ragnraok

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.

ragnraok

#!/usr/bin/env python
#
# Shows GOP structure of video file. Useful for checking suitability for HLS and DASH packaging.
# Example:
#
# $ iframe-probe.py myvideo.mp4
# GOP: IPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPP 60 CLOSED
# GOP: IPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPP 60 CLOSED
# GOP: IPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPP 60 CLOSED
# GOP: IPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPPP 60 CLOSED

ragnraok

# -*- coding: utf-8 -*-
from flask import Flask, request, make_response
from translator import google_translate
from moe_pic import get_pict
from douban_music import get_music
from logging.handlers import RotatingFileHandler

import libxml2
import time
import logging

ragnraok

import cv
import sys

input_img_name = sys.argv[1]
output_img_name = sys.argv[2]

input_img = cv.LoadImage(input_img_name, cv.CV_LOAD_IMAGE_COLOR)

# blur the image
dst = cv.CreateImage(cv.GetSize(input_img), input_img.depth, input_img.channels)

ragnraok

# -*- coding: utf8 -*-

import sys

from PyQt4.QtCore import *
from PyQt4.QtGui import *


class Form(QDialog):
    def __init__(self, parent=None):