'commit'

dsLightRag/Test/T2_AnswerFromRAG.py

@@ -38,16 +38,14 @@ if __name__ == '__main__':
     wb = load_workbook(excel_file)
     ws = wb.active  # 获取第一个sheet
     # 读取C列第2行到101行的数据
-    idx = 1
     for row in range(2, 102):  # 行号从2到101
         query_text = ws[f'C{row}'].value
-        logger.info("问题{}:{}".format(idx, query_text))
+        logger.info("问题{}:{}".format(row - 1, query_text))
         # 知识库作答
         rag_answer = getAnswer(query_text)
-        logger.info("成功完成问题{}:{}".format(idx, query_text))
+        logger.info("成功完成问题{}:{}".format(row - 1, query_text))
         # 回写到Excel表中
-        ws['O'+str(idx+1)] = rag_answer
-        idx = idx + 1
+        ws['O' + str(row)] = rag_answer
     # 保存修改
     wb.save(excel_file)
     wb.close()

dsLightRag/Test/T4_Score.py

@@ -1,7 +1,17 @@
+import logging
+import re
+
 from openpyxl import load_workbook
 
 from Util import LlmUtil
 
+# 更详细地控制日志输出
+logger = logging.getLogger('MathRag')
+logger.setLevel(logging.INFO)
+handler = logging.StreamHandler()
+handler.setFormatter(logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s'))
+logger.addHandler(handler)
+
 # 要处理的Excel
 excel_file = r'D:\dsWork\dsProject\dsLightRag\Doc\T1、史校长资料\测试结果\100题测试结果.xlsx'
 
@@ -17,19 +27,35 @@ if __name__ == '__main__':
     wb = load_workbook(excel_file)
     ws = wb.active  # 获取第一个sheet
 
-    query_text = prompt + "\n"
-    query_text = query_text + "下面将提供两段文字：\n"
-    query_text = query_text + "【1】：\n"
-    O2_content = ws['O2'].value
-    query_text = query_text + O2_content + "\n"
-
-    query_text = query_text + "【2】：\n"
-    O2_content = ws['D2'].value
-    query_text = query_text + O2_content + "\n"
-
-    response = LlmUtil.get_llm_response(query_text)
-    print(response)
-    # 对比
-    # 【1】:O2,【2】:D2 内容
-    # 结果保存到 P2 (打分过程) Q2(通过正则表达式截取出的 【最终得分】)
+    for row in range(2, 102):  # 行号从2到101
+        # 提示词
+        query_text = prompt + "\n"
+        query_text = query_text + "下面将提供两段文字：\n"
+
+        query_text = query_text + "【1】：\n"
+        O_content = ws['O' + str(row)].value
+        query_text = query_text + O_content + "\n"
+
+        query_text = query_text + "【2】：\n"
+        D_content = ws['D' + str(row)].value
+        query_text = query_text + D_content + "\n"
+
+        question = ws['C' + str(row)].value  # 获取问题
+        logger.info("问题" + str(row - 1) + ":" + question)
+        response = LlmUtil.get_llm_response(query_text)
+        # 【1】:O2,【2】:D2 内容
+        # 结果保存到 P2 (打分过程) Q2(通过正则表达式截取出的 【最终得分】)
+        # 使用正则表达式提取【最终得分】
+        match = re.search(r'【最终得分】：(\d+)分', response)
+        final_score = '0'
+        if match:
+            final_score = match.group(1)
+            # 保存到P2(打分过程)和Q2(最终得分)
+            ws['P' + str(row)] = prompt + "\n" + response  # 提示词+大模型响应
+            ws['Q' + str(row)] = final_score
+        logger.info("大模型响应：" + response)
+        logger.info("得分：" + final_score)
+
+    wb.save(excel_file)
     wb.close()
+    logger.info("恭喜，所有任务处理完成！")