Venkatt Guhesan vguhesan

RAG Implementation Example

requires internet access and tools

A simple RAG system over a text document using LangChain, OpenAI for embeddings/LLM, and Chroma as the vector DB.

Install packages

Make sure Ollama is running with llama3: ollama pull llama3 && ollama run llama3
Have SingleStore running locally (Docker example): docker run -d -p 3306:3306 --name singlestore singlestore/cluster-in-a-box (create the database rag_db manually or let the script handle it)
Install dependencies (once):Bash pip install llama-index llama-index-embeddings-ollama llama-index-llms-ollama llama-index-vector-stores-singlestore singlestoredb
Update the CONFIGURATION section with your paths/credentials.
python rag_pipeline.py

Python Humanize timedelta without Arrow or Humanize library

Given 2 dates that are formatted from a string to arrow type.

>>> from datetime import datetime 
>>> start = datetime.now()
>>> end = datetime.now()
>>> diff = end - start

	// ==UserScript==
	// @name Grok Wide Output Results Panel
	// @namespace http://digitalriver.blog/grok-wide-output
	// @version 2026-02-16
	// @description Makes the Grok Results Output be wider
	// @author Venkatt Guhesan
	// @match https://grok.com/
	// @icon https://grok.com/images/favicon.ico
	// @grant none
	// ==/UserScript==

	// Run me in a developer JavaScript Console
	// Need to place this in a TamperMonkey UserScripts soon

	var targetElem = document.querySelector('html > body > div:nth-of-type(2) > div:nth-of-type(2) > div > div > main > div:nth-of-type(2)');
	targetElem.style.setProperty("--content-max-width", "70rem");

	#!/bin/bash

	# Delete all node_modules directories recursively
	find . -type d -name "node_modules" -print0 \| xargs -0 rm -rf

	echo "All node_modules directories deleted."


	#!/usr/bin/env bash

	# qrc.sh
	# Generate qrcode of a url and display it in an Edge browser on Windows
	# This script depends on https://github.com/skip2/go-qrcode


	# Debug Options
	# Toggle the echo variable assignment to either ":" (nop) or "echo"