skygunner

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.

skygunner

class RedisSessionStore(SessionStore):
    def __init__(self, expire = 1800, key_prefix=''):
        SessionStore.__init__(self)
        self.redis = redis.Redis(tools.config.get('redis_host', 'localhost'), 
                                 int(tools.config.get('redis_port', 6379)), 
                                 int(tools.config.get('redis_dbindex', 1)), 
                                 password=tools.config.get('redis_pass', None))
        self.path = session_path()
        self.expire = expire
        self.key_prefix = key_prefix

skygunner

[add_eventon_el cal_id="10" el_title="UPCOMING PERFORMANCES - 2016" pec="ft" number_of_months="4" fixed_year="2016" show_year="yes"]
[add_eventon_el cal_id="9" el_title="UPCOMING PERFORMANCES - 2017" pec="ft" fixed_date="01" fixed_month="01" fixed_year="2017" number_of_months="12" event_count="90" event_order="ASC"]
[add_eventon_el cal_id="8" el_title="Past Performances - 2016" pec="ft" fixed_date="01" fixed_month="01" fixed_year="2016" number_of_months="8" event_count="90" event_order="DESC"]
[add_eventon_el cal_id="7" el_title="Past Performances - 2015" pec="ft" fixed_date="01" fixed_month="01" fixed_year="2015" number_of_months="12" event_count="90" event_order="DESC" ]
[add_eventon_el cal_id="6" el_title="Past Performances - 2014" pec="ft" fixed_date="01" fixed_month="01" fixed_year="2014" number_of_months="12" event_count="80" event_order="DESC" ]
[add_eventon_el cal_id="5" el_title="Past Performances - 2013" pec="ft" fixed_date="01" fixed_month="01" fixed_year="2013" number_of_months="12" event_count="7

skygunner

My thinkpad has this problem. So
Step 1:
check if wlan auto config service is running and set to auto;

Step 2:
delete all vpn client software
delete all vpn adapter and its drivers
reboot

Step 3:

skygunner

<?php
function cache_image($image_url){
    //replace with your cache directory
    $image_path = 'path/to/cache/dir/';
    //get the name of the file
    $exploded_image_url = explode("/",$image_url);
    $image_filename = end($exploded_image_url);
    $exploded_image_filename = explode(".",$image_filename);
    $extension = end($exploded_image_filename);
    //make sure its an image

skygunner

#!/usr/bin/env bash
 
# names of latest versions of each package
export NGINX_VERSION=1.11.1
export VERSION_PCRE=pcre-8.38
export VERSION_LIBRESSL=libressl-2.4.1
export VERSION_NGINX=nginx-$NGINX_VERSION
#export NPS_VERSION=1.9.32.10
#export VERSION_PAGESPEED=v${NPS_VERSION}-beta
 

skygunner

Build a Squid transparent proxy from source code

Please note that this whole manual refers to the version 3.5.15 of Squid. You probably would have to adapt some commands to the version you will actually download.

Table of contents

• Automated Install
  • Disclaimer
  • Squid installation script
• Manual Install

skygunner

<?php

/**
 * ECSHOP 模版类
 * ============================================================================
 * * 版权所有 2005-2012 上海商派网络科技有限公司，并保留所有权利。
 * 网站地址: http://www.ecshop.com；
 * ----------------------------------------------------------------------------
 * 这不是一个自由软件！您只能在不用于商业目的的前提下对程序代码进行修改和
 * 使用；不允许对程序代码以任何形式任何目的的再发布。