Jina is a very powerful framework that can help you build distributed multi-modal and cross-modal applications, from start to finish.
In order to get you started on your more ambitious projects, we compiled a list of how-to tutorials that guide you through some of Jina’s more advanced features. Happy coding!
Scaling out: In many scenarios, running a single Executor for a given task is just not enough. Whether you need more throughput or to partition your data, we’ve got you covered. This tutorial will show you how to easily scale out using Jina.
Executors on GPU: Machine Learning models are only as fast as the metal they run on, and for maximum performance you want that metal to be a GPU. For a guide on how to run Executors on GPU and accelerate your code, see this tutorial.
External Executors: Executors need not be tied to a specific Flow. If you want to learn how to spawn Executors on their own, use them in various Flows, even from a different machine or from inside a Docker container, then follow along here.
Once you have built your search app using Jina, naturally you want to deploy it. Luckily, Jina plays nice with your favorite tools for the job.
Docker Compose: If you want to learn about Jina’s native support for Docker Compose, including deployment, look no further than this guide.
Kubernetes: If your weapon of choice is Kubernetes then fear not, because it is supported by Jina natively. How you can put that into practice you can find here.