Seth Wahle osteth

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.

Useful Pandas Snippets

A personal diary of DataFrame munging over the years.

Data Types and Conversion

Convert Series datatype to numeric (will error if column has non-numeric values)
(h/t @makmanalp)

	/**
	* HOW TO USE:
	* 1. Go to: https://YOURTEAM.slack.com/files
	* 2. Open inspector for your browser.
	* 3. You'll see: 2017/6/6 22:16:45.834 User id: XXXXXXXXX, team id: XXXXXXXXX
	* 4. Paste user id in to where it says "USER_ID_HERE"
	* 5. Copy/paste this whole script to your console.
	*/
	/*global
	jQuery, TS

	import gc
	import machine
	import pyb
	import time
	import network

	# Configure GPIO pins 0 and 2 to be used for
	# the I²C interface
	iic = machine.I2C(pyb.Pin(2), pyb.Pin(0))

	#!/usr/bin/env python3

	"""Simple HTTP Server With Upload.

	This module builds on BaseHTTPServer by implementing the standard GET
	and HEAD requests in a fairly straightforward manner.

	see: https://gist.github.com/UniIsland/3346170
	"""

	#!/bin/sh

	# This is a skeleton of a bash daemon. To use for yourself, just set the
	# daemonName variable and then enter in the commands to run in the doCommands
	# function. Modify the variables just below to fit your preference.

	daemonName="DAEMON-NAME"

	pidDir="."
	pidFile="$pidDir/$daemonName.pid"