mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-13 07:08:19 +00:00
Code Issues Packages Projects Releases Wiki Activity

rename and refactor *model*

Browse Source 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi
2024-10-11 16:57:40 +02:00
parent 6c9f869dc7
commit 98f1a4597e
6 changed files with 32 additions and 417 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/custom_convert.py
View File

@@ -12,7 +12,7 @@ from docling.datamodel.pipeline_options import (
TesseractOcrOptions,
)
from docling.document_converter import DocumentConverter, FormatOption, PdfFormatOption
from docling.pipeline.standard_pdf_model_pipeline import StandardPdfModelPipeline
from docling.pipeline.standard_pdf_pipeline import StandardPdfPipeline
_log = logging.getLogger(__name__)

18
examples/run_with_formats.py
View File

@@ -9,8 +9,8 @@ from docling.document_converter import (
PdfFormatOption,
WordFormatOption,
)
from docling.pipeline.simple_model_pipeline import SimpleModelPipeline
from docling.pipeline.standard_pdf_model_pipeline import StandardPdfModelPipeline
from docling.pipeline.simple_pipeline import SimplePipeline
from docling.pipeline.standard_pdf_pipeline import StandardPdfPipeline
_log = logging.getLogger(__name__)
@@ -30,7 +30,7 @@ input_paths = [
## to customize use:
doc_converter = DocumentConverter( # all of the below is optional, has internal defaults.
formats=[
allowed_formats=[
InputFormat.PDF,
# InputFormat.IMAGE,
InputFormat.DOCX,
@@ -39,10 +39,10 @@ doc_converter = DocumentConverter( # all of the below is optional, has internal
], # whitelist formats, other files are ignored.
format_options={
InputFormat.PDF: PdfFormatOption(
pipeline_cls=StandardPdfModelPipeline, backend=PyPdfiumDocumentBackend
pipeline_cls=StandardPdfPipeline, backend=PyPdfiumDocumentBackend
), # PdfFormatOption(backend=PyPdfiumDocumentBackend),
InputFormat.DOCX: WordFormatOption(
pipeline_cls=SimpleModelPipeline # , backend=MsWordDocumentBackend
pipeline_cls=SimplePipeline # , backend=MsWordDocumentBackend
),
# InputFormat.IMAGE: PdfFormatOption(),
},
@@ -51,9 +51,9 @@ doc_converter = DocumentConverter( # all of the below is optional, has internal
doc_converter = DocumentConverter( # all of the below is optional, has internal defaults.
pdf=None,
docx=WordFormatOption(
pipeline_cls=SimpleModelPipeline # , backend=MsWordDocumentBackend
pipeline_cls=SimplePipeline # , backend=MsWordDocumentBackend
),
formats=[
allowed_formats=[
InputFormat.PDF,
# InputFormat.IMAGE,
InputFormat.DOCX,
@@ -62,10 +62,10 @@ doc_converter = DocumentConverter( # all of the below is optional, has internal
], # whitelist formats, other files are ignored.
format_options={
InputFormat.PDF: PdfFormatOption(
pipeline_cls=StandardPdfModelPipeline, backend=PyPdfiumDocumentBackend
pipeline_cls=StandardPdfPipeline, backend=PyPdfiumDocumentBackend
), # PdfFormatOption(backend=PyPdfiumDocumentBackend),
InputFormat.DOCX: WordFormatOption(
pipeline_cls=SimpleModelPipeline # , backend=MsWordDocumentBackend
pipeline_cls=SimplePipeline # , backend=MsWordDocumentBackend
),
# InputFormat.IMAGE: PdfFormatOption(),
},