examples: fix api changes (#2129)

Author: shahules786

experimental/ragas_examples/agent_evals/evals.py

@@ -5,13 +5,13 @@
 
 math_agent = get_default_agent()
 
-@numeric_metric(name="correctness")
+@numeric_metric(name="correctness", allowed_values=(0.0, 1.0))
 def correctness_metric(prediction: float, actual: float):
     """Calculate correctness of the prediction."""
     if isinstance(prediction, str) and "ERROR" in prediction:
         return 0.0
     result = 1.0 if abs(prediction - actual) < 1e-5 else 0.0
-    return MetricResult(result=result, reason=f"Prediction: {prediction}, Actual: {actual}")
+    return MetricResult(value=result, reason=f"Prediction: {prediction}, Actual: {actual}")
 
 
 def load_dataset():
@@ -56,13 +56,13 @@ async def run_experiment(row):
         "expected_answer": expected_answer,
         "prediction": prediction.get("result"),
         "log_file": prediction.get("log_file"),
-        "correctness": correctness.result
+        "correctness": correctness.value
     }
 
 
 async def main():
     dataset = load_dataset()
-    _ = await run_experiment.run_async(dataset)
+    _ = await run_experiment.arun(dataset)
 
 
 if __name__ == "__main__":

experimental/ragas_examples/prompt_evals/evals.py

@@ -4,10 +4,10 @@
 
 from .prompt import run_prompt
 
-@discrete_metric(name="accuracy", values=["pass", "fail"])
+@discrete_metric(name="accuracy", allowed_values=["pass", "fail"])
 def my_metric(prediction: str, actual: str):
     """Calculate accuracy of the prediction."""
-    return MetricResult(result="pass", reason="") if prediction == actual else MetricResult(result="fail", reason="")
+    return MetricResult(value="pass", reason="") if prediction == actual else MetricResult(value="fail", reason="")
 
 
 @experiment()
@@ -22,7 +22,7 @@ async def run_experiment(row):
     experiment_view = {
         **row,
         "response":response,
-        "score":score.result,
+        "score":score.value,
     }
     return experiment_view
 
@@ -56,7 +56,7 @@ def load_dataset():
 
 async def main():
     dataset = load_dataset()
-    experiment_results = await run_experiment.run_async(dataset) 
+    experiment_results = await run_experiment.arun(dataset) 
     print("Experiment completed successfully!")
     print("Experiment results:", experiment_results)
 

experimental/ragas_examples/rag_eval/evals.py

@@ -33,8 +33,8 @@ def load_dataset():
 
 my_metric = DiscreteMetric(
     name="correctness",
-    prompt = "Check if the response contains points mentioned from the grading notes and return 'pass' or 'fail'.\nResponse: {response} Grading Notes: {grading_notes}",
-    values=["pass", "fail"],
+    prompt="Check if the response contains points mentioned from the grading notes and return 'pass' or 'fail'.\nResponse: {response} Grading Notes: {grading_notes}",
+    allowed_values=["pass", "fail"],
 )
 
 @experiment()
@@ -50,7 +50,7 @@ async def run_experiment(row):
     experiment_view = {
         **row,
         "response": response,
-        "score": score.result,
+        "score": score.value,
         "log_file": response.get("logs", " "),
     }
     return experiment_view
@@ -59,7 +59,7 @@ async def run_experiment(row):
 async def main():
     dataset = load_dataset()
     print("dataset loaded successfully", dataset)
-    await run_experiment.run_async(dataset)
+    await run_experiment.arun(dataset)
 
 if __name__ == "__main__":
     import asyncio

experimental/ragas_examples/workflow_eval/evals.py

@@ -80,7 +80,7 @@ def load_dataset():
 my_metric = DiscreteMetric(
     name="response_quality",
     prompt="Evaluate the response based on the pass criteria: {pass_criteria}. Does the response meet the criteria? Return 'pass' or 'fail'.\nResponse: {response}",
-    values=["pass", "fail"],
+    allowed_values=["pass", "fail"],
 )
 
 
@@ -99,15 +99,15 @@ async def run_experiment(row):
     experiment_view = {
         **row,
         "response": response.get("response_template", " "),
-        "score": score.result,
+        "score": score.value,
         "score_reason": score.reason,
     }
     return experiment_view
 
 
 async def main():
     dataset = load_dataset()
-    _ = await run_experiment.run_async(dataset)
+    _ = await run_experiment.arun(dataset)
 
 if __name__ == "__main__":
     import asyncio