Shikhar Kwatra from AWS shares his work on enabling generative AI at scale, including fine-tuning and deploying LLMs for production use cases like chatbots and knowledge discovery. He highlights the growing synergy between knowledge graphs and LLMs for fine-tuning models, improving accuracy, and addressing production-level challenges. Shikhar also discusses the rapid advancements in Retrieval-Augmented Generation (RAG) techniques and their practical applications, as well as AWS solutions like Amazon Bedrock and SageMaker for scaling AI workloads efficiently. Stay tuned for his upcoming book, Generative AI with Amazon Bedrock, which dives into these innovations and more!
Neo4j devhub: https://bit.ly/4ghZuIk