Adam Rose adamerose

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.

Postman vs Insomnia comparison

Postman | API Development Environment https://www.getpostman.com
Insomnia REST Client - https://insomnia.rest/

Features	Insomnia	Postman	Notes
Create and send HTTP requests	x	x
Authorization header helpers	x	x	Can create "Authorization" header for you for different authentication schemes: Basic, Digest, OAuth, Bearer Token, HAWK, AWS

	@echo off
	@rem throw this file in jetbrains installation folder, it takes the last created PyCharm folder (the latest ide update) for the script

	FOR /F "delims=" %%i IN ('dir /b /ad-h /t:c /od -filter "PyCharm*"') DO SET a=%%i

	SET PyCharmPath=C:\Program Files (x86)\JetBrains\%a%\bin\PyCharm64.exe

	echo %PyCharmPath%

	echo Adding file entries

	#!/usr/bin/env python
	#
	# MIGRATED TO: https://github.com/mbafford/cli-tools/blob/master/summarize_json
	#
	# Gives a quick summary of the structure of a JSON file, including the keys, object types, and
	# leaf node types. Provides a count of each data type so you can quickly tell which data points
	# are common.
	#
	# Example:
	#

	-- show running queries (pre 9.2)
	SELECT procpid, age(clock_timestamp(), query_start), usename, current_query
	FROM pg_stat_activity
	WHERE current_query != '<IDLE>' AND current_query NOT ILIKE '%pg_stat_activity%'
	ORDER BY query_start desc;

	-- show running queries (9.2)
	SELECT pid, age(clock_timestamp(), query_start), usename, query
	FROM pg_stat_activity
	WHERE query != '<IDLE>' AND query NOT ILIKE '%pg_stat_activity%'

	import win32api, sys
	import Image
	import win32clipboard
	from cStringIO import StringIO

	def send_to_clipboard(clip_type, data):
	win32clipboard.OpenClipboard()
	win32clipboard.EmptyClipboard()
	win32clipboard.SetClipboardData(clip_type, data)
	win32clipboard.CloseClipboard()