In this session, Yaron Haviv, CTO Iguazio was joined by Ehud Barnea, PHD, Head of AI at Tasq.ai and Guy Lecker ML Engineering Team Lead, Iguazio to discuss how to validate, evaluate and fine tune an LLM effectively. They shared firsthand tips of how to solve the production hurdle of LLM evaluation, improving LLM performance, eliminating risks, along with a live demo of a fashion chatbot that leverages fine-tuning to significantly improve the model responses.

Iguazio would like to introduce two practical demonstrations showcasing our call center analysis tool and our innovative GenAI assistant. These demos illustrate how our GenAI assistant supports call center agents with real-time advice and recommendations during customer calls. This technology aims to improve customer interactions and boost call center efficiency. We're eager to share how our solutions can transform call center operations.

Many enterprises operate expansive call centers, employing thousands of representatives who provide support and consult with clients, often spanning various time zones and languages. However, the successful implementation of a gen AI-driven smart call center analysis applications presents unique challenges such as data privacy controls, potential biases, AI hallucinations, language translation and more.

Nuclio is a high-performance serverless framework focused on data, I/O, and compute intensive workloads. It is well integrated with popular data science tools, such as Jupyter and Kubeflow; supports a variety of data and streaming sources; and supports execution over CPUs and GPUs. The Nuclio project began in 2017 and is constantly and rapidly evolving; many start-ups and enterprises are now using Nuclio in production. In this video, Tomer takes you through a quick demo of Nuclio, triggering functions both from the UI and the CLI.

Generative AI has sparked the imagination with the explosion of tools like ChatGPT, CodePilot and others, highlighting the importance of LLMs as the basis for modern AI applications. However, implementing GenAI in the enterprise is challenging, and it becomes even more difficult for banks, insurance companies, and other financial services companies. Many Financial Service companies are struggling and end up missing out on the great value of GenAI and the competitive edge it can provide.

In this MLOps Live session, Gennaro, Head of Artificial Intelligence and Machine Learning at Sense, describe how he and his team built and perfected the Sense chatbot, what their ML pipeline looks like behind the scenes, and how they have overcome complex challenges such as building a complex natural language processing ( NLP) serving pipeline with custom model ensembles, tracking question-to-question context, and enabling candidate matching.

In this session, Yaron Haviv, CTO Iguazio was joined by Nayur Khan, Partner, QuantumBlack, AI by @McKinsey and Mara Pometti​, Associate Design Director, McKinsey & Company to discuss how enterprises can adopt GenAI now in live business applications. There was a very engaging Q&A session with many relatable questions asked.

The influx of new tools like ChatGPT spark the imagination and highlight the importance of Generative AI and foundation models as the basis for modern AI applications. However, the rise of generative AI also brings a new set of MLOps challenges. Challenges like handling massive amounts of data, large scale computation and memory, complex pipelines, transfer learning, extensive testing, monitoring, and so on. In this 9 minute demo video, we share MLOps orchestration best practices and explore open source technologies available to help tackle these challenges.

ChatGPT sparks the imagination and highlights the importance of Generative AI and foundation models as the basis for modern AI applications. However, this also brings a new set of AI operationalization challenges. Challenges like handling massive amounts of data, large scale computation and memory, complex pipelines, transfer learning, extensive testing, monitoring, and so on. In this talk, we explore the new technologies and share MLOps orchestration best practices that will enable you to automate the continuous integration and deployment (CI/CD) of foundation models and transformers, along with the application logic, in production.