Welcome to Jina!

Jina🔊 is a neural search framework that empowers anyone to build SOTA and scalable deep learning search applications in minutes.

🌌 All data types - Scalable indexing, querying, understanding of any data: video, image, long/short text, music, source code, PDF, etc.

⏱️ Save time - The design pattern of neural search systems, from zero to a production-ready system in minutes.

🌩️ Fast & cloud-native - Distributed architecture from day one, scalable & cloud-native by design: enjoy containerizing, streaming, paralleling, sharding, async scheduling, HTTP/gRPC/WebSocket protocols.

🍱 Own your stack - Keep end-to-end stack ownership of your solution, avoid integration pitfalls you get with fragmented, multi-vendor, generic legacy tools.


  1. Make sure that you have Python 3.7+ installed on Linux/MacOS/Windows.

  2. Install Jina

    pip install -U jina
    conda install jina -c conda-forge
    docker run jinaai/jina:latest
  3. Run hello-world demo

    jina hello fashion
  4. That’s it! In the next few seconds the demo will open in a new page in your browser.

Now that you’re set up, let’s dive into more of how Jina works and how to build great apps.

Next steps

Play 3 Hello World

Try Jina on fashion image search, QA chatbot and multimodal search.

Understand Basics

Document, Executor, and Flow are the three fundamental concepts in Jina.

Share Executors

Learn how to share and reuse Executors from community.

Manage Remote Jina

Learn how to deploy and manage Jina on remote via a RESTful interface.

Clean & Efficient Code

Write beautiful & lean code with Jina.

Try Experimental Features

Preview the next big thing we are building. Careful, zapping!

Get Yourself Jina Swag

Awesome Jina swag to our awesome contributors (aka you)!


Join Us

Jina is backed by Jina AI and licensed under Apache-2.0. We are actively hiring AI engineers, solution engineers to build the next neural search ecosystem in opensource.

Index | Module Index