Building Smarter Products with GenAI: A Deep Dive into LLMs, Vector DBs, and RAG

This workshop unlocks the potential of generative AI for practical use by exploring the following:

• large language models (LLMs)
• vector databases
• Retrieval-Augmented Generation (RAG)

Part 1: LLMs transform product development by generating contextually relevant, human-like responses.

This presentation explains how LLMs work, from tokens and embeddings to advanced techniques to enhance their output.

Part 2: We discuss vector databases, a powerful tool for storing and retrieving data, mimicking human memory, and improving AI’s precision.

Part 3: Finally, we play with RAG (Retrieval Augmented Generation), which enhances LLM performance by integrating domain-specific information.

This session uses a specific use case example and offers practical insights into leveraging these technologies to elevate product strategies.

About the speaker:

David Wertheimer is a VP of Engineering with deep expertise in AI/ML. He leads high-performing teams and drives business growth through strategic innovation. With a background in Agile transformations and cloud optimization, David excels at aligning technology with business goals and empowering teams to deliver impactful results.

As a consultant, he specializes in AI strategy and prompt engineering, developing tools to accelerate innovation.

⚠️ This workshop builds upon the fundamentals of LLM prompt writing discussed in the previous session (here's the recording: https://youtu.be/KGZSyaGSd0U ).