Ndamulelo Nemakhavhani ndamulelonemakh

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.

How to get Telegram Bot Chat ID

Content :

Create a Telegram Bot and get a Bot Token
Get Chat ID for a Private Chat
Get Chat ID for a Channel
Get Chat ID for a Group Chat
Get Chat ID for a Topic in a Group Chat

Create a Telegram Bot and get a Bot Token

Handling Line Endings: Windows, WSL2, and Ubuntu

When working on different operating systems, managing line endings is crucial to ensure consistency and avoid issues in a collaborative development environment. Here are the recommendations for configuring Git to handle line endings on Windows, WSL2, and Ubuntu:

1. Windows:

Recommended Setting: core.autocrlf true
Command:
```
git config --global core.autocrlf true
```

	import random

	# -------------------------------
	# Simulated Agent Tools
	# -------------------------------
	class ResearchAgent:
	def run(self, topic, sources_required=3):
	print(f"[ResearchAgent] Researching: {topic} (need {sources_required} sources)")
	return f"Research data about {topic} from {sources_required} sources"

	include api_backends.conf;
	include api_keys.conf;

	limit_req_zone $binary_remote_addr zone=client_ip_10rs:1m rate=1r/s;
	limit_req_zone $http_apikey zone=apikey_200rs:1m rate=200r/s;

	server {
	access_log /var/log/nginx/api_access.log main; # Each API may also log to a
	# separate file

	#!/bin/bash
	set -e

	# Pre-requisite:
	# Generate your token at: https://github.com/settings/tokens/new?scopes=write:packages
	# More info: https://docs.github.com/en/packages/working-with-a-github-packages-registry/working-with-the-container-registry

	export CR_PAT=<YOUR_TOKEN>
	GITHUB_USERNAME=<your-github-account-name>
	echo $CR_PAT \| docker login ghcr.io -u $GITHUB_USERNAME --password-stdin

	FROM node:lts-alpine as build


	WORKDIR /app
	COPY package*.json ./

	# Install dependencies
	RUN npm ci --force
	COPY . .

	# Official reference: https://swagger.io/specification/

	openapi: "3.0.0" # The version of the OpenAPI Specification being used
	info: # Metadata about the API
	version: "1.0.0" # Version of the API
	title: "Sample API" # Name of the API

	servers: # Base URL and other server information
	- url: "http://api.example.com/v1"

	from flask import Flask, render_template, request, redirect

	app = Flask(__name__)
	todos = []

	@app.route('/')
	def index():
	return render_template('index.html', todos=todos)

	@app.route('/add', methods=['POST'])

	<!DOCTYPE html>
	<html lang="en">
	<head>
	<meta charset="UTF-8" />
	<meta name="viewport" content="width=device-width, initial-scale=1.0" />
	<title>Native HTML PDF Preview</title>
	</head>
	<body>
	<div style="display: block; height: 900px; background-color: aqua;">
	<object