Skip to content

fix: skip picture description model init when disabled #3052

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.

Sign up for GitHub

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

Closed
Br1an67 wants to merge 1 commit into from
+14 −10
Closed

fix: skip picture description model init when disabled #3052

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 14 additions & 10 deletions docling/pipeline/base_pipeline.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -152,15 +152,17 @@ def __init__(self, pipeline_options: ConvertPipelineOptions):

# ------ Common enrichment models working on all backends

# Picture description model
if (
picture_description_model := self._get_picture_description_model(
# Picture description model (only instantiate when enabled to avoid
# requiring optional VLM dependencies for simple conversions)
picture_description_model = None
if pipeline_options.do_picture_description:
picture_description_model = self._get_picture_description_model(
artifacts_path=self.artifacts_path
)
) is None:
raise RuntimeError(
f"The specified picture description kind is not supported: {pipeline_options.picture_description_options.kind}."
)
if picture_description_model is None:
raise RuntimeError(
f"The specified picture description kind is not supported: {pipeline_options.picture_description_options.kind}."
)

self.enrichment_pipe = [
# Document Picture Classifier
Expand All @@ -171,16 +173,18 @@ def __init__(self, pipeline_options: ConvertPipelineOptions):
accelerator_options=pipeline_options.accelerator_options,
enable_remote_services=pipeline_options.enable_remote_services,
),
# Document Picture description
picture_description_model,
]
if picture_description_model is not None:
self.enrichment_pipe.append(picture_description_model)
self.enrichment_pipe.append(
# Document Chart Extraction
ChartExtractionModelGraniteVision(
enabled=pipeline_options.do_chart_extraction,
artifacts_path=self.artifacts_path,
options=ChartExtractionModelOptions(),
accelerator_options=pipeline_options.accelerator_options,
),
]
)

def _get_picture_description_model(
self, artifacts_path: Optional[Path] = None
Expand Down