hit-wsy

Results 4 comments of hit-wsy

> > > 参考readme打开表格识别开关就可以了,默认会将表格解析成html格式 > > > > > > 是否能搞成自动识别? 比如表格内的字符能够复制,那就自动转html,否则就表格模型ocr识别??? > > 表格字符能复制也只是字符能复制,表格的结构并不能通过复制得到,表格识别中的模型识别这步是绕不开的 对于非扫描件pdf,pdf函数库不是可以直接提取出表格信息吗,如果表格信息保存完好,至于表格结构可以直接加|或者html标签重新构建,对于这种能否直接识别成html或者md格式,然后识别不出来的再模型识别呢

好的,谢谢,我尝试一下

I have tried to do this, but after setting it up, when the workflow reaches this point, the input displayed becomes the first retrieval. I don't know if this is...

Okay, I will try it in the new version, but please let me show you the details. This is a very simple workflow, as you have shown, the problem lies...