Dipanshu dip-gupta

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.

	#!/usr/bin/env python3

	# !! NOTE - this script is no longer maintained... please see the repo for further
	# updates: https://github.com/jheddings/notes2notion

	# this script attempts to migrate from Apple Notes to Notion while retaining as
	# much information and formatting as possible. there are limitations to the
	# export data from Notes, so we try to preserve the intent of the original note.

	# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,

	import numpy as np
	import pandas as pd
	import datetime as dt

	from sklearn.datasets import make_classification

	def create_price_data(start_price: float = 1000.00, mu: float = .0, var: float = 1.0, n_samples: int = 1000000):

	i = np.random.normal(mu, var, n_samples)
	df0 = pd.date_range(periods=n_samples, freq=pd.tseries.offsets.Minute(), end=dt.datetime.today())