docling-project / docling-project/docling
Is it possible to make the processing deterministic?
Open
question
triage/close-stale
- Dominant language
- Python
- Stars
- 66.4k
- Forks
- 4.8k
- Avg merge
- 3d 4h
- Merged PRs (30d)
- 98
Description
### Question
Is it possible to make the output of
```
from docling.document_converter import DocumentConverter
from time import time
source = "https://arxiv.org/pdf/2408.09869" # document per local path or URL
converter = DocumentConverter()
start = time()
result = converter.convert(source)
end = time()
doctags = result.document.export_to_doctags()
print(doctags)
print(f"Time taken: {end - start} seconds")
print(len(doctags))
```
deterministic across devices somehow?
Contributor guide
Assessment
This issue has not been assessed yet.