From 3bf78fd34648160d23d562f63d838eb0da60af17 Mon Sep 17 00:00:00 2001 From: Seven <246023385+seven7763@users.noreply.github.com> Date: Mon, 3 Aug 2026 10:37:24 +0800 Subject: [PATCH 1/2] docs: note OpenAI client base_url for multi-model gateways Document that the OpenAI-compatible Base Path pattern works with multi-model gateways, using DaoXE (https://api.daoxe.com/v1) as one concrete example. Co-Authored-By: Claude Fable 5 --- en/integrations/langchain/chat-models/chatlocalai.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/en/integrations/langchain/chat-models/chatlocalai.md b/en/integrations/langchain/chat-models/chatlocalai.md index eb30b6fe..e4e7ad4e 100644 --- a/en/integrations/langchain/chat-models/chatlocalai.md +++ b/en/integrations/langchain/chat-models/chatlocalai.md @@ -53,6 +53,10 @@ Fill in the fields: * **Base Path**: The base url from LocalAI such as [http://localhost:8080/v1](http://localhost:8080/v1) * **Model Name**: The model you want to use. Note that it must be inside `/models` folder of LocalAI directory. For instance: `ggml-gpt4all-j.bin` +{% hint style="info" %} +The same **Base Path** pattern works with OpenAI-compatible multi-model gateways when you are not self-hosting LocalAI — for example [DaoXE](https://daoxe.com/?utm_source=github&utm_medium=organic&utm_campaign=flowise-docs&utm_content=chatlocalai) at `https://api.daoxe.com/v1`. +{% endhint %} + {% hint style="info" %} If you are running both Flowise and LocalAI on Docker, you might need to change the base path to [http://host.docker.internal:8080/v1](http://host.docker.internal:8080/v1). For Linux based systems the default docker gateway should be used since host.docker.internal is not available: [http://172.17.0.1:8080/v1](http://172.17.0.1:8080/v1) {% endhint %} From 280f26631eeebe307cc1d50ec28fa37bda90925d Mon Sep 17 00:00:00 2001 From: Seven <246023385+seven7763@users.noreply.github.com> Date: Mon, 3 Aug 2026 20:31:10 +0800 Subject: [PATCH 2/2] docs: note OpenAI client base_url for multi-model gateways