Quickstart
Start running evals with just six lines of code
Install the Atla Python Library
Start by installing the Atla Python library. From the terminal run the following:
pip install atla
Set up your API key
To use Atla, you’ll need to provide your Atla API key. You can set the environment variable with your API key or create a local .env
file which contains the API key.
If you haven’t set up your account yet, you can do so on the sign up page.
export ATLA_API_KEY=pk-abc123
Send your first eval
The final step is to send your first evaluation request to Atla. Create a new Python file (e.g. atla_test.py
) and add the following code:
from atla import Atla
client = Atla(
# defaults to os.environ.get("ATLA_API_KEY")
api_key="my_api_key"
)
evals = client.evaluation.create(
input="If 5 machines take 5 minutes to make 5 widgets, how long would it take 100 machines to make 100 widgets?",
response="Total processing time is 5 widgets * 5 minutes = 25 minutes. Then 25 mins / 100 machines = 15 seconds.",
metrics=["logical_coherence"],
)
print(f"Atla's score: {evals.evaluations['logical_coherence'].score} / 5")
print(f"Atla's critique: {evals.evaluations['logical_coherence'].critique}")
To run the code, enter python atla_test.py
into the terminal.
Atla will return a score and a critique for the response based on the input provided.
Next steps
Now that you have performed your first evaluations, explore what else is possible with Atla.
- For a full description of the base metrics, see our metrics documentation.
- See the example use cases on how to integrate Atla into common applications of LLM’s.
- View the API documentation for in depth details on the API endpoints and parameters.
- Request custom metrics.