更新API密钥管理,优化意图识别和Excel数据验证功能,增强日志记录,改进错误处理机制,支持文档检索功能,提升代码可读性和灵活性。
This commit is contained in:
@@ -135,11 +135,10 @@ class WikijsNounsExtractor:
|
||||
parsed_output = self.terms_list_parser.parse(response.content)
|
||||
return parsed_output.terms
|
||||
except Exception as e:
|
||||
logging.error(f"解析LLM响应时出错: {str(e)}")
|
||||
logging.error(f"原始响应: {response.content}")
|
||||
logging.error(f"解析LLM响应时出错: {str(e)}", exc_info=True)
|
||||
return []
|
||||
except Exception as e:
|
||||
logging.error(f"提取专业名词时出错: {str(e)}")
|
||||
logging.error(f"提取专业名词时出错: {str(e)}", exc_info=True)
|
||||
return []
|
||||
|
||||
def _process_document(self, doc, path_terms):
|
||||
@@ -182,7 +181,7 @@ class WikijsNounsExtractor:
|
||||
|
||||
return path_prefix
|
||||
except Exception as e:
|
||||
logging.error(f"处理文档 {doc['path']} 时出错: {str(e)}")
|
||||
logging.error(f"处理文档 {doc['path']} 时出错: {str(e)}", exc_info=True)
|
||||
return None
|
||||
|
||||
def process_all_documents(self, output_dir: str = "extracted_nouns", max_concurrency: int = 5):
|
||||
@@ -237,7 +236,7 @@ class WikijsNounsExtractor:
|
||||
if i % 10 == 0:
|
||||
logging.info(f"已完成 {i+1}/{len(futures)} 个文档的处理")
|
||||
except Exception as e:
|
||||
logging.error(f"处理文档时出错: {str(e)}")
|
||||
logging.error(f"处理文档时出错: {str(e)}", exc_info=True)
|
||||
|
||||
# 保存最终结果
|
||||
for prefix, terms in path_terms.items():
|
||||
|
||||
Reference in New Issue
Block a user