What is Jina?
Jina is the easiest way to build neural search in the cloud. It provides an one-stop solution for multi-/cross-modality search and has long-term support from a full-time, venture-backed team.
WHAT IS NEURAL SEARCH?
In short, neural search is a new approach to retrieving information. Instead of telling a machine a set of rules to understand what data is what, neural search does the same thing with a pre-trained neural network. This means developers don’t have to write every little rule, saving them time and headaches, and the system trains itself to get better as it goes along.
Read the blog post
WHY JINA?
Time Saver
Bootstrap an AI-powered search system in just a few minutes with cookiecutter.
Plug & Play
With Jina Hub, you can extend Jina with simple Python scripts or Docker images optimized for your search domain.
First-Class AI models
Jina is a new design pattern for neural search systems with first-class support for state-of-the-art AI models like Faiss, Annoy, Onnx, and more.
Production Ready
Cloud-native features out-of-the-box, like containerization, microservice, distributing, scaling, sharding, async IO, REST, gRPC.
JINA 101: FIRST THINGS TO KNOW
Get a high-level overview of the different members of the Jina family and how they work together to deliver an end-to-end modular search system.
Read the blog postJINA "HELLO, WORLD!" 👋🌍
As a starter, you can try out our "Hello, World" - a simple demo of image neural search for Fashion-MNIST. No extra dependencies needed, just run:
jina hello-world
...or even easier for Docker users, no install required:
docker run -v "$(pwd)/j:/j" jinaai/jina hello-world --workdir /j && open j/hello-world.html
replace "open" with "xdg-open" on Linux
The Docker image downloads the Fashion-MNIST training and test dataset and tells Jina to index 60,000 images from the training set. Then it randomly samples images from the test set as queries and asks Jina to retrieve relevant results.
