Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Question]: The file parsing is too slow. #5193

Open
qiufeihong2018 opened this issue Feb 20, 2025 · 4 comments
Open

[Question]: The file parsing is too slow. #5193

qiufeihong2018 opened this issue Feb 20, 2025 · 4 comments
Labels
question Further information is requested

Comments

@qiufeihong2018
Copy link
Contributor

Describe your problem

The file is so small. Its size is only 100MB.The file parsing is too slow.

Image

@qiufeihong2018 qiufeihong2018 added the question Further information is requested label Feb 20, 2025
@Snify89
Copy link

Snify89 commented Feb 20, 2025

"Only" 100MB for a PDF, is not common for a document (3 in parallel)
Thus, this might take a while, depending on your settings and hardware.
Ragflow tries it's best in perfomance and efficiency to parse and retrieve.
Please be patient and/or provide more info about your issue.

@igorperic17
Copy link

Feel free to look at the logs of your LLM provider to see what's actually happening under the hood. I use LM Studio and besides being useful it is quite interesting to see all the stuff RAGFlow does while parsing.

@qiufeihong2018
Copy link
Contributor Author

I closed all the other tasks and only left one. After working on the parsing all night, it's only reached 0.3.

Image

@qiufeihong2018
Copy link
Contributor Author

The file size has shrunk to 16KB.
Image

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested
Projects
None yet
Development

No branches or pull requests

3 participants