Tag: rag

This tutorial provides a comprehensive, step-by-step approach to implementing Retrieval-Augmented Generation (RAG) for enhanced data analytics. It covers essential aspects from data preparation and vectorization to retrieval optimization and prompt engineering, ensuring accurate, secure, and insightful results for enterprise data analytics.

The NVIDIA AI Red Team has identified three paramount security vulnerabilities in Large Language Model (LLM) applications: remote code execution via LLM-generated code, data leakage through insecure access controls in RAG systems, and data exfiltration via active content rendering of LLM outputs. This analysis details these risks and outlines NVIDIA's recommended countermeasures to fortify LLM implementations.

This tutorial explores how Retrieval-Augmented Generation (RAG) significantly improves the quality and safety of local Large Language Models (LLMs) in radiology contrast media consultations. We delve into the methodology, performance improvements, and practical implications for healthcare institutions seeking privacy-preserving AI solutions.

This tutorial explores building knowledge graphs using Relik and LlamaIndex for efficient entity linking and relationship extraction, offering a cost-effective alternative to LLMs for RAG applications.