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

42
tests/test_options.py Normal file
View File

@@ -0,0 +1,42 @@
from pathlib import Path
import pytest
from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
from docling.datamodel.base_models import ConversionStatus
from docling.datamodel.document import ConversionResult
from docling.datamodel.pipeline_options import PipelineOptions, TableFormerMode
from docling.document_converter import DocumentConverter
from .verify_utils import verify_conversion_result
@pytest.fixture
def test_doc_path():
return Path("./tests/data/2206.01062.pdf")
def get_converters_with_table_options():
for cell_matching in [True, False]:
for mode in [TableFormerMode.FAST, TableFormerMode.ACCURATE]:
pipeline_options = PipelineOptions()
pipeline_options.do_ocr = False
pipeline_options.do_table_structure = True
pipeline_options.table_structure_options.do_cell_matching = cell_matching
pipeline_options.table_structure_options.mode = mode
converter = DocumentConverter(
pipeline_options=pipeline_options,
pdf_backend=DoclingParseDocumentBackend,
)
yield converter
def test_e2e_conversions(test_doc_path):
for converter in get_converters_with_table_options():
print(f"converting {test_doc_path}")
doc_result: ConversionResult = converter.convert_single(test_doc_path)
assert doc_result.status == ConversionStatus.SUCCESS