Get started with evaluating prompts using the Maxim SDK. This guide will walk you through setting up the SDK and running your first prompt evaluation test run.

​
Installation

First, install the Maxim SDK for your preferred language: 
pip install maxim-py

​
Getting Your API Key

Before you can use the Maxim SDK, you need to obtain an API key from the Maxim platform:
  1. Log in to Maxim: Go to app.getmaxim.ai/login and sign in to your account
  2. Navigate to Settings: Click on “Settings” in the left sidebar
  3. Go to API Keys: Click on “API keys” under “Organization settings”
  4. Generate New Key: Click the “Generate new” button
  5. Name Your Key: Enter a descriptive name for your API key (e.g., “Development”, “CI/CD”, “Local Testing”)
  6. Copy the Key: Once generated, copy the API key immediately - you won’t be able to see it again
Store your API key securely! You won’t be able to view the complete key value again after closing the generation dialog.

​
Configuration

Initialize the Maxim SDK with your API key: 
from maxim import Maxim

# Initialize Maxim SDK

maxim = Maxim({"api_key": "your-api-key"})

​
Basic Prompt Test Run

Here’s how to create and run a basic prompt evaluation test run using a dataset from the platform: 
# Creating a test run

result = (
    maxim.create_test_run(
        name="Basic Prompt Evaluation", in_workspace_id="your-workspace-id"
    )
    .with_data_structure(
        {
            "input": "INPUT",
            "expected_output": "EXPECTED_OUTPUT",
        }
    )
    .with_data("dataset-id")
    .with_evaluators("Bias")
    .with_prompt_version_id("prompt-version-id")
    .run()
)

print(f"Test run completed! View results: {result.test_run_result.link}")
  • createTestRun is the main function that creates a test run. It takes the name of the test run and the workspace id.
  • withDataStructure is used to define the data structure of the dataset. It takes an object with the keys as the column names and the values as the column types.
  • withData is used to specify the dataset to use for the test run. Can be a datasetId(string), a CSV file, an array of column to value mappings.
  • withEvaluators is used to specify the evaluators to use/attach for the test run. You may create an evaluator locally through code or use an evaluator that is installed in your workspace through the name directly
  • withPromptVersionId is used to specify the prompt version to use for the test run. It takes the id of the prompt version.
  • run is used to execute the test run.

​
Next Steps

Now that you’ve run your first prompt evaluation, explore these guides: