Aries-ckt
commented
3 days ago Thanks for your suggestion. now pdf loader support pdf extract json and pdf extract table, we will integrate OCR to solve the image info in the future.
Open virtual-sln opened 4 days ago
Aries-ckt
commented
3 days ago Thanks for your suggestion. now pdf loader support pdf extract json and pdf extract table, we will integrate OCR to solve the image info in the future.
Search before asking
Description
At present, the knowledge base creation supports the upload of PDF files, but it seems to not handle image-based PDF files, resulting in empty content after upload.
It would be beneficial to enhance the knowledge base creation section to include support for image-based PDFs and image processing. This would allow for the handling of a greater variety of data types.
1、目前知识库创建那边虽然支持pdf文件上传，但好像不支持图片类pdf文件的处理，上传后读取的内容为空。
2、希望可以在创建知识库那块增加对图像类pdf和图像的处理，这样可以处理更多类型的数据。
Use case
No response
Related issues
No response
Feature Priority
None
Are you willing to submit PR?