adithya-s-k / adithya-s-k/omniparse
Issue: Some PDF samples are parsed as empty.
Open
- Dominant language
- Python
- Stars
- 7.9k
- Forks
- 676
- PR merge metrics
- No merged PRs in 30d
Description
[2407.19456v1.pdf](https://github.com/user-attachments/files/16625865/2407.19456v1.pdf)
Ominiparse is very powerful and can parse various types of files quite well. However, some PDF samples return empty results, as if the text inside them does not exist.
this is response
```
{"text":"","images":[],"metadata":{"languages":["en"],"filetype":"other"},"chunks":[]}
```
Contributor guide
Assessment
This issue has not been assessed yet.