[Webinar] Shift Left to Build AI Right: Power Your AI Projects With Real-Time Data | Register Now
GenAI is here, but where’s it going next?
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.
Here’s what’s trending in artificial intelligence now.
How to Build RAG Using Confluent with Flink AI Model Inference and MongoDB
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.
How to Build GenAI apps Faster with Confluent’s Connectors
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.
Get started with the basics of LLMs, vector databases, and AI.
Weiteres und Ressourcen
RAG mit Daten-Streaming: Ein Guide für Entwickler
Wie Retrieval-Augmented Generation (RAG) für Echtzeit-GenAI-Anwendungen mit der Daten-Streaming-Plattform von Confluent effektiv aufgebaut und skaliert werden kann. Connectors, Flink und Stream Governance können für vier Grundbausteine von RAG genutzt werden: Datenanreicherung, Inferenz, Workflows und Post-Processing.