Curious about building cutting-edge RAG (retrieval-augmented generation) systems but unsure where to start? Join me for a hands-on talk where we’ll dive into using NVIDIA NIM microservices to create scalable, high-performance RAG applications.
Part of NVIDIA AI Enterprise, NIM microservices offer fast, secure deployment of AI models in any environment. NIM Retriever is one such solution that includes models for text embedding and reranking. It can be used with different vector stores and integrated with multiple frameworks. In this session, we will show you how to easily build a RAG workflow with NIMs from scratch, and integrate it to create a functional chatbot.
Technical Level: Technical practitioner
Supported by
