From 70073947663a655a255d95d095e212a086a03bb2 Mon Sep 17 00:00:00 2001 From: Vaibhav Srivastav Date: Tue, 13 Aug 2024 19:58:21 +0200 Subject: [PATCH] Up. --- docs/source/basic_tutorials/consuming_tgi.md | 2 +- docs/source/conceptual/streaming.md | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/source/basic_tutorials/consuming_tgi.md b/docs/source/basic_tutorials/consuming_tgi.md index 5409222e..6e562226 100644 --- a/docs/source/basic_tutorials/consuming_tgi.md +++ b/docs/source/basic_tutorials/consuming_tgi.md @@ -125,7 +125,7 @@ Assume you are serving your model on port 8080, we will query through [Inference import gradio as gr from huggingface_hub import InferenceClient -client = InferenceClient(model="http://127.0.0.1:8080") +client = InferenceClient(base_url="http://127.0.0.1:8080") def inference(message, history): partial_message = "" diff --git a/docs/source/conceptual/streaming.md b/docs/source/conceptual/streaming.md index 0c6c1213..2e9f6b8b 100644 --- a/docs/source/conceptual/streaming.md +++ b/docs/source/conceptual/streaming.md @@ -48,7 +48,7 @@ To stream tokens with `InferenceClient`, simply pass `stream=True` and iterate o ```python from huggingface_hub import InferenceClient -client = InferenceClient("http://127.0.0.1:8080") +client = InferenceClient(base_url="http://127.0.0.1:8080") output = client.chat.completions.create( messages=[ {"role": "system", "content": "You are a helpful assistant."}, @@ -78,7 +78,7 @@ The `huggingface_hub` library also comes with an `AsyncInferenceClient` in case ```python from huggingface_hub import AsyncInferenceClient -client = AsyncInferenceClient("http://127.0.0.1:8080") +client = AsyncInferenceClient(base_url="http://127.0.0.1:8080") async def main(): stream = await client.chat.completions.create( messages=[{"role": "user", "content": "Say this is a test"}],