👍

What you'll learn

• How to Deploy your Async Service using the Python SDK

Upon completing this guide, you will have successfully deployed an Async Service. Your Async Service deployment dashboard will resemble the following:

Step 1: Clone the code

To get started, clone the following repository by entering the following command in your terminal:

git clone https://github.com/truefoundry/getting-started-examples

After cloning the repository, navigate to the code directory using the following command:

cd deploy-ml-model

The servicefoundry.yaml script that we'll create in the upcoming steps will be located in this directory.

Step 2: Deploying the Async Service

In this step, we will create a servicefoundry.yaml file to configure and deploy our Async Service. The servicefoundry.yaml file will contain the configuration for your Async Service.

Please create the servicefoundry.yaml file in the same directory where your Async Service code (app.py) is located. After creating the servicefoundry.yaml file, your directory structure will look like the following:

File Structure

.
├── app.py
├── servicefoundry.yaml
└── requirements.txt

servicefoundry.yaml

name: async-service
type: async_service
image:
  type: build
  build_spec:
    type: tfy-python-buildpack
    command: gunicorn app:app --workers 1 --worker-class uvicorn.workers.UvicornWorker --bind 127.0.0.1:8000
    python_version: '3.9'
    requirements_path: requirements.txt
    build_context_path: ./
  build_source:
    type: local
ports:
  - host: <YOUR HOST HERE>
    port: 8000
worker_config:
  input_config:
    type: sqs
    queue_url: <YOUR_INPUT_QUEUE_URL>
    region_name: <YOUR_REGION_NAME>
    visibility_timeout: 1
    wait_time_seconds: 1
    auth:
      aws_access_key_id: <YOUR_AWS_ACCESS_KEY_ID>
      aws_secret_access_key: <YOUR_AWS_SECRET_ACCESS_KEY>
  output_config:
    type: sqs
    queue_url: <YOUR_OUTPUT_QUEUE_URL>
    region_name: <YOUR_REGION_NAME>
    auth:
      aws_access_key_id: <YOUR_AWS_ACCESS_KEY_ID>
      aws_secret_access_key: <YOUR_AWS_SECRET_ACCESS_KEY>
  sidecar:
    destination_url: <your destination url>
    request_timeout: 10
resources:
  cpu_limit: 1
  cpu_request: 0.5
  memory_limit: 200
  memory_request: 500
  ephemeral_storage_limit: 1000
  ephemeral_storage_request: 2000

📘

Picking a value for host

Providing a host value depends on the base domain urls configured in the cluster settings, you can learn how to find the base domain urls available to you here

For e.g. If your base domain url is *.truefoundry.your-org.com then a valid value can be fastapi-your-workspace-8000.truefoundry.your-org.com.

Alternatively if you have a non wildcard based domain url e.g. truefoundry.your-org.com, then a valid value can be truefoundry.your-org.com/fastapi-your-workspace-8000

To deploy your Async Service using the servicefoundry CLI, execute the following command in your terminal:

servicefoundry deploy --workspace-fqn=YOUR_WORKSPACE_FQN

Run the above command from the same directory containing the app.py and requirements.txt files.

After executing the command mentioned above, the deployment process will begin.
Please be patient and wait for the deployment process to finish. You can monitor the deployment status, and once it displays "SUCCESS", your Async Service will be successfully deployed.

Once the deployment process is complete, you will receive a link to access the dashboard. Look for a message like You can find the application on the dashboard: in the output.
Click on the provided link to access the deployment dashboard.

Interact with your Async Service

Follow the following guide to learn how to Interact with the Async Service you just deployed:
Interacting with your Async Service