - a Guide and an API:

  1. The Guide builds concepts, providing examples, etc.

GitBook is well suited to

@pelson
pelson / README.md
Last active August 13, 2017 16:58
Feature extraction from the XKCD handwriting dataset
@carloslimaborges
carloslimaborges / forksync.txt
Created January 18, 2017 02:56
Sync fork with original
git fetch upstream
git checkout master
git merge upstream/master
git merge upstream/master
git commit
git push
@jasonkit
jasonkit / filter-visualize.py
Last active December 18, 2022 09:55
Python script for visualizing inception feature at different stages
import os.path
import tensorflow as tf
from tensorflow.python.platform import gfile
import matplotlib.pyplot as plt
log_dir = "/tmp/inception_v3_log"
if not os.path.exists(log_dir):
os.makedirs(log_dir)
@punkdata
punkdata / git-get-files-by-size.py
Last active September 25, 2022 00:36
Git this script lists the files that are larger than the size you specify. Example use: python git-find-big-files.py fix-remove-files 1000000 (file size in MBs)
#!/usr/bin/python
# run the script: python git-find-big-files.py <the branch> <file size>
# Example use: python git-find-big-files.py fix-remove-files 1000000 (this value equals 1 Megabyte)
# the Fix-remove-files specifies the branch that you are cleaning
import os, sys
def getOutput(cmd):
return os.popen(cmd).read()
@akiross
akiross / imgaverage.py
Created January 18, 2016 14:13
A very simple tool for making average of similar images
#!/usr/bin/env python3
import os
import re
import numpy as np
from ast import literal_eval as make_tuple
from tkinter import *
from tkinter import ttk
from tkinter import filedialog