In this talk, we will discuss how to create an AI agent with a semantic cache using Microsoft’s AutoGen module for Python. Two different semantic cache implementations will be presented using different vector databases. The first implementation will use PostgreSQL with pgVector, which is easy to deploy on local developer workstations. The second implementation will use ScyllaDB Cloud with Vector Search, which is better suited for enterprise-grade applications that require low latency and scalability.

VegasTech