π¨ Integrations
With Hugging Face Inference Endpoints, you can easily deploy Transformers, Diffusers or any model on dedicated, fully managed infrastructure. Click here to create an endpoint.
There are two ways to add a Hugging Face Endpoint resource.
ILLA Builder
>> Click Resources
tab >> Click Create New
>> Choose Hugging Face Endpoint
>> Configure the connection information and click Save Resource
+ New
in the action list >> Choose Hugging Face Endpoint
>> Configure the connection information or click + New Resource
to add new connection informationProperties | Required | Description |
---|---|---|
Name | required | Define a resource name that will be used for display in ILLA |
Endpoint URL | required | create Endpoint here: https://ui.endpoints.huggingface.co/new and get the URL. |
Token | required | The organization token. You can get it in https://huggingface.co/settings/tokens. |
Enter the edit page >> click + New
in the action list >> Choose Hugging Face Endpoint
>> Choose an existing resource or add a new resource
Properties | Required | Description |
---|---|---|
Parameter type | required | The parameter type of your Endpoint. For example, if your Endpoint needs an text input, choose fill in βinputsβ parameter with text. If your Endpoint needs an JSON input, choose fill in βinputsβ parameter with JSON or key-value. |
Parameter | required | Enter your parameter. Use {{ componentName.value }} to use data of components. |
We have deployed openai/whisper-base
which gets an audio file input and converts into text. It is suitable for meeting minutes, podcasts to text, etc. Next we will introduce how to use this model to build an application in ILLA Cloud.
We have built an interface using the components such as file upload and button, as follows.
Fill in the fields shown below to finish the resource configuration. Create an Endpoint and get the Endpoint URL. And get the organization API token in profile settings.
Select a parameter type first. Take openai/whisper-base
as an example, this model requires binary file input so we change the parameter to Binary
.
Set the binary to be passed to the model as the file data uploaded from the file upload component. For example, {{upload1.value[0]}}
Add an event handler to the button to trigger the action run when the button is clicked. And set the value of text component to {{whisper.data[0].text}} to display the convert result on text component.
After the above steps are configured, the application is created and the running results are as follows.