update test case col names in grade_answer.py

Signed-off-by: minmin-intel <[email protected]>

evals/evaluation/agent_eval/crag_eval/run_benchmark/grade_answers.py

@@ -11,30 +11,24 @@
 
 
 def convert_data_format_for_ragas(data):
-    # data: pandas dataframe
-    # columns: ['query', 'answer', 'ref_answer']
-    # return: a dict with keys: 'input', 'actual_output', 'expected_output'
     output = {
-        "input": data["query"].tolist(),
-        "actual_output": data["answer"].tolist(),
-        "expected_output": data["ref_answer"].tolist(),
-        "retrieval_context": [["dummy_context"] for _ in range(data["query"].shape[0])],
+        "question": data["query"].tolist(),
+        "answer": data["answer"].tolist(),
+        "ground_truth": data["ref_answer"].tolist(),
+        "contexts": [["dummy_context"] for _ in range(data["query"].shape[0])],
     }
     return output
 
 
 def make_list_of_test_cases(data):
-    # data: pandas dataframe
-    # columns: ['query', 'answer', 'ref_answer']
-    # return: a list of dicts with keys: 'input', 'actual_output', 'expected_output'
     output = []
     for _, row in data.iterrows():
         output.append(
             {
-                "input": [row["query"]],
-                "actual_output": [row["answer"]],
-                "expected_output": [row["ref_answer"]],
-                "retrieval_context": [["dummy_context"]],
+                "question": [row["query"]],
+                "answer": [row["answer"]],
+                "ground_truth": [row["ref_answer"]],
+                "contexts": [["dummy_context"]],
             }
         )
     return output

tests/test_ragas.py

@@ -5,13 +5,14 @@
 
 
 import unittest
-
+import os
 from evals.metrics.ragas import RagasMetric
 
-
+host_ip = os.getenv("host_ip", "localhost")
+port = os.getenv("port", "8008")
 class TestRagasMetric(unittest.TestCase):
 
-    @unittest.skip("need pass localhost id")
+    # @unittest.skip("need pass localhost id")
     def test_ragas(self):
         # Replace this with the actual output from your LLM application
         actual_output = "We offer a 30-day full refund at no extra cost."
@@ -24,7 +25,7 @@ def test_ragas(self):
         from langchain_community.embeddings import HuggingFaceBgeEmbeddings
 
         embeddings = HuggingFaceBgeEmbeddings(model_name="BAAI/bge-base-en-v1.5")
-        metric = RagasMetric(threshold=0.5, model="http://localhost:8008", embeddings=embeddings)
+        metric = RagasMetric(threshold=0.5, model=f"http://{host_ip}:{port}", embeddings=embeddings)
         test_case = {
             "question": ["What if these shoes don't fit?"],
             "answer": [actual_output],