fix(fix "gbk" encode error in 批量总结PDF文档 line14):

由于不可编码字符,导致报错,添加软解码,处理原始文本。
This commit is contained in:
欧玮杰 2023-03-31 10:03:10 +08:00
parent 285fa4690c
commit 125fa7c378

View File

@ -11,6 +11,7 @@ def 解析PDF(file_manifest, project_folder, top_p, temperature, chatbot, histor
file_content = ""
for page in doc:
file_content += page.get_text()
file_content = file_content.encode('gbk', 'ignore').decode('gbk')
print(file_content)
prefix = "接下来请你逐文件分析下面的论文文件,概括其内容" if index==0 else ""