agentscope-ai/OpenJudge

# Initialize grader grader = Grader.load("Relevance") # Evaluate response response = { "query": "What is machine learning?", "response": "Machine learning is a subset of AI that enables systems to learn from data.", } score = grader.evaluate(response) print(score) # Output: # { # "name": "Relevance", # "score": 0.95, # "reasoning": "The response directly addresses the query with an accurate definition of machine learning." # } ``` ### Batch Evaluation Example Evaluate multiple responses at scale: ```python # Load test data test_data = [ {"query": "What is AI?", "response": "AI is artificial intelligence."}, {"query": "What is ML?", "response": "Machine learning is

459 stars.