Author(s): Prisca Ekhaeyemhe

Originally published on Towards AI.

A practical guide to choosing between prompting, RAG, and fine-tuning from someone who learned the hard way.

This year, I’ve spent a lot of time learning about Large Language Models (LLMs) and building applications powered by them. Like many people diving into this space, I was excited to apply what I’d learned, especially about Retrieval-Augmented Generation (RAG). My first instinct? Build a sophisticated RAG-powered app. Non-members can read it here.

The article shares insights gained from testing and learning about Large Language Models (LLMs), focusing on the importance of simplicity and practicality in approach. It emphasizes three techniques: Prompt Engineering, Retrieval-Augmented Generation (RAG), and Fine-Tuning, discussing their pros and cons, and when to use each. The author reflects on their own journey, advocating for starting with the simplest methods before resorting to more complex strategies, allowing the specific business problem to dictate the solution.

Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI