OpenAI Blog
·
4 years ago
OpenAI released a new API endpoint that generates embeddings for text and code, enabling applications like semantic search, clustering, and classification. The embeddings endpoint is now available in the OpenAI API for developers to integrate into their applications. This allows developers to build systems that understand semantic meaning rather than relying on keyword matching alone.
Hugging Face Blog
·
4 years ago
The huggingface_hub library added new search features including ModelSearchArguments and ModelFilter classes that let users find models and datasets programmatically without leaving their Python interface. A query for text-classification models trained on GLUE and compatible with PyTorch returned 140 matching models through the simplified API. Users can now construct complex multi-criteria searches with readable syntax instead of trial-and-error parameter formatting.