RICH0423

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.

RICH0423

Dev K8s Networking on MacOS

Context

Unlike Linux on MacOS Docker runs inside VM. This causes issues when trying to access containers directly as their IP is not reachable from host network. It is especially annoying when trying to get a local development environment for K8s.

This short guides aim to solve the problem. Solution is: https://github.com/chipmk/docker-mac-net-connect

RICH0423

package com.rich.gcp.app;

import com.google.api.client.http.GenericUrl;
import com.google.api.client.http.HttpRequest;
import com.google.api.client.http.HttpResponse;
import com.google.api.client.http.HttpTransport;
import com.google.api.client.http.javanet.NetHttpTransport;
import com.google.api.gax.core.CredentialsProvider;
import com.google.auth.http.HttpCredentialsAdapter;
import com.google.auth.oauth2.GoogleCredentials;

RICH0423

import psycopg2

#establishing the connection
conn = psycopg2.connect(
   database="postgres", user='postgres', password='12345678', host='127.0.0.1', port= '5432'
)
#Creating a cursor object using the cursor() method
cursor = conn.cursor()

#Executing an MYSQL function using the execute() method

RICH0423

docker run -d \
  -h redis \
  -e REDIS_PASSWORD=passw0rd \
  -v redis-data:/data \
  -p 6379:6379 \
  --name redis \
  --restart always \
  redis:6.2.6-alpine /bin/sh -c 'redis-server --appendonly yes --requirepass ${REDIS_PASSWORD}'

RICH0423

package com.rich.stream.example;

import org.apache.kafka.common.serialization.Serdes;
import org.apache.kafka.common.utils.Bytes;
import org.apache.kafka.streams.KafkaStreams;
import org.apache.kafka.streams.StreamsBuilder;
import org.apache.kafka.streams.StreamsConfig;
import org.apache.kafka.streams.Topology;
import org.apache.kafka.streams.kstream.KeyValueMapper;
import org.apache.kafka.streams.kstream.Materialized;

RICH0423

package main

import (
    "fmt"
)

// fibonacci is a function that returns
// a function that returns an int.
func fibonacci() func() int {
    prev1, prev2 := 0, 1

RICH0423

apiVersion: apps/v1
kind: Deployment
metadata:
  name: nginx-deployment  # Deployment name
spec:
  selector:  # defines how the Deployment finds which Pods to manage
    matchLabels:
      app: nginx
  replicas: 2
  template:    # The Pods are labeled app:nginx using the labels field

RICH0423

import java.util.Arrays;
import java.util.List;
import java.util.stream.Collectors;
import java.util.stream.IntStream;

public class Array2ListDemo {

	public static void main(String[] args) {

		/**** Converting a Primitive 'int' Array to List ****/

RICH0423

@EnableWebSecurity
public class WebSecurityConfig extends WebSecurityConfigurerAdapter {

	@Override
	protected void configure(HttpSecurity http) throws Exception {
		http
			// by default uses a Bean by the name of corsConfigurationSource
			.cors().and()
			...
	}