bobvanluijt

🌳 Evolution of NLP: From Word2Vec to GPT-5

An overview of how natural-language modeling evolved from statistical embeddings to modern large language models.

---

🕰️ Historical Overview

Early NLP (Pre-2010)
│

bobvanluijt

# Assumes Ubuntu 22.04
$ sudo apt-get update && \
  sudo apt-get -y install gcc && \
  wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-ubuntu2204.pin && \
  sudo mv cuda-ubuntu2204.pin /etc/apt/preferences.d/cuda-repository-pin-600 && \
  wget https://developer.download.nvidia.com/compute/cuda/12.3.1/local_installers/cuda-repo-ubuntu2204-12-3-local_12.3.1-545.23.08-1_amd64.deb && \
  sudo dpkg -i cuda-repo-ubuntu2204-12-3-local_12.3.1-545.23.08-1_amd64.deb && \
  sudo cp /var/cuda-repo-ubuntu2204-12-3-local/cuda-*-keyring.gpg /usr/share/keyrings/ && \
  sudo apt-get update && \
  sudo apt-get -y install cuda-toolkit-12-3 nvidia-cuda-toolkit python3-pip nvtop && \

bobvanluijt

const weaviate = require("weaviate-ts-client");

// Create a secret based on the API key
const apiKey = new weaviate.ApiKey("4jne...9me1");

// Create client objects
const client = weaviate.client({
  scheme: 'https',
  host: 'your-cluster.weaviate.network',
  apiKey: apiKey,

bobvanluijt

import weaviate

# Set the Weaviate URL
url = "https://your-cluster.weaviate.network"

# Create a secret based on the API key
my_secret_key = weaviate.AuthApiKey(api_key="4jne...9me1")

# Create client objects
client = weaviate.Client(url, auth_client_secret=my_secret_key)

bobvanluijt

$ curl \
    -H "Authorization: Bearer 4jne...9me1" \
    https://your-cluster.weaviate.network/v1/meta

bobvanluijt

{
  "id": "9f683bbb-a826-11eb-8c6c-e778e9b30943",
  "url": "https://hcicolombo.gov.in/pages?id=eyJpdiI6IkgzT1ZLY2ZPOWNKMXNOZWZydlwvNkRBPT0iLCJ2YWx1ZSI6IkJzMUpBYlhURjVaMENkZ2thY09ncVE9PSIsIm1hYyI6ImJjZTM4NjM5NTFkNGU3MjEzM2IwMDYyZjdmY2QwNTUwN2IyYWFkMjQ1Y2ViYWFmNjdjOWIxNGVjYjY4ZmVmYWYifQ==&subid=eyJpdiI6InB1NysxYXFCK0hxWlNTQXBoMm9mcWc9PSIsInZhbHVlIjoieDl2V1BhWktSNGU4aUxPZWN4akhmQT09IiwibWFjIjoiYzFlODU1NTRmZDI2MmFjZTE4NzZiMzdjODcyODMzNTA0MjU1ZmY1OGIyYjBhMTg5MzM5NjVkM2NhMjFkY2U5NCJ9",
  "title": "Welcome to High Commission of India, Colombo, Sri Lanka",
  "sha": "sha1:LFWBZ4WVRD5AGSI42HZJ57BLQYIG6CQF",
  "raw": "Welcome to High Commission of India, Colombo, Sri Lanka Affairs Minister Smt. Sushma Swaraj led an inter-ministerial delegation to Colombo from 5-6 February 2016 for the 9th Session of the India-Sri Lanka Joint Commission. Earlier, External Affairs Minister Smt. Sushma Swaraj was in Colombo on 6-7 March 2015 to prepare for Prime Minister’s visit. EAM visited from 31 August-01 September 2017 to attend the s

bobvanluijt

##
# Read only Weaviate config.
# Update the comments in the config file below
#
# The setup assumes that Nginx can find the Weaviate instance
# or cluster on http://weaviate-server:4001 (this can be updated)
#
##
server {
    listen 4000 default_server;       # port 4000 is where the nginx config listens to

bobvanluijt

{
  Get {
    Paragraph(
      nearText: {
        concepts: ["jazz saxophone players"]
      }
      limit: 25
    ) {
      content
      order

bobvanluijt

{
  Get {
    Paragraph(
      ask: {
        question: "What was Michael Brecker's first saxophone?"
        properties: ["content"]
      }
      where: {
        operator: Equal
        path: ["inArticle", "Article", "title"]

bobvanluijt

{
  Get {
    Paragraph(
      nearText: {
        concepts: ["Italian food"]
      }
      limit: 50
    ) {
      content
      order