Some of the latest big evolutionary steps in generative AI has been models that support function calling and “agentic” capabilities. This is provides generative models with “tools” that allow them to go beyond generating outputs for simple queries, and start planning the best way to solve complex queries. In this talk, we’ll be diving into using vector databases as the backbone for these types of complex AI architectures, both serving as knowledge bases, and memory.
Basic understanding of vector databases and vector search would be useful.
In this technical talk, we will start by covering the history of how agentic AI came about. We will go over how we can design prompts in a way that instruct LLMs to use tools and plan out how to solve complex queries. Next, we will learn about function calling and how this feature of LLMs can be used as the basis of agents.
The talk will include a small amount of coding, ending in a working agent in the form of a technical assistant.
Tuana is a Developer Relations Engineer at Weaviate, where she educates the their open-source community on AI tooling, latest methods and workflows. Previously, she lead the DevRel team at deepset, the company behind Haystack. Her primary focus is the open-source AI community and helping people learn how they can make the most out of Weaviate for scalable AI applications. She has a degree in Computer Science from the University of Bristol in the UK.