Jina NOW - get your neural search case up and running in minutes.
Project description
One command to host them all. Bring your search case into the cloud in minutes.
Tell us what you think: Survey
NOW gives the world access to neural image search with just one command.
- ⛅ Cloud: We handle deployment and maintenance.
- 🐎 Fast and easy: Set up your search use case in minutes with minimal effort.
- 🌈 Quality: You provide the labels, NOW fine-tunes the model.
- ✨ Nocode: Non-technical people can deploy with ease.
Read how Jina NOW is production ready.
Install
pip install jina-now
If you need sudo to run Docker, use sudo to install and use Jina NOW as well.
Mac M1
For the M1 we recommend using a Conda environment. In a new Conda environment:
- Run
conda install grpcio tokenizers protobuf - Run
pip install jina-now.
Quick start
jina now start
1. Choose your data source.
You may either choose a demo dataset hosted by NOW, or use your own custom dataset, to build an application.
NOW can support your custom data in the form of a DocumentArray, as a path to a local folder, or S3 bucket.
? How do you want to provide input? (format: https://docarray.jina.ai/) (Use arrow keys)
❯ Demo dataset
DocumentArray name (recommended)
Local folder
S3 bucket
- Elasticsearch (will be available in upcoming versions)
You can choose a demo dataset to get started quickly. The demo datasets are hosted by NOW which can be easily used to build a search application. There is a large variety of datasets, including images, text, and audio.
If you would like to use your own custom data, you can choose DocumentArray name. You will be asked to provide the
DocumentArray ID (or name) or URL of your dataset.
? Please enter your DocumentArray name:
You can also choose the local folder option to upload your data, in which case NOW asks for the path to the folder containing your data:
? Please enter the path to the local folder:
Perhaps your data is stored in an S3 bucket, which is an option NOW also supports. In this case, NOW asks for the URI to the S3 bucket, as well as the credentials and region thereof.
? Please enter the S3 URI to the folder:
? Please enter the AWS access key ID:
? Please enter the AWS secret access key:
? Please enter the AWS region:
A final step in loading your data is to choose the fields of your data that you would like to use for search and filter respectively. You can choose from the fields that are available in your data. For more information on this, see the guide to loading your data.
2. Choose your deployment type.
We recommend cloud deployment to run your app on our servers. Alternatively, you can deploy locally.
? Where do you want to deploy your search engine? (Use arrow keys)
❯ ⛅️ Jina Cloud
📍 Local
For local deployment, NOW asks where you want to deploy it and reads your local .kube/config and lists all Kubernetes clusters you have access to.
If you don't want to use an existing cluster, you can create a new one locally.
? Which cluster do you want to use to deploy your search engine? (Use arrow keys)
kind-jina-now
minikube
❯ 🐣create new
3. Follow the links. After NOW finishes processing, you'll see two links:
- The Swagger UI is useful for frontend integration.
- The "playground" lets you run example queries and experiment with your search use case.
🚀 Deploy playground and BFF
BFF docs are accessible at:
http://localhost:30090/api/docs
Playground is accessible at:
http://localhost:30080/?host=gateway&search_field=image&data=best-artworks&port=8080
Example of the playground.
Example of the Swagger UI.
More information on using Jina NOW CLI and API
Supported modalities (more coming soon)
- 📝 Text
- 🏞 Image
- 🥁 Music
- 🎥 Video (for GIFs)
- 🧊 3D Mesh (coming soon)
Example datasets
👕 Fashion
☢️ Chest X-Ray
💰 NFT - bored apes
🖼 Art
🚗 Cars
🏞 Street view
🦆 Birds
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
