Changjiang Cai ccj5351

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.

How can building a heap be O(n) time complexity?

Several highly voted answers have given excellent explanations. I will show several figures to show the proof clearly and hope it is easy to understand.

Height of a Heap

The height of heap h = O(log(N)), where N is the number of (internal) nodes.

Note: ◯ for internal nodes, and □ for external nodes or leaf nodes; values are only saved at internal nodes.

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

	#!/bin/bash
	#
	# script to extract ImageNet dataset
	# ILSVRC2012_img_train.tar (about 138 GB)
	# ILSVRC2012_img_val.tar (about 6.3 GB)
	# make sure ILSVRC2012_img_train.tar & ILSVRC2012_img_val.tar in your current directory
	#
	# https://github.com/facebook/fb.resnet.torch/blob/master/INSTALL.md
	#
	# train/

	import random
	from itertools import chain, cycle, islice
	import torch.utils.data as data

	import matplotlib.pyplot as plt
	from matplotlib.patches import Rectangle
	import time
	import torch
	import numpy as np

	1. Check Python3 root
	>>> import sys
	>>> import os
	>>> sys.executable
	'/usr/local/bin/python3'

	OR

	$ which python3
	/usr/local/bin/python3

	#!/bin/bash
	# add the GPG key for the official Docker repository to the system
	curl -fsSL https://download.docker.com/linux/ubuntu/gpg \| sudo apt-key add -

	# add the Docker repository to APT sources
	sudo add-apt-repository "deb [arch=amd64] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable"

	# update the package database with the Docker packages from the newly added repo
	sudo apt-get update

	import sys, getopt

	import tensorflow as tf

	usage_str = 'python tensorflow_rename_variables.py --checkpoint_dir=path/to/dir/ ' \
	'--replace_from=substr --replace_to=substr --add_prefix=abc --dry_run'


	def rename(checkpoint_dir, replace_from, replace_to, add_prefix, dry_run):
	checkpoint = tf.train.get_checkpoint_state(checkpoint_dir)