Demo: Build An AI Meeting Coach With Flink SQL, OpenAI, & Confluent

Learn how to build a real-time meeting coach system that uses Confluent's data streaming platform, Apache Flink® SQL, and Azure OpenAI to provide sales teams with timely, contextual advice.

Learn more: https://cnfl.io/4g3Agi0

In this demo, Brenner Heintz, Staff Technical Marketing Manager at Confluent, demonstrates the system's architecture, key components, and how it leverages company knowledge documents to enhance sales conversations.

CHAPTERS

0:00 - Introduction

1:14 - How the System Works

2:17 - Retrieval Augmented Generation (RAG)

3:30 - Using Company-Specific Documents

4:10 - Technical Architecture

5:50 - Creating Embeddings

6:04 - Deploying Models in Azure AI Foundry

6:51 - Processing Documents for Vector Search with Flink Actions

9:32 - Sending Data to MongoDB Vector Database

10:55 - Vector Search Function in Flink SQL

12:48 - Generating Responses with GPT-4 Mini

14:35 - Technical Highlights and Event-Driven Architecture

15:21 - Why Build on Confluent's Platform

17:23 - Conclusion and GitHub Repo

–

ABOUT CONFLUENT
Confluent is pioneering a fundamentally new category of data infrastructure focused on data in motion. Confluent’s cloud-native offering is the foundational platform for data in motion – designed to be the intelligent connective tissue enabling real-time data, from multiple sources, to constantly stream across the organization. With Confluent, organizations can meet the new business imperative of delivering rich, digital front-end customer experiences and transitioning to sophisticated, real-time, software-driven backend operations. To learn more, please visit www.confluent.io.

#apacheflink #flinksql #confluent