23.01.25, online
LiveWebinar 3.01 Production-ready RAG with Azure AI Search
This session demonstrates how to build a production-ready Retrieval Augmented Generation (RAG) application to chat over your domain’s data with Azure AI Search.
Thursday, 23rd January 2025
14:15 – 15:00
Mélony Qin
Microsoft
Learn how to build a production-ready Retrieval Augmented Generation (RAG) application to chat over your domain’s data with Azure AI Search. Discover the benefits of hybrid search with semantic ranker to find both vector and keyword-based results amongst billions of documents. Explore different approaches to data ingestion, to extract, split, vectorize, and store your data in Azure AI Search. Consider multiple ways to evaluate your RAG app answers, to ensure high-quality responses. Finally, see how you can productionize your RAG app with efficient vector storage, private network deployment, and user authentication.
Key takeaways for this session are
- Basics of vector embeddings and vector search strategies
- Azure AI Search option: full-text search, vector search, hybrid search, semantic ranker
- Data ingestion process for Azure AI Search, manual and integrated vectorization feature
- Evaluation strategies for RAG app answers: AI Studio, Promptflow-evals SDK
- Efficient vector storage with quantization
- Security best practices: private network deployment, user authentication, data access control
Speaker details
Mélony is a technology specialist at Microsoft, a CNCF Ambassador, and a member of the current release team for the Kubernetes SIG release. She is the author of four books, including Azure Integration Guide for Business, The Kubernetes Workshop, Certified Kubernetes Administrator (CKA) Exam Guide, and Microsoft Azure Infrastructure, all published by Packt Publishing.
Mélony has a passion for cloud-native and AI technologies and runs the Cloud Native Innovators newsletter and blogs on cvisiona.com and her YouTube channel, CVisiona. She is committed to helping customers and partners worldwide succeed in the cloud-native and AI space.
Jetzt anmelden!