pyflowred-node-ai-openai

OpenAI for PyFlowRED's AI nodes — and anything that speaks the OpenAI API.

pip install pyflowred-node-ai-openai

or, in a running instance, Menu → Manage palette → Install → pyflowred-node-ai-openai, which also declares it so a rebuilt instance installs it again by itself.

What it adds

One configuration node, ai-provider-openai. PyFlowRED's ai chat, ai structured, ai agent, ai embed and ai query point at it and ask it for a model.

A base URL is a first-class setting

The OpenAI API is the one interface other things implement, so vLLM behind a company gateway, LM Studio on a laptop and OpenRouter are this node with a different Base URL — and, for the first two, often No credential at all.

Reasoning models

They do not take a temperature, and the client drops it rather than failing — so one flow can run against a reasoning model and an ordinary one without being edited. Measured: a temperature given to gpt-5-mini is dropped, the same one given to gpt-4o-mini is kept.

Reasoning takes off, low, medium or high. A token budget written there, as Gemini wants one, is turned into the nearest level — so a flow moved from Gemini keeps working.

The credential is not in the flow file

It is a credential property, so it lands encrypted in the instance's credentials file. Written as ${secret:NAME} it is fetched from the instance's secrets provider when the call is made, so a rotated key is picked up without a deploy.

Independent on purpose

This package depends on langchain-openai and not on PyFlowRED, and it imports nothing from it. The contract a provider satisfies is three attributes on an object, so the engine and the providers are released apart.

Apache-2.0.