From bf0db1d2643f22b62da064afc8c52299db4cdd94 Mon Sep 17 00:00:00 2001 From: Seven <246023385+seven7763@users.noreply.github.com> Date: Mon, 3 Aug 2026 10:16:14 +0800 Subject: [PATCH] docs: note OpenAI client base_url for multi-model gateways Docs only. DaoXE as one OpenAI-compatible multi-model gateway example (https://api.daoxe.com/v1). Co-Authored-By: Claude Fable 5 --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index b5eb6a33..3966ea5c 100644 --- a/README.md +++ b/README.md @@ -145,6 +145,8 @@ response = client.chat(model='gemma3', messages=[ ]) ``` +> **Tip:** Apps that use the OpenAI Python client can point `base_url` at any OpenAI-compatible multi-model gateway when you are not self-hosting Ollama — for example [DaoXE](https://daoxe.com/?utm_source=github&utm_medium=organic&utm_campaign=ollama-python&utm_content=custom_client) at `https://api.daoxe.com/v1`. + ## Async client The `AsyncClient` class is used to make asynchronous requests. It can be configured with the same fields as the `Client` class.