Shawn Zhang hustshawn

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.

Vagrant and VMWare Tech Preview on Apple M1 Pro

This document summarizes notes taken while to make the VMWare Tech preview work on Apple M1 Pro, it originated from discussions in hashicorp/vagrant-vmware-desktop#22

Installing Rosetta

First install Rosetta if not already done, this is needed to run x86 code:

Tabs and Windows

Function	Shortcut
New Tab	`⌘` + `T`
Close Tab or Window	`⌘` + `W` (same as many mac apps)
Go to Tab	`⌘` + `Number Key` (ie: `⌘2` is 2nd tab)
Go to Split Pane by Direction	`⌘` + `Option` + `Arrow Key`
Cycle iTerm Windows	`⌘` + `backtick` (true of all mac apps and works with desktops/mission control)

GPG - SSH setup

Generating the master key

Here we create the master key. We want only Certify capability: we use the master key only to create the subkeys, Sign - Encrypt - Authenticate capabilities will be assigned to the subkeys.

Run the following command to start the master key generation process. Select the set your own capabilities creation process (type 8)

  ▶ gpg --full-generate-key --expert

Multiple SSH Keys settings for different github account

create different public key

create different ssh key according the article Mac Set-Up Git

$ ssh-keygen -t rsa -C "your_email@youremail.com"

AWS Service annotations

service.beta.kubernetes.io/aws-load-balancer-access-log-emit-interval (in minutes)
service.beta.kubernetes.io/aws-load-balancer-access-log-enabled (true|false)
service.beta.kubernetes.io/aws-load-balancer-access-log-s3-bucket-name
service.beta.kubernetes.io/aws-load-balancer-access-log-s3-bucket-prefix
service.beta.kubernetes.io/aws-load-balancer-additional-resource-tags (comma-separated list of key=value)
service.beta.kubernetes.io/aws-load-balancer-backend-protocol (http|https|ssl|tcp)
service.beta.kubernetes.io/aws-load-balancer-connection-draining-enabled (true|false)

	1. # create new .py file with code found below
	2. # install ollama
	3. # install model you want “ollama run mistral”
	4. conda create -n autogen python=3.11
	5. conda activate autogen
	6. which python
	7. python -m pip install pyautogen
	7. ollama run mistral
	8. ollama run codellama
	9. # open new terminal

	{
	"https://blog.twitter.com/developer": "https://blog.twitter.com/api/blog.rss?name=developer",
	"https://code.facebook.com/posts/": "https://code.facebook.com/posts/rss",
	"http://blog.chromium.org/": "http://blog.chromium.org/feeds/posts/default",
	"http://www.theguardian.com/info/developer-blog": "http://www.theguardian.com/info/developer-blog/rss",
	"http://open.blogs.nytimes.com/": "http://open.blogs.nytimes.com/feed/",
	"http://blog.apps.npr.org/": "http://blog.apps.npr.org/atom.xml",
	"http://www.webperformancetoday.com/": "http://www.webperformancetoday.com/feed/",
	"http://www.filamentgroup.com/lab/": "http://www.filamentgroup.com/lab/atom.xml",
	"http://githubengineering.com/": "http://githubengineering.com/atom.xml",

	; if you're using the starter bundle file `docker/php/php-fpm.d/docker.conf`
	[global]
	daemonize = no
	pid = run/php-fpm.pid

	[www]
	listen = /usr/local/var/run/php-fpm.sock
	listen.owner = www-data
	listen.group = www-data
	listen.mode = 0660

	sudo pip install awscli
	aws configure
	aws ses send-email \
	--from "john@gmail.com" \
	--destination "ToAddresses=mike@gmail.com" \
	--message "Subject={Data=from ses,Charset=utf8},Body={Text={Data=ses says hi,Charset=utf8},Html={Data=,Charset=utf8}}"