Skip to main content
The chat() method sends a chat completion request to a running model server and returns a ChatMessage payload. It is a simple API for quick prompts when you do not need to call the HTTP endpoint directly.

Basic Chat

Multiturn conversations

For multiturn conversations the chat() method accepts an additional history argument which can also be used to set system prompts.

Model instantiation

The model exposes a variety of customization parameters including base_image, which allows you to customize the model container runtime. This is especially useful if you need to run inference on custom hardware which requires a specifically compiled version of llama.cpp, vLLM, and more.

Async models

The async model API is identical to the sync examples above.

Before you call chat()

The server must be running. If you are not using a context manager, manage the model lifecycle yourself:

Method signature

Parameters

Returns

A ChatMessage typed dict with the assistant response.

Raises

  • RuntimeError if the server is not running.

When to use chat() vs direct HTTP

For direct HTTP calls, see the quick start example that uses requests.