Jaga Santagostino kandros

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.

Emacs packages, features, files, layers, extensions, auto-loading, require, provide, use-package… All these terms getting you confused? Let’s clear up a few things.

Files

Emacs files contains code that can be evaluated. When evaluated, the functions, macros and modes defined in that file become available to the current Emacs session. Henceforth, this will be termed as loading a file.

One major problem is to ensure that all the correct files are loaded, and in the

The Beginning

Yes...it's true...redux is smart....smarter than you even know. It really does want to help you. It strives to be sane and easy to reason about. With that being said, redux gives you optimizations for free that you probably were completely unaware of.

`connect()`

connect is the most important thing in redux land IMO. This is where you tie the not between redux and your underlying components. You usually take state and propogate it down your component hiearchy in the form of props. From there, presentational

Animated Weather Icons

Based on dribbble shot https://dribbble.com/shots/2097042-Widget-Weather by kylor

A Pen by Josh Bader on CodePen.

License.

Libraries

jQuery - The de-facto library for the modern age. It makes things like HTML document traversal and manipulation, event handling, animation, and Ajax much simpler with an easy-to-use API that works across a multitude of browsers.
Backbone - Backbone.js gives structure to web applications by providing models with key-value binding and custom events, collections with a rich API of enumerable functions, views with declarative event handling, and connects it all to your existing API over a RESTful JSON interface.
AngularJS - Conventions based MVC framework for HTML5 apps.
Underscore - Underscore is a utility-belt library for JavaScript that provides a lot of the functional programming support that you would expect in Prototype.js (or Ruby), but without extending any of the built-in JavaScript objects.
lawnchair - Key/value store adapter for indexdb, localStorage

	// Usually I use this in my app's config file, in case I need to disable all cache from the app
	// Cache is from `js-cache`, something like `import Cache from 'js-cache';`
	const cacheable = true,
	cache = new Cache();

	// On request, return the cached version, if any
	axios.interceptors.request.use(request => {

	// Only cache GET requests
	if (request.method === 'get' && cacheable) {

	// routes.js
	const routes = [
	{
	path: '/',
	component: Home,
	exact: true
	},
	{
	path: '/gists',
	component: Gists

	const addAccountToTransactions = (txs, accounts) => (
	txs.map(tx => (
	// add the relationship
	{
	...tx,
	account: accounts[tx.accountKey]
	}
	))
	)

	import React, { PropTypes, Component } from 'react'
	import { getRef, listToArray } from '../utils/firebase'
	import { ErrorMessage, Loading } from '../Theme'

	/*

	```js
	<Ref path="/somewhere">
	{({ error, loaded, value }) => (
	// `value` is an object w/ keys

	import mongoose from 'mongoose';

	let schema = new mongoose.Schema({
	email: { type: String, required: true, unique: true },
	password: { type: String, required: true }
	});

	schema.statics.findOrCreate = async (conditions, opt_attr) => {
	let document = await User.findOne(conditions);