Building RAG at scale with Semantic Kernel and DataStax Astra DB
Many organizations struggle to build scalable, intelligent systems that can not only retrieve but also generate relevant information in real time. Creating retrieval augmented generation (RAG) systems is often complex, requiring expertise in both data integration and AI.
In this demo session, we’ll showcase how we built WikiChat, a real-time RAG-based chatbot for Wikipedia, using Microsoft Semantic Kernel, DataStax Astra DB, and Azure OpenAI. Learn how you can streamline development and enhance your ability to create dynamic, responsive applications that meet the needs of today’s users.
Watch this webinar to learn:
In this demo session, we’ll showcase how we built WikiChat, a real-time RAG-based chatbot for Wikipedia, using Microsoft Semantic Kernel, DataStax Astra DB, and Azure OpenAI. Learn how you can streamline development and enhance your ability to create dynamic, responsive applications that meet the needs of today’s users.
Watch this webinar to learn:
- Introduction to building retrieval augmented generation (RAG)-based apps on Semantic Kernal and Astra DB
- How to effectively leverage Azure OpenAI for creating embeddings
- How to effectively scale real-time applications for rapidly changing data sources, such as Wikipedia
© 2024 DataStax