deepeval

import os import asyncio from deepeval import evaluate from deepeval.test_case import LLMTestCase from deepeval.metrics import AnswerRelevancyMetric # Configure your LLM API key (e.g., OpenAI, Cohere, etc.) # Most metrics require an LLM to run. Replace with your actual key or set as env var. # os.environ["OPENAI_API_KEY"] = os.environ.get('OPENAI_API_KEY', 'your_openai_api_key_here') async def main(): # Define a simple LLM test case test_case = LLMTestCase( input="What is the capital of France?", actual_output="Paris is the capital of France.", expected_output="Paris", context=["France is a country in Western Europe. Its capital is Paris."], retrieval_context=["Paris is known for the Eiffel Tower."] ) # Initialize a metric, e.g., AnswerRelevancyMetric # Some metrics can take additional parameters or a specific LLM model. answer_relevancy_metric = AnswerRelevancyMetric(threshold=0.7) # Run the evaluation results = await evaluate( [test_case], metrics=[answer_relevancy_metric] ) print("Evaluation Results:") for result in results: print(f" Input: {result.input}") print(f" Actual Output: {result.actual_output}") for m in result.metrics_results: print(f" Metric: {m.metric_name}, Score: {m.score}, Pass: {m.success}") if __name__ == '__main__': asyncio.run(main())