Generative AI is already changing the way we work, but how can we change the way GenAI works? See where large language models (LLMs) and GenAI are today and where better data can take them tomorrow.
In this GenAI tutorial webinar by Confluent and MongoDB, you’ll learn how to build retrieval-augmented generation (RAG) in 4 key steps: data augmentation, inference, workflows, and post-processing. See a step-by-step walkthrough of vector embedding and get all your questions answered in a live Q&A.
In this demo webinar, you’ll learn about building a real-time knowledge base for RAG architecture. We’ll show you how to configure a source connector to bring in data from various sources, Flink SQL for vector embedding, and sink connector to send data to vector stores like MongoDB Atlas Vector search.