qant

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.

qant

//Override woocommerce product categories widgets
	add_action( 'widgets_init', 'floweb_override_woocommerce_widgets', 15 );
	function floweb_override_woocommerce_widgets() {
	  	// Ensure our parent class exists to avoid fatal error
		if ( class_exists( 'WC_Widget_Cart' ) ) {
			unregister_widget( 'WC_Widget_Cart' );
			require get_template_directory() . '/functions/custom-widgets/floweb-class-wc-widget-cart.php';
			register_widget( 'Floweb_WC_Widget_Cart' );
		}
	}

qant

//This command must occur after you create your tracker object and before you use any of the enhanced ecommerce specific functionality.
ga('require', 'ec');

qant

<?php
if ( ! function_exists( 'wc_rest_get_product_images' ) ) {
	add_filter( 'woocommerce_rest_prepare_product_object', 'wc_rest_get_product_images', 10, 2 );

	/**
	 * Get the images for a product or product variation
	 * and returns all image sizes.
	 *
	 * @param WP_REST_Request                 $request Request object.
	 * @param WC_Product|WC_Product_Variation $product Product instance.

qant

<?php

/*
 * THE FILTER
 *
*/
function custom_responsive_image_sizes($sizes, $img_name, $attachment_id) {
	$sizes  = wp_get_attachment_image_sizes($attachment_id, 'original');
	$meta   = wp_get_attachment_metadata($attachment_id);
	$width  = $meta['width'];

qant

<?php 
$args = array(
  'post_type' 	=> array( 'product' ),
  'meta_key'  	=> 'total_sales',
  'orderby'   	=> 'meta_value_num',
  'order' 		=> 'desc',
  'posts_per_page'		=> 5
);

$popular_products = new WP_Query( $args );

qant

<?php
/**
 * Hook: Empty cart before adding a new product to cart WITHOUT throwing woocommerce_cart_is_empty
 */
add_action ('woocommerce_add_to_cart', 'lenura_empty_cart_before_add', 0);

function lenura_empty_cart_before_add() {
    global $woocommerce;

    // Get 'product_id' and 'quantity' for the current woocommerce_add_to_cart operation

qant

//Woocommerce Checkout JS events
$( document.body ).trigger( 'init_checkout' );
$( document.body ).trigger( 'payment_method_selected' );
$( document.body ).trigger( 'update_checkout' );
$( document.body ).trigger( 'updated_checkout' );
$( document.body ).trigger( 'checkout_error' );

//Woocommerce cart page JS events
$( document.body ).trigger( 'wc_cart_emptied' );
$( document.body ).trigger( 'update_checkout' );

qant

<?php

// Get headers for 100 unique random domains with get_headers() and cURL to determine which is faster.

/*
TL;DR -> cURL is significantly faster.

get_headers (GET) vs cURL:
Execution time : 139.95884609222 seconds  
Execution time : 65.998840093613 seconds

qant

<div id="google_translate_element"></div>
<script> 
function googleTranslateElementInit() {
  new google.translate.TranslateElement({
    pageLanguage: 'en'
  }, 'google_translate_element');
}
</script>
<script src="http://translate.google.com/translate_a/element.js?cb=googleTranslateElementInit"></script>