feat: Support tableformer model choice (#90)

* Support tableformer model choice

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update datamodel structure

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update docs

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Cleanup

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Add test unit for table options

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Ensure import backwards-compatibility for PipelineOptions

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update README

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Adjust parameters on custom_convert

Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>

* Update Dockerfile

Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>

---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>
This commit is contained in:
Christoph Auer
2024-09-26 21:37:08 +02:00
committed by GitHub
parent 39977b5631
commit d6df76f90b
16 changed files with 711 additions and 592 deletions

View File

@@ -1,7 +1,8 @@
from pathlib import Path
from typing import Callable, Iterable, List
from docling.datamodel.base_models import Page, PipelineOptions
from docling.datamodel.base_models import Page
from docling.datamodel.pipeline_options import PipelineOptions
class BaseModelPipeline:

View File

@@ -1,6 +1,6 @@
from pathlib import Path
from docling.datamodel.base_models import PipelineOptions
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
@@ -32,6 +32,7 @@ class StandardModelPipeline(BaseModelPipeline):
"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,
}
),