Neural Enhanced Collaborative Tool for Automated Recommendation and INtelligent Exploration
...which is a very cool acronym and totally not the fruit I was eating when I was coming up with a name for this project
Nectarine is an open-source recommendation system project that leverages state-of-the-art recommender systems implemented in TensorFlow, making it easier to deliver personalized content and experiences to your audience.
-
Two-Tower Recommender Systems: Nectarine harnesses the power of two-tower recommender models to deliver accurate and efficient recommendations for your application.
-
Kubernetes Integration: Nectarine is designed to seamlessly deploy and scale within Kubernetes clusters, ensuring scalability, high availability, and easy management.
-
KServe Integration: Nectarine is served with KServe, enabling users to expose and manage recommendation endpoints efficiently.
-
Helm Chart for Easy Deployment: Deploy Nectarine effortlessly in your Kubernetes cluster using our Helm chart, which simplifies the installation process and provides configuration options.
Nectarine is released under the MIT License, which means you are free to use, modify, and distribute the software. Attribution is highly appreciated