hesling hesling

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.

HR发给应聘者常用邮件模板
人才关系管理，具体到招聘工作中，就是应聘者关系管理。据调查，90%以上的求职者，对应聘的公司了解程度并不深。因此，与HR的沟通过程将被做为推断企业整体管理水平的重要依据。在招聘工作过程中，与应聘者保持规范、高效、人性化的沟通，可以大大提高企业的雇主品牌影响力，在人才的争夺中获得无形的优势。

一、收到简历后的回复 XXXX先生\女士，您好！感谢您投递xx公司的XX职位。您的简历我们已经收到，我们会在7个工作日内处理您的简历。附：公司简介 xx公司人力资源部

说明：在应聘者投递简历后，很多招聘工作较为成熟的企业会马上给应聘者发送一封邮件，以表明公司收到了应聘者的求职申请。这一封邮件是HR与应聘者的第一次接触，很多公司会采用自动化的软件来实现这一功能，它所体现的是企业对每一位应聘者的重视以及招聘工作的专业化程度。

	from PIL import Image

	# Create a blank grey image
	wip_img = Image.new("RGBA", (550, 450), "#f2f2f2")
	# Load the santa hat
	santa_hat = Image.open("santa_hat.png")
	# At first this is just a black rectangle of the same size as the hat
	shadow = Image.new("RGBA", santa_hat.size, color="black")

	# Coordinates at which to draw the hat and shadow

	const waitForAjax = async (page) => {
	await page.evaluate(() => {
	return new Promise((resolve, reject) => {
	const times = 10;
	let i = 0;
	const interval = setInterval(() => {
	const ajaxCalls = jQuery.active;
	if (ajaxCalls === 0) {
	clearInterval(interval);
	resolve();

	var CryptoJS = require('crypto-js')
	var request = require('request-promise')

	/*
	* npm install crypto-js request-promise request
	* node wx_t1t_hack.js
	*/

	// export function testEncription(msg, fullKey) {
	// var fullKey = fullKey.slice(0, 16)