Workshop: Introduction to RAG

Bring your laptop and join us for a hands-on workshop on Retrieval-Augmented Generation (RAG).

Retrieval-Augmented Generation (RAG) enhances LLMs by grounding them in external sources of knowledge. When you submit a query, RAG retrieves relevant information in real time and feeds it directly to the LLM as context for a more accurate response.

In this workshop, we will:

• Walk through the core concepts of RAG (15 mins)
• See how it works through a demo (15 mins)
• Build your RAG application with Foundry Local (1 hour)

Please come prepared with:

• A laptop
• Internet access (hotspot or ethernet cable)
• VS Code with C# Dev Kit extension
• .NET 10.0 SDK installed
• Foundry Local installed