From 16a679390e0dbd465400d733976b3698c84654ec Mon Sep 17 00:00:00 2001 From: osanseviero Date: Tue, 15 Aug 2023 23:53:32 +0200 Subject: [PATCH] Add mention that it just works with api-hosted models --- docs/source/basic_tutorials/consuming_tgi.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/source/basic_tutorials/consuming_tgi.md b/docs/source/basic_tutorials/consuming_tgi.md index b9f5978a..ab324f4b 100644 --- a/docs/source/basic_tutorials/consuming_tgi.md +++ b/docs/source/basic_tutorials/consuming_tgi.md @@ -16,7 +16,7 @@ curl 127.0.0.1:8080/generate \ ## Inference Client -[`huggingface-hub`](https://huggingface.co/docs/huggingface_hub/main/en/index) is a Python library to interact with the Hugging Face Hub, including its endpoints. It provides a nice high-level class, [`~huggingface_hub.InferenceClient`], which makes it easy to make calls to a TGI endpoint. `InferenceClient` also takes care of parameter validation and provides a simple to-use interface. +[`huggingface-hub`](https://huggingface.co/docs/huggingface_hub/main/en/index) is a Python library to interact with the Hugging Face Hub, including its endpoints. It provides a nice high-level class, [`~huggingface_hub.InferenceClient`], which makes it easy to make calls to a TGI endpoint. `InferenceClient` also takes care of parameter validation and provides a simple to-use interface. At the moment, `InferenceClient` only works for models hosted with the Inference API or Inference Endpoints. You can simply install `huggingface-hub` package with pip.