One line to host them all. Bootstrap your image search case in minutes.

NOW gives the world access to customized neural image search in just one line of code. Main features

• 🐥 Easy: Minimal effort required to set up your search case
• 🐎 Fast: Set up your search case within minutes
• 🌈 Quality: If you provide labels to your documents, Jina NOW fine-tunes a model for you
• 🌳 Reliable: We take care of the deployment and maintenance (coming soon)
• ✨ Nocode: Deployment can be done by non-technical people

pip install jina-now

In case you need sudo for running Docker, install and use jina-now using sudo as well.

For the Mac M1 it is generally recommended using a conda environment as outlined in the Jina documentation. In a new conda environment first execute conda install grpcio tokenizers protobuf. Then run pip install jina-now.

jina now [start | stop] --data [<pushpullid> | <localpath> | <url>] --quality [medium | good | excellent] --cluster <k8s-cluster-name>

jina now start

jina now start --quality medium --data /local/img/folder

You can now send requests to the API using the jina client. This case shows a local deployment.

from jina import Client    
client = Client(
        host='localhost',
        protocol="grpc",
        port=31080,
) 
response = client.search(
        Document(text=search_text), # or in case you send an image: Document(url=image_path),
        parameters={"limit": 9, "filter": {}},
)

jina now stop

• Python 3.7, 3.8, 3.9 or 3.10

• Docker installation
• 10 GB assigned to docker
• User must be permitted to run docker containers

• Billing account enabled

• No further requirements (coming soon)

• Text
• Image
• Audio
• Video
• 3D mesh
• PDF
• ...

👕 Fashion

☢️ Chest X-Ray

💰 NFT - bored apes

🖼 Art

🚗 Cars

🏞 Street view

🦆 Birds