mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add DoclingParseV3 backend implementation

Browse Source 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer
2025-02-06 20:29:44 +01:00
parent ed74fe2ec0
commit 3f0e98b1ad
3 changed files with 288 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
docs/examples/batch_convert.py
View File

@@ -6,10 +6,11 @@ from typing import Iterable
import yaml
from docling.datamodel.base_models import ConversionStatus
from docling.backend.docling_parse_v3_backend import DoclingParseV3DocumentBackend
from docling.datamodel.base_models import ConversionStatus, InputFormat
from docling.datamodel.document import ConversionResult
from docling.datamodel.settings import settings
from docling.document_converter import DocumentConverter
from docling.document_converter import DocumentConverter, PdfFormatOption
_log = logging.getLogger(__name__)
@@ -103,10 +104,11 @@ def main():
logging.basicConfig(level=logging.INFO)
input_doc_paths = [
Path("./tests/data/2206.01062.pdf"),
Path("./tests/data/2203.01017v2.pdf"),
Path("./tests/data/2305.03393v1.pdf"),
Path("./tests/data/redp5110_sampled.pdf"),
Path("tests/data/redp5110_sampled.pdf"),
# Path("./tests/data/2206.01062.pdf"),
# Path("./tests/data/2203.01017v2.pdf"),
# Path("./tests/data/2305.03393v1.pdf"),
# Path("./tests/data/redp5110_sampled.pdf"),
]
# buf = BytesIO(Path("./test/data/2206.01062.pdf").open("rb").read())
@@ -119,13 +121,17 @@ def main():
# settings.debug.visualize_tables = True
# settings.debug.visualize_cells = True
doc_converter = DocumentConverter()
doc_converter = DocumentConverter(
format_options={
InputFormat.PDF: PdfFormatOption(backend=DoclingParseV3DocumentBackend)
}
)
start_time = time.time()
conv_results = doc_converter.convert_all(
input_doc_paths,
raises_on_error=False, # to let conversion run through all and examine results at the end
raises_on_error=True, # to let conversion run through all and examine results at the end
)
success_count, partial_success_count, failure_count = export_documents(
conv_results, output_dir=Path("scratch")