Update app.py

app.py

@@ -22,12 +22,16 @@ def get_evaluation_questions():
     Both lists must be of equal length.
     """
     questions_str = os.environ.get("TEST_QUESTION_1")
+    print("questions",questions_str)
     expected_str = os.environ.get("TEST_EXPECTED_1")
+    print("expected",expected_str)
     if not questions_str or not expected_str:
         return []
     try:
         questions_list = json.loads(questions_str)
+        print("questions lst ",questions_list)
         expected_list = json.loads(expected_str)
+        print("expected lst",expected_list)
     except Exception as e:
         print(f"Error parsing evaluation questions: {str(e)}")
         return []
@@ -94,6 +98,7 @@ def submit_prompt(email, name, system_prompt):
             )
             # Extract the answer from the response object.
             answer = response.choices[0].message.content.strip()
+            print("llm answer", answer)
         except Exception as e:
             answer = f"Error during OpenAI API call: {str(e)}"
 
@@ -101,8 +106,10 @@ def submit_prompt(email, name, system_prompt):
         if expected.lower() in answer.lower():
             score += 1
             verdict = "Correct"
+            print(f"{expected.lower()} DOES NOT MATCH {answer.lower()}")
         else:
             verdict = "Incorrect"
+            print(f"{expected.lower()} MATCHES {answer.lower()}")
 
         responses.append(
             f"Question: {question}\n"