Guide
Deploying a Custom Workflow
Learn how to deploy a custom workflow to Sieve.
First, please make sure you have signed up for a Sieve account as per the quickstart guide.
Install the Sieve CLI
pip install https://mango.sievedata.com/v1/client_package/sievedata-0.0.1.1.2-py3-none-any.whl
Then, export your Sieve API key as an environment variable. You can find your API key in the Sieve dashboard.
export SIEVE_API_KEY=YOUR_API_KEY
Create a Workflow
Create a new folder and add the files below.
import sieve
from typing import Dict, Tuple
from yolo import Yolo
from splitter import VideoSplitter
@sieve.workflow(name="yolo_object_detection")
def yolo_workflow(video: sieve.Video) -> Dict:
images = VideoSplitter(video)
yolo_outputs = Yolo()(images)
return yolo_outputs
Deploy the Workflow
You workflow will be deployed. You can monitor the status via your terminal or on the Sieve dashboard.
sieve deploy
Run the Workflow
You can run the workflow on a video file. You can do this via the dashboard, the API, or the CLI. We can use this file to test.
CLI
sieve push yolo_object_detection '{"video": {"url": "https://storage.googleapis.com/sieve-test-videos-central/01-lebron-dwade.mp4"}}'
API
curl --request POST \
--url https://mango.sievedata.com/v1/push \
--header "X-API-Key: $SIEVE_API_KEY" \
--header "Content-Type: application/json" \
--data '{
"workflow_name": "yolo_object_detection",
"inputs": {
"video": {
"url": "https://storage.googleapis.com/sieve-test-videos-central/01-lebron-dwade.mp4"
}
}
}'
Dashboard
Navigate to the yolo_object_detection
worklow on the dashboard, enter the video URL, and click Send Request
.
More Examples
You can find more examples in the Sieve Examples Repo.