Update app.py

app.py

@@ -8,7 +8,6 @@ from datasets import load_dataset
 import pandas as pd
 from fuzzywuzzy import process
 
-
 # 현재 작업 디렉토리 출력
 print("Current Working Directory:", os.getcwd())
 
@@ -33,6 +32,12 @@ def load_optimized_dataset(data_files):
     name_to_number = full_data.groupby('사건명')['사건번호'].apply(list).to_dict()
     summary_to_number = full_data.groupby('판시사항')['사건번호'].apply(list).to_dict()
     number_to_fulltext = full_data.set_index('사건번호')['전문'].to_dict()
+
+    # 디버깅용 로깅
+    logging.debug(f"Sample entries in name_to_number: {list(name_to_number.items())[:3]}")
+    logging.debug(f"Sample entries in summary_to_number: {list(summary_to_number.items())[:3]}")
+    logging.debug(f"Sample entries in number_to_fulltext: {list(number_to_fulltext.items())[:3]}")
+
     return name_to_number, summary_to_number, number_to_fulltext
 
 name_to_number, summary_to_number, number_to_fulltext = load_optimized_dataset(data_files)
@@ -42,6 +47,10 @@ print("Dataset loaded successfully.")
 all_case_names = list(name_to_number.keys())
 all_case_summaries = list(summary_to_number.keys())
 
+# 디버깅용 로깅
+logging.debug(f"Sample all_case_names: {all_case_names[:3]}")
+logging.debug(f"Sample all_case_summaries: {all_case_summaries[:3]}")
+
 # 로깅 설정
 logging.basicConfig(level=logging.DEBUG, format='%(asctime)s:%(levelname)s:%(name)s: %(message)s', handlers=[logging.StreamHandler()])
 
@@ -105,7 +114,10 @@ async def generate_response(message):
     # 유사한 사건명 및 판시사항 찾기
     matched_case_names = process.extractBests(user_input, all_case_names, limit=3, score_cutoff=70)  # score_cutoff 값 조정
     matched_case_summaries = process.extractBests(user_input, all_case_summaries, limit=3, score_cutoff=70)
-    
+
+    logging.debug(f"Matched case names: {matched_case_names}")
+    logging.debug(f"Matched case summaries: {matched_case_summaries}")
+
     if matched_case_names:
         case_numbers = []
         for case_name, score in matched_case_names: