Spaces:

holistic-ai
/

explainbility_benchmark

Sleeping

Zekun Wu commited on May 17, 2024

Commit

4a24dd6

1 Parent(s): 51c7b4d

update

Files changed (1) hide show

pages/5_Conversation_Evaluation.py CHANGED Viewed

@@ -105,7 +105,7 @@ else:
             eval = evaluator(model_name)
             scores = eval.evaluate_conversation(conversation, context)
             st.write('### Scores')
-            details = write_evaluation_commentary(scores["aggregate_scores"])
             df = pd.DataFrame(details)
             st.write(df)

             eval = evaluator(model_name)
             scores = eval.evaluate_conversation(conversation, context)
             st.write('### Scores')
+            details = write_evaluation_commentary(scores)
             df = pd.DataFrame(details)
             st.write(df)