RAG pipelines, evaluation and safe deployment

AI-103 · Build generative AI apps · Updated

Build grounded RAG apps with Azure AI Search, tune retrieval quality, and evaluate groundedness and relevance with Foundry evaluators.

This lesson is part of full AI-103 access

The first 2 AI-103 lessons are free. Full access opens every lesson with its practice questions, and the exam-style AI-103 question bank.

In this lesson
  • The RAG flow
  • Retrieval choices
  • Evaluation
  • Improve answers in code
  • Exam traps
  • Practice questions

Get full access Try the free practice exam Log in

AI-103 course outline

All 8 lessons · Course overview
  1. Foundry resources, projects and connectionsPlan and manage an Azure AI solution Free
  2. Responsible AI and Content SafetyPlan and manage an Azure AI solution Free
  3. Prompting, parameters and multimodal requestsBuild generative AI apps Full access
  4. RAG pipelines, evaluation and safe deploymentBuild generative AI apps Full access
  5. Foundry Agent Service, tools and memoryBuild agents Full access
  6. Agent workflows and observabilityBuild agents Full access
  7. Azure AI Search indexing, skillsets and securityImplement vision, language and search solutions Full access
  8. Choosing Vision, Speech, Language and Document servicesImplement vision, language and search solutions Full access