Exercise 03 - Evaluating and Deploying LLMs
Scenario
In this exercise, you will be using the chat flows within Azure AI Foundry to evaluate and test your large language models (LLMs). This exercise is critical for Lamna Healthcare Company as it aims to create a robust 24/7 support virtual agent that can efficiently manage customer interactions without hallucinations and off topic responses.
By achieving these objectives, Lamna’s team will enhance their understanding and practical skills in deploying and managing conversational AI solutions using Azure AI Foundry, tailored to their specific healthcare service needs.
Objectives
After you complete this exercise, you will be able to:
- Evaluate your Chat flow
- Deploy a RAG flow.
Lab Duration
- Estimated Time: 60 minutes