Mikk is an Estonian software developer who began his career in 2011, initially focusing on macOS and iOS applications. Over the years, he developed a variety of applications, including those for salary management and vehicle telematics, showcasing his proficiency in Swift and Apple platform development.
In recent years, Mikk pivoted towards BE development, embracing Elixir as his primary language. He’s built numerous microservices using Elixir, leveraging technologies like Kafka to manage data flow and system communications effectively. This shift signifies his growing interest in functional languages and system design.
Mikk’s journey in software development has been marked by an inclination towards machine learning (ML). He’s experimented with various ML frameworks and tools to explore the potential of artificial intelligence in software solutions. These forays into ML reflects his curiosity and commitment to staying at the forefront of technological advancements.
You’ve mastered the “Hello World” of Large Language Models (LLMs) and are eager to expand your skills to build a real application. However, you quickly realize that basic knowledge is not enough.
This journey involves numerous steps, including selecting the right model, data gathering, fine-tuning, retrieval methods and embeddings that enhance the performance and quality of your application.
In this talk, we will focus on a retrieval method called approximate nearest neighbors (ANN): what they are, how to use them, and how to integrate them with other LLMs like OpenAI and LLaMA2. The goal is to improve the quality of responses while minimizing costs and overcome the techincal limitation that LLM have.
This presentation will be conducted in a Livebook notebook.