Nick Granado heatxsink

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.

Download the latest Raspberry Pi OS Lite image from https://www.raspberrypi.com/software/operating-systems/ (2022-04-04 at the time of this writing).

Insert your microSD card. Use Raspberry Pi Imager to burn the image to your microSD card. Make to select "Set username and password" in the config before starting. Name the user pi and select your own password.

Ensure the disk is mounted again, then enable SSH.

$ touch /Volumes/boot/ssh

	#!/usr/bin/env python3
	"""
	To use:
	1. install/set-up the google cloud api and dependencies listed on https://github.com/GoogleCloudPlatform/python-docs-samples/tree/master/texttospeech/cloud-client
	2. install pandoc and pypandoc, also tqdm
	3. create and download a service_account.json ("Service account key") from https://console.cloud.google.com/apis/credentials
	4. run GOOGLE_APPLICATION_CREDENTIALS=service_account.json python make_audiobook.py book_name.epub
	"""
	import re
	import sys

	import (
	"github.com/jinzhu/gorm"
	_ "github.com/jinzhu/gorm/dialects/sqlite"
	"encoding/json"
	"fmt"
	)

	// The model.
	type User struct {
	gorm.Model