Hugging Face
Hugging Face is an open-source hub dedicated to AI/ML models and tools, offering access to a vast collection of machine learning models. This platform makes it easy to incorporate specialized AI and ML functionalities into your applications.
You can use Hugging Face models with Elasticsearch in three ways:
Inference API
In 8.12 we added Hugging Face to the Inference API, allowing you to use models deployed in Hugging Face's inference endpoints directly in Elasticsearch. This allows you to use Hugging Face's scalable infrastructure and provides the ability to perform inference on GPUs!
Transformers library & Hosted models in Elasticsearch
With eland, you can load Hugging Face transformers models into Elasticsearch, and perform inference on dedicated ML nodes inside your cluster. This way, your data never has to leave Elasticsearch to perform inference, giving you full control over your data.
Get started with these blogs
Elasticsearch open inference API adds native chunking support for Hugging Face
Building RAG with Gemma, Hugging Face and Elasticsearch
Tutorials for building semantic search with Hugging Face and Elastic
Index millions of documents with GPU-accelerated inference using Hugging Face and Elasticsearch
Use Elasticsearch open inference API integration with Hugging Face to build semantic search