Walter Jenkins AvidDabbler

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.

Calibre Server on Linux

Introduction

Calibre is a powerful cross-platform, open source, ebook manager and editing platform. Its calibre-server component can be used to publish an e-book library on a local network. While you can launch calibre-server as a desktop application, it can also be run as a daemon on a headless Linux server.

This tutorial on setting up calibre-server using Ubuntu 14.04 is very good, but dated.

	# THIS LINUX SETUP SCRIPT HAS MORPHED INTO A WHOLE PROJECT: HTTPS://OMAKUB.ORG
	# PLEASE CHECKOUT THAT PROJECT INSTEAD OF THIS OUTDATED SETUP SCRIPT.
	#
	#

	# Libraries and infrastructure
	sudo apt update -y
	sudo apt install -y \
	docker.io docker-buildx \
	build-essential pkg-config autoconf bison rustc cargo clang \

	export type GeometryTypes = {
	Point: GeoJSON.Point;
	LineString: GeoJSON.LineString;
	Polygon: GeoJSON.Polygon;
	MultiPoint: GeoJSON.MultiPoint;
	MultiLineString: GeoJSON.MultiLineString;
	MultiPolygon: GeoJSON.MultiPolygon;
	GeometryCollection: GeoJSON.GeometryCollection;
	};

	package main

	import (
	"fmt"
	"net/http"
	"strconv"

	"github.com/jinzhu/gorm"
	_ "github.com/jinzhu/gorm/dialects/sqlite"
	"github.com/labstack/echo"