Skip to main content

Jina NOW - get your neural search case up and running in minutes.

Project description

Jina NOW logo: The data structure for unstructured data
One command to host them all. Bring your search case into the cloud in minutes.
Tell us what you think: Survey

Python 3.7 3.8 3.9 3.10 PyPI

Jina NOW logo: The data structure for unstructured data

NOW gives the world access to neural image search in just one command execution. Main features

  • Cloud: We take care of the deployment and maintenance
  • 🐥 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
  • Nocode: Deployment can be done by non-technical people

You can read more on how Jina NOW is production ready here.

Installation

pip install jina-now

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

Mac M1

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.

Usage

You can use the following command to start Jina NOW.

jina now start

First, you will get asked what search case you would like to deploy.

Quick Start

jina now start

First, you will be prompted to choose an app. As for now, we support images or text searches. But in the future, we will add many more options here.

Screenshot 2022-05-31 at 01 08 25

In the next step, you get asked to select the dataset type for your search app. You can choose between demo datasets, docarray (name or URL/path to it), local path to a folder of the data or a bucket on S3.

If you chose docarray.pull, you will be asked to insert your docarray id. Likewise, if you chose docarray URL, you will be prompted to enter the URL. In case you selected local path, jina-now will ask you to enter the local path of the data folder as shown bellow.

question-local-path

Currently, we provide two deployment options. We recommend using the cloud deployment. This will run your search app on our servers. Alternatively, you can select the local deployment option.

question-deployment

In case of local deployment, you will be asked where you want to deploy it. Jina NOW 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.

question-cluster

After the program execution is finished, two links will be shown to you. The first one brings you to the swagger UI which is useful for frontend integration. The second URL leads you to a playground where you can run example queries and experiment with the search case.

Screenshot 2022-05-26 at 16 34 56

Example of the playground.

Screenshot 2022-05-26 at 16 36 49

Example of the swagger ui.

Screenshot 2022-05-26 at 16 36 06

For more information on how to use Jina NOW CLI and API click here

Supported apps (more will be added)

  • Text to Image search 📝 ▶ 🏞
  • Image to Text search 🏞 ▶ 📝
  • Image to Image search 🏞 ▶ 🏞
  • Text to Text search 📝 ▶ 📝
  • Music to Music search 🥁 ▶ 🥁
  • Text to Video search 📝 ▶ 🎥 (only gif at the moment)
  • Text to 3D Mesh search 📝 ▶ 🧊
  • ...

IMAGE ALT TEXT HERE


Examples

👕 Fashion image
☢️ Chest X-Ray
💰 NFT - bored apes
🖼 Art image
🚗 Cars image
🏞 Street view image
🦆 Birds image

Now use your custom data :)

Project details


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.

Source Distribution

jina-now-0.0.34.tar.gz (304.0 kB view details)

Uploaded Source

File details

Details for the file jina-now-0.0.34.tar.gz.

File metadata

  • Download URL: jina-now-0.0.34.tar.gz
  • Upload date:
  • Size: 304.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.1 CPython/3.7.15

File hashes

Hashes for jina-now-0.0.34.tar.gz
Algorithm Hash digest
SHA256 d8668c73e65597f862f491f8c5c5f50dc3ae97cf19401e9020f78d072d51f66c
MD5 f26260fbc3690f2ef3656876b3a8ee02
BLAKE2b-256 36292a9acc37e65aee6513611b052a08070758b7174c8c412e554463ab396deb

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page