Denis xfenix

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.

Git hooks for convenient development

Hooks description

commit-msg: add ticket id from current branch name to the commit message
pre-push: check if CHANGELOG.md has been changed and prompts a warning message if not

Quickstart

Docker - How to cleanup (unused) resources

Once in a while, you may need to cleanup resources (containers, volumes, images, networks) ...

delete volumes

// see: https://github.com/chadoe/docker-cleanup-volumes

$ docker volume rm $(docker volume ls -qf dangling=true)

$ docker volume ls -qf dangling=true | xargs -r docker volume rm

	// ****************************
	//* ******* OUTPUT ********
	//* ** 20X Improvement ****
	//* ****** Tested on ******
	//* **** Node v10.14.2 ****
	// ****************************
	// Start testing : Original
	// Original, #0: 1299.590ms
	// Original, #1: 1268.201ms
	// Original, #2: 1261.733ms

	class E(BaseException):
	def __new__(cls, args, *kwargs):
	return cls
	def a(): yield
	a().throw(E)

	FROM nginx:alpine AS builder

	# nginx:alpine contains NGINX_VERSION environment variable, like so:
	# ENV NGINX_VERSION 1.15.0

	# Our NCHAN version
	ENV NCHAN_VERSION 1.1.15

	# Download sources
	RUN wget "http://nginx.org/download/nginx-${NGINX_VERSION}.tar.gz" -O nginx.tar.gz && \

	import sys

	def j(lineno):
	frame = sys._getframe().f_back
	called_from = frame

	def hook(frame, event, arg):
	if event == 'line' and frame == called_from:
	try:
	frame.f_lineno = lineno

	import discord
	import asyncio

	client = discord.Client()

	@client.event
	async def on_ready():
	print('Logged in as')
	print(client.user.name)
	print(client.user.id)

	#! /usr/bin/env python
	# -- coding: utf-8 --
	"""This module's docstring summary line.

	This is a multi-line docstring. Paragraphs are separated with blank lines.
	Lines conform to 79-column limit.

	Module and packages names should be short, lower_case_with_underscores.
	Notice that this in not PEP8-cheatsheet.py

	package main

	import (
	"io/ioutil"
	"os/exec"
	"fmt"
	)

	// EXAMPLE: echo "Subject: TestnHello" \| sendmail -f you@domain.com you@domain.com
	// Useful Links: https://gobyexample.com/spawning-processes