azure-ai-evaluation

import os from azure.ai.evaluation import evaluate, RelevanceEvaluator # Ensure environment variables are set for Azure OpenAI # AZURE_OPENAI_ENDPOINT, AZURE_OPENAI_KEY, AZURE_OPENAI_DEPLOYMENT model_config = { "azure_endpoint": os.environ.get("AZURE_OPENAI_ENDPOINT", ""), "api_key": os.environ.get("AZURE_OPENAI_KEY", ""), "azure_deployment": os.environ.get("AZURE_OPENAI_DEPLOYMENT", ""), } # Example for a simple AI-assisted quality evaluation relevance_evaluator = RelevanceEvaluator(model_config=model_config) # For a conversation/turn based evaluation # result = relevance_evaluator( # query="What is the capital of Japan?", # response="Tokyo is the capital of Japan." # ) # For evaluating a dataset data_for_evaluation = [ {"id": "1", "query": "What is the capital of France?", "response": "Paris.", "context": "France is a country in Europe. Its capital is Paris."}, {"id": "2", "query": "Who painted the Mona Lisa?", "response": "Leonardo da Vinci.", "context": "Leonardo da Vinci was an Italian polymath."} ] # You can use `evaluate` function for batch evaluation on a dataset # Ensure you have a configured Azure AI Project if logging results to AI Studio # azure_ai_project = { # "subscription_id": os.environ.get("AZURE_SUBSCRIPTION_ID", ""), # "resource_group_name": os.environ.get("AZURE_RESOURCE_GROUP", ""), # "project_name": os.environ.get("AZURE_AI_PROJECT_NAME", ""), # } # results = evaluate( # data=data_for_evaluation, # evaluators=[relevance_evaluator], # # azure_ai_project=azure_ai_project # Uncomment to log to AI Studio # ) print("Evaluators initialized. Ready for evaluation.")