When using python and pytest you can simply install the baserun plugin and start testing immediately. The plugin works by automatically collecting and aggregating all LLM and baserun logs during the course of a test and then uploading them to baserun to review and collaborate on with your team.

​
Setup

pip install baserun

pytest --baserun test_module.py
========================Baserun========================
Test results available at: https://app.baserun.ai/runs/<id>
=======================================================

​
Automatically using Baserun in tests

You can automatically include the --baserun option on every invocation of pytest by creating or updating your pytest.ini file with: 
[pytest]
addopts = --baserun

​
Running multiple tests

It’s often helpful to exercise the same test over multiple examples. To do this, we suggest using the parametrize decorator and for larger numbers of examples you can read from a file or other data structure. 

@pytest.mark.parametrize("place,expected", [("Paris", "Eiffel Tower"), ("Rome", "Colosseum")])
def test_trip(place, expected):
    response = openai.ChatCompletion.create(
        model="gpt-3.5-turbo",
        temperature=0.7,
        messages=[
            {
                "role": "user",
                "content": "What are three activities to do in {place}?"
            }
        ],
    )

    assert expected in response["choices"][0]["message"]["content"]

​
Naming

Baserun lets you compare test results and debug each step side by side. We consider the name of the pytest function and its parameters as a unique identifier for the test. In the example above, two tests would be run and identified by (test_trip, "Paris", "Eiffel Tower") and (test_trip, "Rome", "Colosseum")

Automatic evaluations

Evaluate tests’ outputs.