Serverless
With Picsellia π₯ Serverless Deployment you can deploy your exported models easily.
Pre-requisite
In order to benefit from our serverless deployment engine, you need to have some exported models in your model registry.
Select the model that you want to deploy
To select the model, browse into your model registry page


Let's select the city-objects
model π₯


You can quickly see the overview of your exported model i.e the training set used and the Experiment that created this model.
Deploy Serverless


You have 3 different options:
- Deploy Serverless
- Use your Custom Serving ( coming soon )
- Only use your deployment dashboard to Monitor you models
Access your deployment Dashboard


Your deployment is now created and you can access its name on top-left
You have now access to your Deployment Dashboard, this is the one-stop place to:
- Model Management
- Latency Monitoring
- Prediction images visualization and review
- Alerting, etc.
If you want more information about all the monitoring metrics provided in Picsellia Monitoring suite, please check the Model Monitoring Section of Picsellia's Documentation π₯
Try prediction
import os
import requests
import json
token = "0e1220d4ce70323188f5d3646cfd877caedba23"
deployment_name = "every-envelope"
url = "https://steroids.picsellia.com/api/v1/predict/{}".format(deployment_name)
headers = {
"Authorization": "Token " + token,
}
data = {
"source": "test",
"tag": "test_tag1"
}
imgpath = "pexels-sergio-souza-2293649.jpg"
r = requests.post(
url=url,
files={'media': open(imgpath, 'rb')},
headers=headers,
data=data
)
prediction = r.json()
Now you have a scalable and serverless API endpoint that won't change even if you change your model version :)


Updated 6 months ago