NeoAnd/Docling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: enrichment models batch size and expose picture classifier (#878)

Browse Source 
* expose picture classifier in CLI

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* use different batch size in each model

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* remove batch size from CLI

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* cleanup imports

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi
2025-02-05 11:46:01 +01:00
committed by GitHub
parent 17448163e7
commit 5ad6de0560
4 changed files with 13 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docling/pipeline/base_pipeline.py
View File

@@ -79,7 +79,7 @@ class BasePipeline(ABC):
for model in self.enrichment_pipe:
for element_batch in chunkify(
_prepare_elements(conv_res, model),
settings.perf.elements_batch_size,
model.elements_batch_size,
):
for element in model(
doc=conv_res.document, element_batch=element_batch