Farbod Samsamipour farbod-s

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.

فعال سازی 6to4 tunnel IPV6 Local بدون نیاز به IPv6

Source: https://github.com/idaniali/6to4-tunnel-IPV6-Local

Source: https://github.com/Azumi67/6TO4-GRE-IPIP-SIT

Step 0:

Public DNS Servers

Provider	Primary IP	Secondary IP	Focus
Radar	10.202.10.10	10.202.10.11	Gaming
Shelter	94.103.125.157	94.103.125.158	Gaming
Electro	78.157.42.100	78.157.42.101	Filtering
403	10.202.10.202	10.202.10.102	Filtering
Shecan	178.22.122.100	185.51.200.2	Filtering
Begzar	185.55.226.26	185.55.225.25	Filtering

	# Source: https://rosettacode.org/wiki/Voronoi_diagram
	# Dependency: ➜ ~ pip install pillow

	from PIL import Image
	import random
	import math

	def generate_voronoi_diagram(width, height, num_cells):
	image = Image.new("RGB", (width, height))
	putpixel = image.putpixel

	const SPREADSHEET_ID = '{{SHEET_ID}}';
	const SHEET_ID = 123456789;
	const RANGE = 'ApplicantsList!A2:L2';
	//----------------------
	chrome.runtime.onConnect.addListener(port => {
	port.onMessage.addListener(request => {
	if (request.action === 'copyValues') {
	const info = request.data;
	writeToGoogleSheets(SPREADSHEET_ID, RANGE, [info[0], 'To Call / Email - 1', '', 'Jobinja', info[4], '', info[1], '', '', info[3], '', info[2]]);
	}

	curl -s https://api.github.com/repos/google/bundletool/releases/latest \
	\| grep "browser_download_url.*jar" \
	\| cut -d : -f 2,3 \
	\| tr -d \" \
	\| wget -qi -

	# encoding=utf8
	#----------
	# AUTHOR: Farbod Samsamipour <farbod.ps@gmail.com>
	# GITHUB: https://github.com/firebase/firebase-admin-python
	#----------
	import os
	import importlib.util
	import plistlib as plist
	import firebase_admin
	from firebase_admin import credentials, project_management

	#!/bin/bash
	#----------
	# Set variables
	sl='en'
	tl=''
	query=''
	#----------
	# Get the options
	while getopts ":s:t:q:" option; do
	case $option in

	<div style="font-family: sans-serif;">
	<? var data = valid(); ?>
	<form id="form" name="form">
	<? if(Object.prototype.toString.call(data) === '[object Array]') { ?>
	<? for (var i = 0; i < data.length; i++) { ?>
	<? for (var j = 0; j < data[i].length; j++) { ?>
	<input type="checkbox" id="ch<?= '' + i + j ?>" name="ch<?= '' + i + j ?>" value="<?= data[i][j] ?>"><?= data[i][j] ?><br>
	<? } ?>
	<? } ?>
	<? } else { ?>

	# encoding=utf8
	import sys, os
	import requests
	import json

	def t5(t, e, n, i):
	return abs(float(n) * float(i) / float(t) - float(e))

	def number_check(t):
	return t if t > 0 else 0