During its operational lifespan, equipment used in chemical, mechanical, and metallurgical process plants is subjected to various degradation mechanisms, including corrosion, erosion, fatigue, and deformation. These factors can severely impact equipment integrity, increasing the likelihood of failure. While complete elimination of failures is impractical, an effective asset management program focuses on maximizing reliability and availability through well-structured inspection and maintenance strategies. However, developing and implementing such programs is complex and costly. Risk-based approaches, such as Risk-Based Inspection (RBI) and Reliability-Centered Maintenance (RCM), offer systematic methods to optimize resource allocation and minimize accident risks. Failure Modes and Effects Analysis (FMEA) is a widely used technique for risk assessment. Primarily qualitative, FMEA can incorporate quantitative elements by estimating failure likelihood and consequences. While benefiting from human expertise, traditional FMEA is often criticized for being time-intensive, prone to human error, and inherently static. Recent advancements in Generative AI have opened avenues for automating the FMEA process. A current project is developing a framework that combines open-source Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) to automate the creation of FMEA/FMECA tables using only pre-vetted, credible documents. At the proof-of-concept (PoC) stage, the project has shown promising results in automating failure analysis. This paper introduces the proposed framework and presents initial findings.