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

llama_parse freezed when parsing word files (doc & docx) #144

Open
michalwelna0 opened this issue Apr 16, 2024 · 0 comments
Open

llama_parse freezed when parsing word files (doc & docx) #144

michalwelna0 opened this issue Apr 16, 2024 · 0 comments

Comments

@michalwelna0
Copy link

Providing word files to LlamaParse (doc & docx files) caused a situation where LLamaParse freezed trying to parse documents - console was showing printing dots (showing progress) as it is usually using LLamaParse, but the dots were going back and forth meaning parsing in progress. The process was never finished and after more than 20 minutes the parsing was aborted.
Situation only took place once providing some word files with PDFs, when only PDFs were provided, LlamaParse had no problem with parsing them. When problematic word files were converted to PDFs, parsing went successfully. The daily limit was no exceeded since I was able to parse only PDF files.
Problematic Word files are in Polish and contain not only plain text but some tables etc.

Running LlamaParse after a weekend on the same set of word files suprisingly was successfull and problem did not occur. Seems like strange case worth investigating. Here are a sample files that were passed when problem occurred.

8173_zalacznik_nr_1_-formularz_ofertowy.docx
8174_zalacznik_nr__2_-wykaz_uslug.docx
8175_zalacznik_nr__3-_wykaz_osob.docx

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

1 participant