AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Navigating Vector Databases and Data Pipelines
This chapter explores the speaker's journey from in-memory vector indexing to dedicated vector databases, emphasizing technical considerations for production use, especially in a Kubernetes environment. Key topics include the building of Retrieval-Augmented Generation (RAG) pipelines, optimizing data ingestion techniques, and evaluating systems like the Morningstar Intelligence Engine. The discussion also covers collaboration between financial experts and engineers to enhance the quality and efficiency of data processing and chatbot evaluations.