Skip to content

Instantly share code, notes, and snippets.

View sarfraznawaz2005's full-sized avatar
🏠
Working from home

Sarfraz Ahmed sarfraznawaz2005

🏠
Working from home
View GitHub Profile

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.

@sarfraznawaz2005
sarfraznawaz2005 / index.md
Created December 16, 2022 12:45 — forked from meigwilym/index.md
Notes on stitcher.io's Laravel beyond CRUD

Laravel beyond CRUD

stitcher.io

A blog series for PHP developers working on larger-than-average Laravel projects

Written for projects with a development lifespan of six to twelve months, with a team of three to six developers working on them simultaneously.

Chapter 1: Domain oriented Laravel

@sarfraznawaz2005
sarfraznawaz2005 / parse-commit-log.php
Created August 22, 2020 21:48 — forked from drupol/parse-commit-log.php
Parse commit log with loophp/collection
<?php
declare(strict_types=1);
include 'vendor/autoload.php';
use loophp\collection\Collection;
use loophp\collection\Contract\Operation\Sortable;
$commandStream = static function (string $command): Generator {
@sarfraznawaz2005
sarfraznawaz2005 / gh-pages.md
Created March 4, 2018 07:02 — forked from ramnathv/gh-pages.md
Creating a clean gh-pages branch

Creating a clean gh-pages branch

This is the sequence of steps to follow to create a root gh-pages branch. It is based on a question at [SO]

cd /path/to/repo-name
git symbolic-ref HEAD refs/heads/gh-pages
rm .git/index
git clean -fdx
echo "My GitHub Page" &gt; index.html
@sarfraznawaz2005
sarfraznawaz2005 / readability.js
Created June 29, 2016 16:45 — forked from jakedahn/readability.js
Readability.js
/*jslint undef: true, nomen: true, eqeqeq: true, plusplus: true, newcap: true, immed: true, browser: true, devel: true, passfail: false */
/*global window: false, readConvertLinksToFootnotes: false, readStyle: false, readSize: false, readMargin: false, Typekit: false, ActiveXObject: false */
var dbg = (typeof console !== 'undefined') ? function(s) {
console.log("Readability: " + s);
} : function() {};
/*
* Readability. An Arc90 Lab Experiment.
* Website: http://lab.arc90.com/experiments/readability
@sarfraznawaz2005
sarfraznawaz2005 / README.md
Created May 6, 2016 10:38 — forked from oodavid/README.md
Deploy your site with git

Deploy your site with git

This gist assumes:

  • you have a local git repo
  • with an online remote repository (github / bitbucket etc)
  • and a cloud server (Rackspace cloud / Amazon EC2 etc)
    • your (PHP) scripts are served from /var/www/html/
    • your webpages are executed by apache
  • apache's home directory is /var/www/
@sarfraznawaz2005
sarfraznawaz2005 / csv-export.sh
Created May 1, 2016 09:53 — forked from bxt/csv-export.sh
Exporting whole MySQL databse to CSV files
#!/bin/bash
# USAGE: Will create a .tar.gz with CSVs of all tables in schema.
# Configure below and run as root (i.e. the user mysql runs as)
#
# The script will (or should) SELECT * INTO OUTFILE your tables
# and save them into csv files under /tmp dir first, then name them
# like the tables and move them thogether into a directory. Then
# it will tar everything together and chown you the tarball.
# Schema to export:
@sarfraznawaz2005
sarfraznawaz2005 / interviewitems.MD
Created January 27, 2016 10:42 — forked from amaxwell01/interviewitems.MD
My answers to over 100 Google interview questions

##Google Interview Questions: Product Marketing Manager

  • Why do you want to join Google? -- Because I want to create tools for others to learn, for free. I didn't have a lot of money when growing up so I didn't get access to the same books, computers and resources that others had which caused money, I want to help ensure that others can learn on the same playing field regardless of their families wealth status or location.
  • What do you know about Google’s product and technology? -- A lot actually, I am a beta tester for numerous products, I use most of the Google tools such as: Search, Gmaill, Drive, Reader, Calendar, G+, YouTube, Web Master Tools, Keyword tools, Analytics etc.
  • If you are Product Manager for Google’s Adwords, how do you plan to market this?
  • What would you say during an AdWords or AdSense product seminar?
  • Who are Google’s competitors, and how does Google compete with them? -- Google competes on numerous fields: --- Search: Baidu, Bing, Duck Duck Go