Post Content
​ With the ever-growing list of large language models (LLMs) available in Generative AI Hub, selecting the best one for specific use cases can be a daunting task. This talk delves into our process of evaluating LLMs for running our use-case, Joule on the SAP Design System, focusing on three critical metrics: accuracy in answering questions, response speed, and query cost. Through this talk, we’ll explore how we need to balance the needs of expert users and community members while addressing the demand for rapid, cost-effective, and accurate responses.
Speaker: Joerg Goeppert and Hee Tatt Ooi, SAP   Read More SAP DevelopersÂ
#SAP
