The Hugging Face Inference API provides a service for integrating natural language processing (NLP) models into applications.
Users can create a Hugging Face Endpoint to access a wide range of pre-trained models for tasks such as text classification, named entity recognition, text generation, and more. With the Inference API, developers can quickly deploy and scale their NLP models without the need for extensive infrastructure setup or maintenance.
Additionally, Hugging Face provides comprehensive documentation and support, making it easy for developers to leverage the capabilities of the Inference API in their projects.
You can find more details and the supported operations at Hugging Face | qibb Catalog.
How to get started with Hugging Face integration
Before you get started using Hugging Face integration please make sure that you have the needed permissions for the operations.
For access to your own endpoints, you will need your host URL and an Access Token associated with your account.
Your host URL is assigned when you create an endpoint and you can overwrite the placeholder in the host input as seen here.
When you have logged into your Hugging Face account, you can create the necessary token under Settings > Access Tokens.
Once you have the URL and token you can proceed with the following steps.
For accessing your own endpoints and for the flow examples, you will also need your namespace (your username or organization name) and the name of the endpoint you wish to access. Here is an example showing where to add these parameters as well as the token.
Go to qibb Workflow Editor, open Node Catalog in the right sidebar, and install the Hugging Face node by clicking on the + button.
Drag the Hugging Face node and any other nodes you require from the left sidebar to your flow and connect them.
Open the Hugging Face node. Select an operation, enter your token and parameters as required, and you can start using the integration!
Importing flow examples of a node
Once you've successfully installed a node from the qibb catalog, you can easily import example flows that showcase how the nodes can be used. These example flows are directly accessible within the Flow Editor and are designed to guide users with helpful hints, including how to configure mandatory parameters and credentials.
Here's how to import examples:
In the top right corner of the Flow Editor, click on the menu icon.
Select Import to open the Import Dialog.
Click on the Examples tab.
Choose an example from the list.
Confirm your selection by clicking on the Import button.
By following these steps, you are now ready to make basic API calls using the provided examples. For further exploration of what’s possible, you can find more complex examples in the Flow Catalog.