Update llm.py

llm.py

@@ -35,10 +35,10 @@ def evaluate_docs(docs: List[str], question: str) -> List[tuple]:
     results = []
     for i, doc in enumerate(docs):
         raw = _chat(prompts.evaluate_doc_prompt(question, doc), max_tokens=50)
-        logger.info(f"Doc {i} Evaluation Raw Output: '{raw}'")
+        print(f"Doc {i} Evaluation Raw Output: '{raw}'")
 
         raw_lower = raw.lower()
-        logger.info(f"Doc {i} Evaluation lowerd Raw Output: '{raw_lower}'")
+        print(f"Doc {i} Evaluation lowerd Raw Output: '{raw_lower}'")
         
         if "incorrect" in raw_lower:
             label = "Incorrect"
@@ -48,8 +48,8 @@ def evaluate_docs(docs: List[str], question: str) -> List[tuple]:
             label = "Ambiguous"
 
 
-        logger.info(f"Final parsed label for Doc {i}: {label}")    
-        logger.info(f"Doc {i}: {doc}") 
+        print(f"Final parsed label for Doc {i}: {label}")    
+        print(f"Doc {i}: {doc}") 
         results.append((doc, label))
     return results