memocong

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.

memocong

"""
Single Responsibility Principle
“…You had one job” — Loki to Skurge in Thor: Ragnarok
A class should have only one job. 
If a class has more than one responsibility, it becomes coupled. 
A change to one responsibility results to modification of the other responsibility.
"""

class Animal:
    def __init__(self, name: str):

memocong

Table of Contents

• set -e, -u, -x, -o pipefail
• set -e
• set -x
• set -u
• set -o pipefail
• Setting IFS
• Original Reference

set -e, -u, -x, -o pipefail

memocong

Default

Powerlevel10k

memocong

"""Simple implementation of a B+ tree, a self-balancing tree data structure that (1) maintains sort
data order and (2) allows insertions and access in logarithmic time.
"""

class Node(object):
    """Base node object.

    Each node stores keys and values. Keys are not unique to each value, and as such values are
    stored as a list under each key.

memocong

import bisect
import itertools
import operator


class _BNode(object):
    __slots__ = ["tree", "contents", "children"]

    def __init__(self, tree, contents=None, children=None):
        self.tree = tree

memocong

Introduction

Installing pycurl on MacOS with Python 3.6+ and newer proved to be tricky, especially since a lot of the available resources seem to be outdated ([1], [2], [3]).

This gist was last updated at 2020-12-31.

Steps:

1. Remove previously installed Homebrew versions of curl:

    brew uninstall curl