karpathy

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.

mberman84

import os

os.environ["OPENAI_API_KEY"] = "XXX"
os.environ["GROQ_API_KEY"] = "YYY"

from routellm.controller import Controller

client = Controller(
  routers=["mf"],
  strong_model="gpt-4-1106-preview",

AhsanAyaz

  [
    {
        "created": "2022-11-21T23:25:28.008Z",
        "name": "sjs-request-page-index",
        "tags": [
            "sjs-request-page-index"
        ],
        "content": "import { Component } from \"solid-js\";\n\nconst RequestIndex: Component = () => {\n  return (\n    <div class=\"flex flex-col md:flex-row gap-4 justify-center items-center bg-gray-200 p-4 border border-gray-300 min-h-full rounded-lg\">\n      <div class=\"text-2xl flex gap-4 items-center\">\n        <ion-icon class=\"text-4xl\" name=\"arrow-back-circle-outline\"></ion-icon>\n        <span>Select a request from the left panel</span>\n      </div>\n    </div>\n  );\n};\n\nexport default RequestIndex;",
        "contentType": "typescriptreact"
    },

mneedham

# The NYC Taxis Dataset - https://www1.nyc.gov/site/tlc/about/tlc-trip-record-data.page

pip install parquet-cli

parq data/yellow_tripdata_2022-01.parquet

parq data/yellow_tripdata_2022-01.parquet --schema

parq data/yellow_tripdata_2022-01.parquet --head 10

bradtraversy

Laravel Xampp Setup (Windows & Mac)

Install Xampp

Install Xampp from https://www.apachefriends.org/index.html

• Run the Xampp installer and open the Xampp control panel
• Make sure that you enable the Apache and MySQL services
• On mac you need to click "Start" on the Home tab, "Enable" on the Network tab and "Mount" on the Location Tab. Click "Explore" on the location tab to open your Xampp/Lampp folder

Install Composer

bradtraversy

Laravel Valet Setup (Mac)

This will get you setup with Laravel & Valet on your Mac. Quentin Watt has a good video tutorial on getting setup here as well

Install Homebrew

Go to https://brew.sh/ and copy the command and run in your terminal

It will be something like this...

/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"

adameubanks

"diagnosis(1=m, 0=b)",radius_mean,texture_mean,perimeter_mean,area_mean,smoothness_mean,compactness_mean,concavity_mean,concave points_mean,symmetry_mean,fractal_dimension_mean,radius_se,texture_se,perimeter_se,area_se,smoothness_se,compactness_se,concavity_se,concave points_se,symmetry_se,fractal_dimension_se,radius_worst,texture_worst,perimeter_worst,area_worst,smoothness_worst,compactness_worst,concavity_worst,concave points_worst,symmetry_worst,fractal_dimension_worst
1,17.99,10.38,122.8,1001,0.1184,0.2776,0.3001,0.1471,0.2419,0.07871,1.095,0.9053,8.589,153.4,0.006399,0.04904,0.05373,0.01587,0.03003,0.006193,25.38,17.33,184.6,2019,0.1622,0.6656,0.7119,0.2654,0.4601,0.1189
1,20.57,17.77,132.9,1326,0.08474,0.07864,0.0869,0.07017,0.1812,0.05667,0.5435,0.7339,3.398,74.08,0.005225,0.01308,0.0186,0.0134,0.01389,0.003532,24.99,23.41,158.8,1956,0.1238,0.1866,0.2416,0.186,0.275,0.08902
1,19.69,21.25,130,1203,0.1096,0.1599,0.1974,0.1279,0.2069,0.05999,0.7456,0.7869,4.585,94.03,0.00615,0.04006,0.03832,0.02058,0.0225

wumb0

<#

  ____       _       _              
 |  _ \ __ _| |_ ___| |__           
 | |_) / _` | __/ __| '_ \          
 |  __/ (_| | || (__| | | |         
 |_|   \__,_|\__\___|_| |_|         
  _____      _                  _   
 | ____|_  _| |_ _ __ __ _  ___| |_ 
 |  _| \ \/ / __| '__/ _` |/ __| __|

benawad

{
  "suggest.noselect": false,
  "coc.preferences.formatOnSaveFiletypes": [
    "javascript",
    "typescript",
    "typescriptreact",
    "json",
    "javascriptreact",
    "typescript.tsx",
    "graphql"

benawad

" Specify a directory for plugins
call plug#begin('~/.vim/plugged')

Plug 'neoclide/coc.nvim', {'branch': 'release'}
Plug 'scrooloose/nerdtree'
"Plug 'tsony-tsonev/nerdtree-git-plugin'
Plug 'Xuyuanp/nerdtree-git-plugin'
Plug 'tiagofumo/vim-nerdtree-syntax-highlight'
Plug 'ryanoasis/vim-devicons'
Plug 'airblade/vim-gitgutter'