Zach Whaley zachwhaley

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.

Azure Container App - Custom Domain Managed Certficate scripts

This gist contains a create and destroy script to provision and cleanup custom domains and managed certficates assigned to Azure Container Apps.

This gist supports the following workflow:

Bind custom domain to existing Container App
Provision a managed certificate for the custom domain
Bind the managed certificate to the custom domain

This gist contains lists of modules available in

Python 3.10
Python 3.9
Python 3.8
Python 3.7
Python 3.6
Python 2.7

in AWS Lambda.

	// In Groovy
	// collect = "map"
	// inject = "reduce"
	//
	// See http://docs.groovy-lang.org/next/html/documentation/working-with-collections.html for docs

	////////////////////////////////////////////////////////////////////////////////
	// Arrays
	def myNumbers = [3, 5, 1]

	import requests
	import time
	import json

	token = ''

	#Delete files older than this:
	ts_to = int(time.time()) - 30 * 24 * 60 * 60

	def list_files():

	require 'net/http'
	require 'json'
	require 'uri'

	@token = ''

	def list_files
	ts_to = (Time.now - 30 * 24 * 60 * 60).to_i # 30 days ago
	params = {
	token: @token,

	#
	all: test


	openssl-fips-2.0.8.tar.gz:
	wget http://www.openssl.org/source/openssl-fips-2.0.8.tar.gz


	openssl-1.0.1i.tar.gz:
	wget http://www.openssl.org/source/openssl-1.0.1i.tar.gz

	#!/bin/sh
	#
	# My workflow:
	# git checkout -b myfeature
	# ...edit stuff...git commit...edit stuff...git commit...ready to ship...
	# git ship myfeature -rpd
	#
	# It exits if the merge or rebase requires intervention,
	# for merge: fix the conflict, commit the merge, and re-run the git ship command
	# for rebase: clean up the conflict, run `git rebase --continue` and then re-run the git ship command

	/* Solarized Dark

	For use with Jekyll and Pygments

	http://ethanschoonover.com/solarized

	SOLARIZED HEX ROLE
	--------- -------- ------------------------------------------
	base03 #002b36 background
	base01 #586e75 comments / secondary content

	import java.util.*;
	public class Solution{
	public final static int MAX_NUMBER_OF_STATES = 390625;//5^8

	class State{
	int steps;
	int[] conf;
	int peg1, peg2;
	int prev;