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

Some visual feedback is needed (progress bar?) while uploading document to be used for RAG #2190

Open
kha84 opened this issue May 11, 2024 · 1 comment

Comments

@kha84
Copy link

kha84 commented May 11, 2024

Is your feature request related to a problem? Please describe.
I'm thrilled to see the RAG feature has finally came to my beloved web UI. But when I upload some big documents (say 15 Mb of PDF) I get no visual feedback on what is happening - the front-end doesn't give any clues and the file I have just submitted doesn't show anywhere until it's finally processed. I know such big documents take a while to be processed - and I see that from docker logs (open-web-ui is installed via docker), but this is the only how I can track the progress of creating embeddings. And only once the document is processed it appears in the list - which is the only visual indication I get from UI.

Describe the solution you'd like
It would be great to see some additional visual indicator showing a processing progress, denoting that nothing has stucked or frozen, but it's still being processed, after new document was added. Ideally with some kind of progress bar. I found a place in frontend code where it's done, but my JS/TS knowledge is limited to make proper changes -

export const uploadDocToVectorDB = async (token: string, collection_name: string, file: File) => {

Describe alternatives you've considered
If there's no easy way to get a progress indicator, at least to introduce some modal window saying "please wait till your document will be processed"

@AdaptiveStep
Copy link

Yeah, maybe a little "miniwizard" for importing documents would be in order. It seems to completely ignore the content of the PDF if it only contains one image per page. This way it could show how much storage it takes, and so on..

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

No branches or pull requests

2 participants