2422f706a1
--------- Signed-off-by: Maxim Lysak <mly@zurich.ibm.com> Co-authored-by: Maxim Lysak <mly@zurich.ibm.com>
40 lines
1.5 KiB
Python
40 lines
1.5 KiB
Python
from pathlib import Path
|
|
|
|
from docling.datamodel.pipeline_options import PipelineOptions
|
|
from docling.models.easyocr_model import EasyOcrModel
|
|
from docling.models.layout_model import LayoutModel
|
|
from docling.models.table_structure_model import TableStructureModel
|
|
from docling.pipeline.base_model_pipeline import BaseModelPipeline
|
|
|
|
|
|
class StandardModelPipeline(BaseModelPipeline):
|
|
_layout_model_path = "model_artifacts/layout/beehive_v0.0.5_pt"
|
|
_table_model_path = "model_artifacts/tableformer"
|
|
|
|
def __init__(self, artifacts_path: Path, pipeline_options: PipelineOptions):
|
|
super().__init__(artifacts_path, pipeline_options)
|
|
|
|
self.model_pipe = [
|
|
EasyOcrModel(
|
|
config={
|
|
"lang": ["fr", "de", "es", "en"],
|
|
"enabled": pipeline_options.do_ocr,
|
|
}
|
|
),
|
|
LayoutModel(
|
|
config={
|
|
"artifacts_path": artifacts_path
|
|
/ StandardModelPipeline._layout_model_path
|
|
}
|
|
),
|
|
TableStructureModel(
|
|
config={
|
|
"artifacts_path": artifacts_path
|
|
/ StandardModelPipeline._table_model_path,
|
|
"enabled": pipeline_options.do_table_structure,
|
|
"mode": pipeline_options.table_structure_options.mode,
|
|
"do_cell_matching": pipeline_options.table_structure_options.do_cell_matching,
|
|
}
|
|
),
|
|
]
|