nathania

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.

nathania

Install native ARM R: https://cloud.r-project.org/

Install RStudio (probably preview) which is not native as of today: https://www.rstudio.com/products/rstudio/download/preview/

This blog post is helpful for getting Tensorflow working, but it is older, before the ARM version of R and the RStudio version that supports it was available.

This other blog post has specific steps outlined, but some of it has also been superseded.

nathania

# install.packages(c("here", "fs", "stringr", "purrr", "git2r"))

# to add invisibly in your R profile, open with usethis::edit_r_profile()
# then define it in an environment, e.g.
# .env <- new.env()
# .env$move_slides_to_web <- {function definition}

move_slides_to_web <- function(folder = NULL, index = NULL) {
  
  if (is.null(folder)) {

nathania

ruler <- function(width = getOption("width")) {
  x <- seq_len(width)
  y <- dplyr::case_when(
    x %% 10 == 0 ~ as.character((x %/% 10) %% 10),
    x %% 5 == 0  ~ "+",
    TRUE         ~ "-"
  )
  cat(y, "\n", sep = "")
  cat(x %% 10, "\n", sep = "")
}

nathania

# Adapted from https://stackoverflow.com/a/7267364/1036500 by Andrie de Vries

library(ggplot2)

td <- expand.grid(
  hjust=c(0, 0.5, 1),
  vjust=c(0, 0.5, 1),
  angle=c(0, 45, 90),
  text="text"
)

nathania

#!/usr/bin/env python
# numpy and biopython are required -- pip install numpy biopython

from Bio import Entrez
from Bio import Medline

MAX_COUNT = 10
TERM = 'Tuberculosis'

print('Getting {0} publications containing {1}...'.format(MAX_COUNT, TERM))

nathania

#!/usr/bin/env ruby -wKU

# Adapted from Brett Terpstra’s original “Markdown to Evernote” service (http://brettterpstra.com/a-better-os-x-system-service-for-evernote-notes-with-multimarkdown/)
# Martin Kopischke 2011 – License: Creative Commons Attribution Share-Alike (CC BY-SA) 3.0 Unported (http://creativecommons.org/licenses/by-sa/3.0/)
# Changes:	– create only one Evernote note per (Multi)Markdown input passed (instead of one per line)
#			– do not choke on shell escape characters (use Tempfile instead of shell pipe for osascript)
#			– default to MultiMarkdown 3 executable (instead of MMD 2 Perl script)
#			– make smart typography processing optional (set SMARTY to 'false' to bypass processing;
#			  note smart typography cannot be disabled in MMD 3.0 and 3.0.1
#			– handle both smart typography processing scripts (ie. SmartyPants.pl)

nathania

-- the following variable allows to choose what we want to export
-- it can be "Selected Papers Only", "Selected Collection" or "Entire Library"
set myDesiredSaveRange to "Selected Collection"

-- the following variable allows is the path where we save the bib file
set myPath to "~/Desktop/from_papers.bib"

-- do we also have a prettifier?
set runPrettifier to true
-- path to it

nathania

# Ruby/C/Fortran Bridge Rakefile
# Cameron Carroll, July 2012
# Purpose: Rake build script to facilitate calling Fortran code from Ruby in order to outsource
#          heavy lifting computation. This script will compile Fortran and C code in present directory
#          but leaves implementation and linking up to the user.
#
# Notes: This script may require a little bit of configuration depending on the system.
#     1: The Ruby include flags are specifically for MY system. I haven't found a way to generate them,
#        so you have to either tailor them by hand or generate a extconf.rb makefile, enable verbose mode,
#        and copy the include flags from the compile command. Yeah, I know, I know...