From OpenAI to Open LLMs with Messages API on Hugging Face

Hugging Face Blog · 2 years ago

Hugging Face released a Messages API in Text Generation Inference version 1.4.0 that makes open-source language models compatible with OpenAI's Chat Completion API, allowing users to swap between OpenAI and open models using existing client libraries. The API works with OpenAI's Python and JavaScript clients as well as third-party frameworks like LangChain and LlamaIndex, requiring only a change in the endpoint URL and API key. The Messages API does not currently support function calling and only works with models that have a chat_template defined in their tokenizer configuration.