Generative models such as ChatGPT have changed many product roadmaps. Interfaces and user experience can now be re-imagined and often drastically simplified to what resembles a google search bar where the input is natural language. However, some models remain behind APIs without the ability to re-train on contextually appropriate data. Even in the case where the model weights are publicly available, re-training or fine-tuning is often expensive, requires expertise and is ill-suited to problem domains with constant updates. How then can such APIs be used when the data needed to generate an accurate output was not present in the training set because it is consistently changing?

Read more

Let’s face it, the challenge of search today is indexing billions of entries while delivering relevant results quickly. Traditional keyword-based methods have limitations, leaving us searching for a better way to improve search. But what if we could use deep learning to revolutionize search? Imagine representing data as vectors, where the distance between vectors reflects similarity, and using Vector Similarity Search algorithms to search billions of vectors in milliseconds. It’s the future of search, and it can transform text, multimedia, images, recommendations, and more. Check out this panel discussion, where you will learn how you can incorporate vector search into your own applications to harness deep learning insights at scale.

Read more

This post, originally written for the NVIDIA Developer Blog, details offline, online, and online large-scale recommendation system architectures. With a focus on deployment, we use a building block framework, NVIDIA Merlin, and a real-time data layer, Redis, to construct examples of end-to-end recommendation systems.

Read more