Folgert Karsdorp fbkarsdorp

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.

This example pulls together various examples of work with trees in D3.js.

The panning functionality can certainly be improved in my opinion and I would be thrilled to see better solutions contributed.

One can do all manner of housekeeping or server related calls on the drop event to manage a remote tree dataset for example.

Dragging can be performed on any node other than root (flare). Dropping can be done on any node.

Panning can either be done by dragging an empty part of the SVG around or dragging a node towards an edge.

tmux shortcuts & cheatsheet

start new:

tmux

start new with session name:

tmux new -s myname

	import torch
	from torch import LongTensor
	from torch.nn import Embedding, LSTM
	from torch.autograd import Variable
	from torch.nn.utils.rnn import pack_padded_sequence, pad_packed_sequence

	## We want to run LSTM on a batch of 3 character sequences ['long_str', 'tiny', 'medium']
	#
	# Step 1: Construct Vocabulary
	# Step 2: Load indexed data (list of instances, where each instance is list of character indices)

	"""
	Three ways of computing the Hellinger distance between two discrete
	probability distributions using NumPy and SciPy.
	"""

	import numpy as np
	from scipy.linalg import norm
	from scipy.spatial.distance import euclidean

	#!/usr/bin/env python

	"""
	nsb_entropy.py

	June, 2011 written by Sungho Hong, Computational Neuroscience Unit, Okinawa Institute of
	Science and Technology
	May, 2019 updated to Python 3 by Charlie Strauss, Los Alamos National Lab

	This script is a python version of Mathematica functions by Christian Mendl