- AI Engineering
- Posts
- Hands-On Large Language Models
In today’s newsletter:
Hands-On Large Language Models – Notebook Examples Repository
Open Source Browser using Agent
Turn any website into LLM-ready data with just a few clicks
Reading time: 2 minutes.
This repository contains the complete code examples from the book Hands-On Large Language Models.
It includes notebook examples that cover everything from the introduction to language models to fine-tuning them.
Chapter 1: Introduction to Language Models
Chapter 2: Tokens and Embeddings
Chapter 3: Looking Inside Transformer LLMs
Chapter 4: Text Classification
Chapter 5: Text Clustering and Topic Modeling
Chapter 6: Prompt Engineering
Chapter 7: Advanced Text Generation Techniques and Tools
Chapter 8: Semantic Search and Retrieval-Augmented Generation
Chapter 9: Multimodal Large Language Models
Chapter 10: Creating Text Embedding Models
Chapter 11: Fine-tuning Representation Models for Classification
Chapter 12: Fine-tuning Generation Models
If you're trying to understand how LLMs are actually used in the real world, this notebook examples are worth checking out.
Turn the internet into an agent-friendly environment and websites into structured, navigable maps just using natural language!
Notte provides a full-stack web AI agents framework, allowing you to develop, deploy, and scale your own agents with a single API.
Key Features:
Browser Sessions: On-demand headless browsers with proxy config, CDP, cookie integration, and session replay.
Run Automated LLM Agents: Solve complex web tasks.
Observe, Step, Scrape: Use natural language to observe website states and execute actions with granular control.
Secrets Vault: Enterprise-grade credential management for Sessions & Agents.
Fast, reliable, and high success rates. Full code & replays are public.
Notte also leads the benchmarks with 96.6% task reliability and 47s time per task.
It’s 100% Open Source.
Firecrawl released Templates, a collection of ready-to-use playground setups, code snippets, and full repositories to scrape and structure web data for your projects.
You can run them instantly using Replit.
Key Templates Include:
Playground Templates: Pre-configured Firecrawl setups for crawling websites and scraping JavaScript-heavy pages.
Code Snippets: Reusable code segments you can drop into your own applications.
Complete Repositories: Full applications with one-click Replit integration, like Open Deep Research and Trend Finder.
Getting web data just got a lot easier.
templates
That’s a Wrap
That’s all for today. Thank you for reading today’s edition. See you in the next issue with more AI Engineering insights.
PS: We curate this AI Engineering content for free, and your support means everything. If you find value in what you read, consider sharing it with a friend or two.
Your feedback is valuable: If there’s a topic you’re stuck on or curious about, reply to this email. We’re building this for you, and your feedback helps shape what we send.
WORK WITH US
Looking to promote your company, product, or service to 120K+ AI developers? Get in touch today by replying to this email.