woss

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.

woss

CREATE TABLE CameraDetails (
    Manufacturer SYMBOL,
    Model SYMBOL,
    Orientation SYMBOL,
    Software STRING,
    DateAndTime timestamp,
    YCbCrPositioning SYMBOL,
    Compression SYMBOL,
    XResolution LONG,
    YResolution LONG,

woss

# Put this file in the root of substrate / polkadot directory and build the image using	
# the following command:	
#	
#     docker build -t <container id> .	
#	
# you can pick <container id> yourself. For example: `johndoe/rpi-cross`.	
#	

FROM rust:latest

woss

var flattenObject = function(ob) {
	var toReturn = {};
	
	for (var i in ob) {
		if (!ob.hasOwnProperty(i)) continue;
		
		if ((typeof ob[i]) == 'object') {
			var flatObject = flattenObject(ob[i]);
			for (var x in flatObject) {
				if (!flatObject.hasOwnProperty(x)) continue;

woss

var flattenObject = function(ob) {
	var toReturn = {};
	
	for (var i in ob) {
		if (!ob.hasOwnProperty(i)) continue;
		
		if ((typeof ob[i]) == 'object') {
			var flatObject = flattenObject(ob[i]);
			for (var x in flatObject) {
				if (!flatObject.hasOwnProperty(x)) continue;

woss

const { createApolloFetch } = require('apollo-fetch');

const fetch = createApolloFetch({
  uri: 'https://1jzxrj179.lp.gql.zone/graphql',
});

fetch({
  query: '{ posts { title }}',
}).then(res => {
  console.log(res.data);

woss

// convert 0..255 R,G,B values to binary string
RGBToBin = function(r,g,b){
    var bin = r << 16 | g << 8 | b;
    return (function(h){
        return new Array(25-h.length).join("0")+h
    })(bin.toString(2))
}

// convert 0..255 R,G,B values to a hexidecimal color string
RGBToHex = function(r,g,b){

woss

license: gpl-3.0

woss

requirements_file = 'base.pip'

requirements = open(requirements_file, 'r')
content = requirements.read().splitlines()
content = list(set(content))
content.sort(key=lambda y: y.lower())
content = '\n'.join(content)

file = open('sorted_'+requirements_file, 'w')
file.write(content)

woss

requirements_file = 'base.pip'

requirements = open(requirements_file, 'r')
content = requirements.read().splitlines()
content = list(set(content))
content.sort(key=lambda y: y.lower())
content = '\n'.join(content)

file = open('sorted_'+requirements_file, 'w')
file.write(content)