Learn how to integrate large language models (LLMs) with NVIDIA Inference Microservices (NIM) and cuGraph to create cutting-edge, graph-based AI solutions for handling complex, interconnected data. We'll cover fine-tuning techniques, Langchain agents, and GPU-accelerated graph analytics to enhance AI capabilities and retrieval-augmented generation (RAG) evaluation. Prerequisite(s):
Generative AI knowledge about LLMs and RAG. Understanding of vector-based RAG and embedding vectors.
活动: GTC 25
日期: March 2025
行业: 金融服务
话题: Generative AI - Retrieval-Augmented Generation (RAG)