🧪🤖 openai-responses

Pytest plugin for automatically mocking OpenAI requests. Built on top of RESPX.

Supported endpoints

/v1/chat/completions
/v1/embeddings
/v1/files
/v1/assistants
/v1/threads (+ messages, runs, and steps)

View full support coverage here.

Usage

Simply decorate any test function that contains code that makes a call to an OpenAI endpoint. See docs for more.

import openai_responses
from openai import OpenAI


@openai_responses.mock.chat.completions(
    choices=[
        {"message": {"content": "Hello, how can I help?"}},
        {"message": {"content": "Hi! I'm here to help!"}},
        {"message": {"content": "How can I help?"}},
    ],
)
def test_create_completion_with_multiple_choices():
    client = OpenAI(api_key="fakeKey")
    completion = client.chat.completions.create(
        model="gpt-3.5-turbo",
        messages=[
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "Hello!"},
        ],
        n=3,
    )
    assert len(completion.choices) == 3

Important

This project does not try to generate fake responses from the models. Any part of a response that would be generated by a model will need to be defined by the user or will fallback to a default value.