From the course: No-Code Generative AI for Business Professionals

Unlock the full course today

Join today to access over 24,700 courses taught by industry experts.

Fine-tuning and retrieval augmented generation (RAG)

Fine-tuning and retrieval augmented generation (RAG) - ChatGPT Tutorial

From the course: No-Code Generative AI for Business Professionals

Start my 1-month free trial Buy for my team

Fine-tuning and retrieval augmented generation (RAG)

“

- [Instructor] Fine tuning and retrieval augmented generation, or RAG, are two approaches to build GenAI chatbots using your own company data. Enterprise customers and startups, or IT consulting companies fine-tune foundation models with the small dataset using what is called semi-supervised learning. For example, a travel company may use its past documents from customer support records to fine-tune a model that teaches the AI the terminology used by customers in the travel industry, as well as documentation or promotional material related to travel products, and also set the right professional tone to truly engage with customers. Then an intelligent customer support chatbot application can be built upon this fine-tune model. Remember the three steps of the 1-2-3 framework from earlier? To build generative AI products, we always start with the business problem. Now we'll map to the data using fine-tuning, and then map to the GenAI capabilities to build applications. So now I'm going…

Contents