This workshop focuses on effectively transitioning Language Modeling (LLM) applications to production. Participants will learn key processes such as generating synthetic test data using Azure OpenAI, optimizing data retrieval with VectorDB, and evaluating LLM applications. In addition, the workshop covers local testing, monitoring, tracing and integration of Recovery Augmented Generation (RAG) with Azure AI search, as well as testing and automation strategies.

Agenda

• Generating Synthetic Test Data Using Azure OpenAI
• Optimizing Data Retrieval with VectorDB
• LLM Application Evaluation
• Local Testing
• LLM Application Monitoring and Tracing
• RAG with Azure AI Search
• Testing and Automation for LLM Applications

After the presentation, you'll have the opportunity to book a follow-up meeting with the Microsoft team - sign up!