Peltarion AI
Using this connector, you can connect your app with your Peltarion models. Just add the connector and enter URL and token from the Peltarion platform, and send your data
This connector is available in the following products and regions:
Service | Class | Regions |
---|---|---|
Logic Apps | Standard | All Logic Apps regions except the following: - Azure Government regions - Azure China regions - US Department of Defense (DoD) |
Power Automate | Premium | All Power Automate regions except the following: - US Government (GCC) - US Government (GCC High) - China Cloud operated by 21Vianet - US Department of Defense (DoD) |
Power Apps | Premium | All Power Apps regions except the following: - US Government (GCC) - US Government (GCC High) - China Cloud operated by 21Vianet - US Department of Defense (DoD) |
Contact | |
---|---|
Name | Peltarion |
URL | https://peltarion.com/ |
[email protected] |
Connector Metadata | |
---|---|
Publisher | Peltarion |
Website | https://peltarion.com/ |
Privacy policy | https://peltarion.com/privacy-policies |
Categories | AI;Data |
Use deep learning in your apps! Peltarion’s plugin is the simplest and fastest way to create smart applications. With this integration, you can build and deploy AI models and connect them with Power Apps.
Some examples of what you can build:
- An app that can classify customer support tickets according to urgency and sentiment (tutorial, demo)
- An app that can label images as per the clothing category they belong to (say in an e-commerce catalog) (tutorial)
- An app for predicting house value in a particular neighborhood (tutorial)
More examples here.
Getting started
- Sign up for free on the Peltarion Platform
- Follow along with these tutorials (link, link) or by watching this demo (link)
- Build and train your AI model on the Peltarion platform
- Add the Peltarion connector to your app and enter your credentials
To call the API you only need one action. To use the connector and store the value into a variable res, you can call the API like this:
ClearCollect(dd, { <YOUR-INPUT-PARAM>: TextInput1.Text});
Set(jdata, JSON(dd, JSONFormat.IncludeBinaryData));
Set(res, Peltarion.callapi(jdata))
Check out the GitHub-page for more details.
The res is an object with three values:
- key is the name of the predicted class. For regression problems, the key is always "value"
- val is the probability of the class
- errorMessage holds the error message, if any
Your URL, token and input name is found on the Deployment view on the Peltarion Platform.
For information on how to build and train an AI model on the Peltarion platform, visit our knowledge center
Creating a connection
The connector supports the following authentication types:
Default | Parameters for creating connection. | All regions | Not shareable |
Default
Applicable: All regions
Parameters for creating connection.
This is not shareable connection. If the power app is shared with another user, another user will be prompted to create new connection explicitly.
Name | Type | Description | Required |
---|---|---|---|
Peltarion API URL | string | The Peltarion API URL for this app | True |
Peltarion API Token | string | The Peltarion API Token for this app | True |
Throttling Limits
Name | Calls | Renewal Period |
---|---|---|
API calls per connection | 100 | 60 seconds |
Actions
Call Peltarion API |
This function calls your model deployed on the Peltarion Platform. |
Call Peltarion API
This function calls your model deployed on the Peltarion Platform.
Parameters
Name | Key | Required | Type | Description |
---|---|---|---|---|
Call body in JSON format.
|
peltarionbody | True | string |
Peltarion body |
Returns
Name | Path | Type | Description |
---|---|---|---|
key
|
key | string |
key |
val
|
val | string |
val |
errorMessage
|
errorMessage | string |
errorMessage |