Skip to content

Instantly share code, notes, and snippets.

View tosin2013's full-sized avatar

Tosin Akinosho tosin2013

View GitHub Profile

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.

@dlbewley
dlbewley / login-pull-secrets.sh
Created November 2, 2022 22:34
Podman login to all registries in pull secret
# if you don't want to just use --authfile or set REGISTRY_AUTH_FILE for whatever reason
# you may login to each registry in your pull secret thusly
# spoiler alert, here's how to extract usernames and passwords from your pull secret
PULL_SECRET_PATH=pull-secret.json
for R in $(jq -r '.auths|keys[]' $PULL_SECRET_PATH ); do
echo "Logging into $R"
U=$(jq -r ".auths.\"$R\".auth" $PULL_SECRET_PATH | base64 -d | awk -F: '{print $1}')
P=$(jq -r ".auths.\"$R\".auth" $PULL_SECRET_PATH | base64 -d | awk -F: '{print $2}')
@tosin2013
tosin2013 / configure-rhel9.x.sh
Last active September 19, 2025 15:38
configure-rhel9.x.sh
#!/bin/bash
set -xe
CHECKLOGGINGUSER=$(whoami)
if [ ${CHECKLOGGINGUSER} == "root" ];
then
echo "login as sudo user to run script."
echo "You are currently logged in as root"
exit 1
fi
@acsulli
acsulli / openshift_authn_authz.md
Created July 1, 2021 19:59
Supporting information for the OpenShift.tv live stream here: https://www.youtube.com/watch?v=RG6xt2q72nw

Configuring Active Directory authentication with OpenShift 4

  1. Understand AD LDAP structure and naming. Read the docs on the components

    Refer to the OpenShift docs for the LDAP identity provider and LDAP group syncing.

  2. Create the OAuth config

    # create a secret for the bindDN user password
@tosin2013
tosin2013 / configure-sudo-user.sh
Created June 27, 2021 19:01
Configure Sudo user
#!/bin/bash
set -xe
if [ -z $1 ];
then
echo "Please pass user to be created."
echo "USAGE: $@ username"
exit 1
fi
USER=${1}
@cdoan1
cdoan1 / 00_setup_local_mirror_registry.sh
Last active October 7, 2021 17:35
disconnected downstream
#!/bin/bash
#
# Reference: https://www.openshift.com/blog/openshift-4-2-disconnected-install
#
HOSTNAME=`hostname`
USERNAME=admin
PASSWORD=password
yum -y install podman httpd httpd-tools
mkdir -p $(pwd)/registry/{auth,certs,data}
@tosin2013
tosin2013 / utilities-pod.md
Last active February 20, 2026 15:07
utilities-pod.md

Deploying a Simple Utility Service in OpenShift

This document outlines the steps for deploying a basic utility service in OpenShift using the oc command-line tool and Docker images.

What it does

This script creates a deployment for a service named utilities with the following functionalities:

  • Runs the fedora:latest Docker image.
  • Installs essential utilities like nc, wget, curl, bind-utils, iputils, net-tools, and telnet.
@dmesser
dmesser / standalone-kubelet-fc31.md
Last active March 5, 2023 13:10
Standalone Kubelet on Fedora 31

What is this about?

This gist describes how to set up standalone kubelet + CRI-O + CNI on Fedora Core 31. The goal is to place a Kubernetes Pod manifest on an single node and access the application from the network. This guide has been tested on x86-64 and armv7 deployments.

Prepare the system

Make sure the system is up to date:

dnf -y update

OCP 4.2/4.3 All-In-One (UPI mode)

This document assume reader is familiar with the OCP4x installation process.

Before Deployment

  • Setup the install-config.yaml to deploy a single master and no workers
    apiVersion: v1
    baseDomain: example.com