Adam Lewis Adam-D-Lewis

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.

	# You'll need to save the 2 files separately in the same dir to run.

	# mcp-server.py =================================================================================
	from pathlib import Path

	from mcp.server.fastmcp import FastMCP

	server = FastMCP('Pydantic AI Server')

	@server.tool()

	import os
	import sys
	import threading
	import time
	import webbrowser
	from dataclasses import dataclass
	from datetime import datetime
	from typing import Iterable, Tuple

	# Third-party

	import panel as pn

	script = """
	<script>
	function querySelectorDeep(selector, rootNode=document.body) {
	const arr = []

	const traverser = node => {
	// 1. decline all nodes that are not elements
	if(node.nodeType !== Node.ELEMENT_NODE) {

	# POC Type with your voice script
	# You may also need to install the additional dependencies: portaudio flac

	from pathlib import Path
	import speech_recognition as sr
	import pyaudio
	from pynput.keyboard import Controller
	from threading import Thread
	import wave