infiniflow / ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
https://ragflow.io
Apache License 2.0
22.86k stars 2.24k forks source link

[Bug]: Can't parse PPTX file, error code: 102 #2467

Open sherzlock opened 1 month ago

sherzlock commented 1 month ago

Is there an existing issue for the same bug?

Branch name

main

Commit ID

deeb950e1c75321e44d06771f39c98115cf2ef8a

Other environment information

No response

Actual behavior

3321726495253_ pic 知识库是 general的解析,但里面有些文件是 pptx,所以单独设置为 presentation,但显示为 102,不支持

Expected behavior

No response

Steps to reproduce

1. 文件管理中建立 1 个文件夹,上传相关文件,有pdf/pptx/xls等格式
2. 建立知识库,关联此文件夹,进行解析,general 方案,关闭布局识别,打开raptor策略
3. 开始解析,pptx 文件解析失败,显示不支持
4. 单独转换为 presentation 格式进行解析,显示上面如图所示,102 错误,不支持

Additional information

No response

KevinHuSh commented 1 month ago

Bug fixed. But you need to redo action of linking.

sherzlock commented 1 month ago

Bug fixed. But you need to redo action of linking.错误已修复。但您需要重新执行链接操作。

thanks a lot. Do I need to pull the mirror again or perform an upgrade?