fix: Code styling

Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
This commit is contained in:
Nikos Livathinos 2024-12-08 22:14:48 +01:00
parent 64c7382880
commit 04977aac9f
3 changed files with 11 additions and 5 deletions

View File

@ -343,9 +343,9 @@ def convert(
raise RuntimeError(f"Unexpected PDF backend type {pdf_backend}")
pdf_format_option = PdfFormatOption(
pipeline_options=pipeline_options,
backend=backend, # pdf_backend
)
pipeline_options=pipeline_options,
backend=backend, # pdf_backend
)
format_options: Dict[InputFormat, FormatOption] = {
InputFormat.PDF: pdf_format_option,
InputFormat.IMAGE: pdf_format_option,

View File

@ -143,7 +143,11 @@ class PdfPipelineOptions(PipelineOptions):
table_structure_options: TableStructureOptions = TableStructureOptions()
ocr_options: Union[
EasyOcrOptions, TesseractCliOcrOptions, TesseractOcrOptions, OcrMacOptions, RapidOcrOptions
EasyOcrOptions,
TesseractCliOcrOptions,
TesseractOcrOptions,
OcrMacOptions,
RapidOcrOptions,
] = Field(EasyOcrOptions(), discriminator="kind")
images_scale: float = 1.0

View File

@ -96,11 +96,13 @@ class StandardPdfPipeline(PaginatedPipeline):
def download_models_hf(
local_dir: Optional[Path] = None, force: bool = False
) -> Path:
from functools import partialmethod
from huggingface_hub import snapshot_download
# Disable tqdm prints used by HF
from tqdm import tqdm
from functools import partialmethod
tqdm.__init__ = partialmethod(tqdm.__init__, disable=True)
download_path = snapshot_download(