Developing Large Language Models for Cyber Applications

Get an inside look at RAG with our step-by-step tutorial presented by Software Engineer Bradley Hartlove. Learn how to build smarter LLM applications without the complexity.

As a Software Engineer at SealingTech, I know firsthand that training large language models (LLMs) can be expensive, not to mention overwhelming with the countless libraries, guides, and resources that are out there. It’s why I created a two-part video series featuring 4 tutorials designed to help fellow engineers in the cyber community get up and running on building generative AI applications without dealing with the expense, training, or research.

If you missed the first two tutorials: Introduction to Building LLM Applications and Inference Engines and Prompting Techniques:

In this next part, we’re going to dive into retrieval augmented generation (RAG) as a method that allows you to inject new knowledge into your model without having to formally undergo training or extensive research. And in the final tutorial, we’ll get into the nuts and bolts of building actual LLM agents.

Let’s continue on to the next two video tutorials.

RAG from Scratch

In this video, you’ll explore:

• Overview of Embeddings
• How to Ingest Documents
• Building a simple RAG pipeline

Building LLM Agents

In this video, you’ll learn:

• Defining Agent Tools
• Building an Agentic Loop

I hope you found these tutorials helpful in gaining a foundational understanding of what LLMs are and how to successfully implement them into your applications.

Interested in continuing the conversation? Follow us on Instagram, Facebook, X, and LinkedIn. To see more of SealingTech’s helpful videos, subscribe to our YouTube Channel.