byung-u

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.

byung-u

Installing Kerberos on Redhat 7

This installation is going to require 2 servers one acts as kerberos KDC server and the other machine is going to be client. Lets assume the FQDN's are (here cw.com is the domain name, make a note of the domain name here):

• Kerberos KDC Server: kdc.cw.com
• Kerberos Client: kclient.cw.com

Important: Make sure that both systems have their hostnames properly set and both systems have the hostnames and IP addresses of both systems in

byung-u

## Cell에서 AA로 시작하지 않는 것들은 모두 안보이게 하고 싶다는
## 요구사항에 대해서 이를 출력해주는 코드
import pandas as pd

def main():
    df = pd.read_csv('./test.csv', delimiter='|', header=None)
    for row in range(df.shape[1]):
        df[row] = df[row].str.replace(r'^((?!AA).)*', '')

byung-u

# I wanna make `grep` result like this
#
# % jgrep pStStps *.c
#
# vi -R MS_Stf.c +1006  if (!HINSERT(HTbl[T->i], &pStStps->lkey, 0, pStStps))
# vi -R MS_Stf.c +1009              pStStps->lkey, errno);
# vi -R MS_Stf.c +1010      CancelEvent(T->pool, pStStps->iTimer);
# vi -R MS_Stf.c +1011      free(pStStps); 
# vi -R MS_Stf.c +1014  return pStStps;

byung-u

#!/usr/bin/env python3.5
#
# 원본 
#     00:14:17.810 --> 00:14:22.529
#     since the previous function was a generator 
#     that returns a list of positions, the caller
# 스크립트 실행 후 개행문자 제거 
#     00:14:17.810 --> 00:14:22.529
#     since the previous function was a generator that returns a list of positions, the caller
#

byung-u

#!/usr/bin/env python3.5
#
# 자막의 원본 파일의 시간 형식 : 00:36:47.450 --> 00:36:50.560
# 구글 기계번역 후의 시간 형식 : 00 : 37 : 24.250 -> 00 : 37 : 30.160
#
# 차이점
#   1. ':' 앞뒤로 공백 추가 
#   2. '-'가 1개 사라짐
# 
# 이를 원래의 자막 시간 형식으로 되돌려 주는 스크립트

byung-u

#!/usr/bin/env python3
# http://stackoverflow.com/questions/7255463/exit-while-loop-by-user-hitting-enter-key

while True:
    i = input("Enter text (or Enter to quit): ")
    if not i:
        print("excape")   # Enter key to quit
        break
    print("Your input:", i)

byung-u

 proc_stat_list[proc_list_idx].mem_percent =
            (double)(proc_stat_list[proc_list_idx].proc_rss * 100.0) / total_mem;