30 Mar 2023: Integrate with Huggingface.co

Neelke Stadler Updated by Neelke Stadler

Often a user experience can be improved by using a machine learning model to infer the meaning of the submitted request.

A convenient way to do this is to use models hosted on Huggingface.co. We made it possible to interact with the Hugging Face API using Stacks.

What can you do with Huggingface.co?

Lots!

Hugging Face is an AI community that promotes open source contributions. The platform provides tools that enable users to build, train and deploy ML models based on open source code and technologies. Even the tech giants like Google, Facebook, AWS, Microsoft, and others use the models, datasets, and libraries.

Hugging Face provides state-of-the-art models for different tasks. It has a vast number of pre-trained models for different tasks including Natural Language Processing tasks (Text classification, Text generation, Translation, Summarization, Question-Answering, etc.), Computer Vision tasks (Image classification, Image segmentation, Object detection), Audio task (Speech recognition, Text-to-speech, Audio classification, etc.) and much more.

You can also train and host your own model on Hugging Face and use that in Turn. You can either refer to the model by name if it's a publicly available model, or specify the URL where to find your model on Hugging Face and the token required for authentication and you're all set.

This is great news! How to we start using it?

Our Turn Developer docs explain it all! Read how to integrate with Machine Learning (ML) hosted on Huggingface.co. We explain how to set up a connection to a model, how to call the Inference API with the model, how to process the results of the model and how to use the results to make an informed decisions

Was this article helpful?

28 Mar 2023: Important changes to template categories

23 Mar 2023: Answer conversations on mobile

Contact