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

Add ability to force reprocess of document #69

Open
paradizelost opened this issue Jan 8, 2025 · 10 comments
Open

Add ability to force reprocess of document #69

paradizelost opened this issue Jan 8, 2025 · 10 comments

Comments

@paradizelost
Copy link

it appears that once the system has processed a document they get added to processed_documents and do not get reprocessed when changes to the prompt is made.

@thorschtn
Copy link

I support this. In the meantime, I work with a second paperlesNGX and a second paperless-ai-instance for testing and development purposes and simply delete the paperless-ai database for a complete reindex.

@MagnusHL
Copy link

MagnusHL commented Jan 8, 2025

+1

@clusterzx
Copy link
Owner

@MagnusHL @thorschtn

Big news!
Try the new update. There is a new playground where you can try all sorts of prompts you create and try them without changing something in paperless.

@mamema
Copy link

mamema commented Jan 8, 2025

tried it, already in the 1.46 release and also in the 2.0 release nothing happens when i click on playground (or chat), just spinning wheel (browser tab)

@TheBig-O
Copy link

TheBig-O commented Jan 8, 2025

I would also like this capability. It appears that many of my documents were skipped and there's no way to force them to be rescanned.

@MagnusHL
Copy link

MagnusHL commented Jan 8, 2025

Is loading in 2.0 here, maybe browser cache?
CleanShot 2025-01-08 at 19 39 30@2x

@paradizelost
Copy link
Author

in 2.0 both chat and playground are working for me just fine, i just need it to be able to re-run on the documents that still have the tag to process them

@mamema
Copy link

mamema commented Jan 8, 2025

yes its working, it just needs time, several minutes here. Dunno why, server is beefy as hell.....

@clusterzx
Copy link
Owner

It downloads the thumbnails, it maybe take some time. But normally it's blazing fast.

@masterjobberman
Copy link

masterjobberman commented Jan 9, 2025

+1 for this i made a change to the cron format part way through it has processed 16 out of 155 would like the ability to check for any files without the ai-processed tag and process them or just a reprocess all documents option
edit- deleting the documents.db-wal, .db-shm and .db files got it to start from scratch and reprocess all files for me

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

7 participants