Overview: In AI-driven customer support and knowledge management, the ability to deliver accurate, contextually relevant responses in real-time is critical. This talk will delve into building a real-time Retrieval-Augmented Generation (RAG) system by integrating OpenAI’s vector embeddings, Qdrant’s vector database and Apache Kafka in a stream processing pipeline. A key focus will be on the importance of using stream processing to ensure the system continuously updates its knowledge base, enabling it to respond to user queries with the most up-to-date information from documentation and public Slack channels.
Audience: This talk is designed for AI engineers, data scientists, software developers, and system architects who are interested in building cutting-edge, real-time AI systems that rely on stream processing to maintain the accuracy, relevance, and timeliness of generated responses.
Find more sessions in the same event location: