Hussein Lezzaik HusseinLezzaik

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.

	""" To use: install LLM studio (or Ollama), clone OpenVoice, run this script in the OpenVoice directory
	git clone https://github.com/myshell-ai/OpenVoice
	cd OpenVoice
	git clone https://huggingface.co/myshell-ai/OpenVoice
	cp -r OpenVoice/* .
	pip install whisper pynput pyaudio
	"""

	from openai import OpenAI
	import time

	# Code inspired from https://gist.github.com/karpathy/00103b0037c5aaea32fe1da1af553355
	# slerp function is entirely lifted from the above gist.

	import torch
	from diffusers import DiffusionPipeline
	import numpy as np


	def interpolate(v1, v2, step, total_steps):
	alpha = step / (total_steps - 1)

	from fastapi import Request, HTTPException
	from pydantic import BaseModel, BaseModel, HttpUrl
	from modal import Secret, App, web_endpoint, Image
	from typing import Optional, List
	from example import proposal
	import os

	app = App(name="circleback", image=Image.debian_slim().pip_install("openai", "pydantic", "fastapi"))

	class Attendee(BaseModel):

	# -----------------------------------------------------------------------------
	# AI-powered Git Commit Function
	# Copy paste this gist into your ~/.bashrc or ~/.zshrc to gain the `gcm` command. It:
	# 1) gets the current staged changed diff
	# 2) sends them to an LLM to write the git commit message
	# 3) allows you to easily accept, edit, regenerate, cancel
	# But - just read and edit the code however you like
	# the `llm` CLI util is awesome, can get it here: https://llm.datasette.io/en/stable/

	gcm() {

	# train_grpo.py
	#
	# See https://github.com/willccbb/verifiers for ongoing developments
	#
	"""
	citation:

	@misc{brown2025grpodemo,
	title={Granular Format Rewards for Eliciting Mathematical Reasoning Capabilities in Small Language Models},
	author={Brown, William},

	import matplotlib.pyplot as plt
	import numpy as np
	import seaborn as sns
	from gymnasium import spaces
	from stable_baselines3 import PPO
	from stable_baselines3.common.env_util import make_vec_env
	from stable_baselines3.common.vec_env import VecEnvWrapper

	sns.set_theme()

	"""
	The most atomic way to train and run inference for a GPT in pure, dependency-free Python.
	This file is the complete algorithm.
	Everything else is just efficiency.

	@karpathy
	"""

	import os # os.path.exists
	import math # math.log, math.exp