yfe404

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.

yfe404

About

Summarizing the instructions of the pass tool (as seen on its website).

Getting Started

Installation

Execute: $ sudo apt install pass

yfe404

Using ZeroTier on PiKVM

Requires PiKVM OS version 2022.06.20 or newer.

Steps

1. Install ZeroTier, then start and stop it to generate an identity

yfe404

yfe404

systemctl enable sshd ; systemctl start sshd

# select relevant servers in /etc/pacman.d/mirrorlist according to your location

# initialise keyring
pacman-key --init 
# initial setup of keys
pacman-key --populate archlinux
# update everything (should be done regularly)
pacman -Sy archlinux-keyring && pacman -Su

yfe404

Pre-conditions
--------------

- The following packages must be installed on both ends: gpg, xxd.
- Sender and Receiver must know the password to encrypt/decrypt the data.

Sender
------

$ gpg --symmetric $FILE_TO_SEND 

yfe404

#!/bin/bash

DISK_IMAGE=~/Downloads/my-image.img
DISK=/dev/sdK
pv $DISK_IMAGE | sudo dd bs=4M of=$DISK

yfe404

# This code is written at BigVision LLC. It is based on the OpenCV project. It is subject to the license terms in the LICENSE file found in this distribution and at http://opencv.org/license.html

# Usage example:  python3 object_detection_yolo.py --video=run.mp4
#                 python3 object_detection_yolo.py --image=bird.jpg
import cv2 as cv
import argparse
import sys
import numpy as np
from urllib.request import urlopen
import os

yfe404

[Unit]
Description="Establish a SSH tunnel to orion to map searx port to local 3337"
After=sshd.service
StartLimitIntervalSec=0

[Service]
Type=simple
Restart=Always
RestartSec=1
User=yfe

yfe404

for c in $(i3-msg -t get_bar_config | python -c \
      'import json,sys;print("\n".join(json.load(sys.stdin)))'); do \
    (i3bar --bar_id=$c >i3bar.$c.log 2>&1) & \
  done;


cat i3bar.bar-*.log