This demonstration focuses on Xilinx's Cosine Similarity library, showing how to build a recommendation engine powered by Xilinx Alveo U50 accelerator cards. After completing this webinar you will be able to set up and use the accelerator library by integrating it into Tigergraph Enterprise Graph Database or by using standalone APIs, using Jupyter Notebooks. The Xilinx Consine Similarity library provides extremely fast compute times and scales with multiple Alveo U50 cards on a single node or in a cluster.

Notebook Walkthroughs:

• Standalone Cosine Similarity Direct Python Webinar
• Recommendation Engine Juypter Notebook Demo