arize-phoenix-evals

import os from phoenix.evals import create_classifier from phoenix.evals.llm import LLM # Set your OpenAI API key from environment variable os.environ["OPENAI_API_KEY"] = os.environ.get('OPENAI_API_KEY', 'sk-your-openai-key') # Replace with actual key or ensure env var is set # Create an LLM instance (ensure OPENAI_API_KEY is set in environment) llm = LLM(provider="openai", model="gpt-4o") # Create a custom classification evaluator evaluator = create_classifier( name="helpfulness", prompt_template="Rate the response to the user query as helpful or not:\n\nQuery: {input}\nResponse: {output}", llm=llm, choices={"helpful": 1.0, "not_helpful": 0.0}, ) # Simple evaluation on a single record scores = evaluator.evaluate({"input": "How do I reset the device?", "output": "Go to settings > reset."}) print(f"Simple evaluation score: {scores[0].score}, label: {scores[0].label}") # Evaluation with input mapping for nested data scores_nested = evaluator.evaluate( {"data": {"query": "How do I restart the app?", "response": "Close and reopen the application."}}, input_mapping={"input": "data.query", "output": "data.response"} ) print(f"Nested evaluation score: {scores_nested[0].score}, label: {scores_nested[0].label}")