Jina AI Cloud Hosting#

https://docs.jina.ai/_images/jcloud-banner.png
../../_images/jcloud-banner.png

After building a Jina project, the next step is to deploy and host it on the cloud. Jina AI Cloud is Jina’s reliable, scalable and production-ready cloud-hosting solution that manages your project lifecycle without surprises or hidden development costs.

Tip

At present, Jina AI Cloud hosts all your Jina projects and offers computational/storage resources for free!

Basics#

Jina AI Cloud provides a CLI that you can use via jina cloud from the terminal (or jcloud or simply jc for minimalists.)

Hint

You can also install just the JCloud CLI without installing the Jina package.

pip install jcloud
jc -h

If you installed the JCloud CLI individually, all of its commands fall under the jc or jcloud executable.

In case the command jc is already occupied by another tool, use jcloud instead. If your pip install doesn’t register bash commands for you, you can run python -m jcloud -h.

For the rest of this section, we use jc or jcloud. But again they are interchangable with jina cloud.

Deploy#

In Jina’s idiom, a project is a Flow, which represents an end-to-end task such as indexing, searching or recommending. In this document, we use “project” and “Flow” interchangeably.

Caution

Flows have a maximum lifetime after which they are automatically deleted.

A Flow can have two types of file structure: a single YAML file or a project folder.

Single YAML file#

A self-contained YAML file, consisting of all configuration at the Flow-level and Executor-level.

All Executors’ uses must follow the format jinaai+docker://<username>/MyExecutor (from Executor Hub) to avoid any local file dependencies:

# flow.yml
jtype: Flow
executors:
  - name: sentencizer
    uses: jinaai+docker://jina-ai/Sentencizer

To deploy:

jc deploy flow.yml

Tip

We recommend testing locally before deployment:

jina flow --uses flow.yml

Project folder#

Tip

The best practice of creating a JCloud project is to use:

jc new

This ensures the correct project structure accepted by JCloud.

Just like a regular Python project, you can have sub-folders of Executor implementations and a flow.yml on the top-level to connect all Executors together.

You can create an example local project using jc new hello. The default structure looks like:

hello/
├── .env
├── executor1
│   ├── config.yml
│   ├── executor.py
│   └── requirements.txt
└── flow.yml

Where:

  • hello/ is your top-level project folder.

  • executor1 directory has all Executor related code/configuration. You can read the best practices for file structures. Multiple Executor directories can be created.

  • flow.yml Your Flow YAML.

  • .env All environment variables used during deployment.

To deploy:

jc deploy hello

The Flow is successfully deployed when you see:

../../_images/deploy.png

You will get a Flow ID, say merry-magpie-82b9c0897f. This ID is required to manage, view logs and remove the Flow.

As this Flow is deployed with the default gRPC gateway (feel free to change it to http or websocket), you can use jina.Client to access it:

from jina import Client, Document

print(
    Client(host='grpcs://merry-magpie-82b9c0897f.wolf.jina.ai').post(
        on='/', inputs=Document(text='hello')
    )
)

Get status#

To get the status of a Flow:

jc status merry-magpie-82b9c0897f
../../_images/status.png

Monitoring#

Basic monitoring is provided to Flows deployed on Jina AI Cloud.

To access the Grafana-powered dashboard, first get the status of the Flow. The Grafana Dashboard link is displayed at the bottom of the pane. Visit the URL to find basic metrics like ‘Number of Request Gateway Received’ and ‘Time elapsed between receiving a request and sending back the response’:

../../_images/monitoring.png

List Flows#

To list all of your “Serving” Flows:

jc list
../../_images/list.png

You can also filter your Flows by passing a phase:

jc list --phase Deleted
../../_images/list_deleted.png

Or see all Flows:

jc list --phase all
../../_images/list_all.png

Remove Flows#

You can remove a single Flow, multiple Flows or even all Flows by passing different identifiers.

To remove a single Flow:

jc remove merry-magpie-82b9c0897f

To remove multiple Flows:

jc remove merry-magpie-82b9c0897f wondrous-kiwi-b02db6a066

To remove all Flows:

jc remove all

By default, removing multiple or all Flows is an interactive process where you must give confirmation before each Flow is deleted. To make it non-interactive, set the below environment variable before running the command:

export JCLOUD_NO_INTERACTIVE=1

Update Flow#

You can update a Flow by providing an updated YAML.

To update a Flow:

jc update super-mustang-c6cf06bc5b flow.yml
../../_images/update_flow.png

Pause / Resume Flow#

You have the option to pause a Flow that is not currently in use but may be needed later. This will allow the Flow to be resumed later when it is needed again by using resume.

To pause a Flow:

jc pause super-mustang-c6cf06bc5b
../../_images/pause_flow.png

To resume a Flow:

jc resume super-mustang-c6cf06bc5b
../../_images/resume_flow.png

Restart Flow, Executor or Gateway#

If you need to restart a Flow, there are two options: restart all Executors and the Gateway associated with the Flow, or selectively restart only a specific Executor or the Gateway.

To restart a Flow:

jc restart super-mustang-c6cf06bc5b
../../_images/restart_flow.png

To restart the Gateway:

jc restart super-mustang-c6cf06bc5b --gateway
../../_images/restart_gateway.png

To restart an Executor:

jc restart super-mustang-c6cf06bc5b --executor executor0
../../_images/restart_executor.png

Scale an Executor#

You can also manually scale any Executor.

jc scale good-martin-ca6bfdef84 --executor executor0 --replicas 2
../../_images/scale_executor.png

Restrictions#

JCloud scales according to your needs. You can demand different resources (GPU/RAM/CPU/storage/instance-capacity) based on the needs of your Flows and Executors. If you have specific resource requirements, please contact us on Slack or raise a GitHub issue.

Restrictions

  • Deployments are only supported in the us-east region.

  • Each Executor is allocated a maximum of 4GB RAM, 2 CPU cores & 10GB of block storage.

  • Three Flows can be deployed at a time, out of which one Flow can use a GPU.

  • A maximum of two GPUs are allocated per Flow.

  • Flows with Executors using GPU are removed after 12 hours, whereas other Flows are removed after 72 hours.