Scaling Unstructured Data Indexing with Apache Pulsar for Generative AI Applications
StreamNative via YouTube
Overview
Learn how Apache Pulsar can efficiently handle unstructured data indexing for Generative AI applications in this 26-minute conference talk from Pulsar Virtual Summit Europe 2024. Explore the fundamentals of generative AI, embeddings, and RAG while discovering how to implement robust and scalable solutions for both exploratory and production environments. Dive into key topics including similarity search, indexing challenges, Pulsar Functions, and scalability considerations. Presented by Nicolo Boschi from DataStax, gain practical insights into leveraging Apache Pulsar as a backbone for modern AI data processing workflows.
Syllabus
Introduction
What is generative AI
Architecture
Similarity search
Indexing
Challenges
Pulser Functions
Scalability
Conclusion
Taught by
StreamNative