mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-26 20:14:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

Cleanup

Browse Source 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer 2024-09-19 17:00:05 +02:00
parent 6ea6f29516
commit f6edd926fc
5 changed files with 8 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Dockerfile
View File

@ -16,7 +16,7 @@ ENV TORCH_HOME=/tmp/
COPY examples/minimal.py /root/minimal.py COPY examples/minimal.py /root/minimal.py
#RUN python -c 'from deepsearch_glm.utils.load_pretrained_models import load_pretrained_nlp_models; load_pretrained_nlp_models(verbose=True);' RUN python -c 'from deepsearch_glm.utils.load_pretrained_models import load_pretrained_nlp_models; load_pretrained_nlp_models(verbose=True);'
RUN python -c 'from docling.document_converter import DocumentConverter; artifacts_path = DocumentConverter.download_models_hf(force=True);' RUN python -c 'from docling.document_converter import DocumentConverter; artifacts_path = DocumentConverter.download_models_hf(force=True);'
# On container environments, always set a thread budget to avoid undesired thread congestion. # On container environments, always set a thread budget to avoid undesired thread congestion.

3
docling/cli/main.py
View File

@ -12,8 +12,9 @@ from pydantic import AnyUrl
from docling.backend.docling_parse_backend import DoclingParseDocumentBackend from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
from docling.datamodel.base_models import ConversionStatus, PipelineOptions from docling.datamodel.base_models import ConversionStatus
from docling.datamodel.document import ConversionResult, DocumentConversionInput from docling.datamodel.document import ConversionResult, DocumentConversionInput
from docling.datamodel.pipeline_options import PipelineOptions
from docling.document_converter import DocumentConverter from docling.document_converter import DocumentConverter
warnings.filterwarnings(action="ignore", category=UserWarning, module="pydantic|torch") warnings.filterwarnings(action="ignore", category=UserWarning, module="pydantic|torch")

4
docling/datamodel/document.py
View File

@ -10,8 +10,8 @@ from docling_core.types import FileInfoObject as DsFileInfoObject
from docling_core.types import PageDimensions, PageReference, Prov, Ref from docling_core.types import PageDimensions, PageReference, Prov, Ref
from docling_core.types import Table as DsSchemaTable from docling_core.types import Table as DsSchemaTable
from docling_core.types import TableCell from docling_core.types import TableCell
from docling_core.types.legacy.base import BoundingBox as DsBoundingBox from docling_core.types.doc.base import BoundingBox as DsBoundingBox
from docling_core.types.legacy.base import Figure from docling_core.types.doc.base import Figure
from pydantic import BaseModel from pydantic import BaseModel
from typing_extensions import deprecated from typing_extensions import deprecated

3
tests/test_e2e_conversion.py
View File

@ -1,9 +1,8 @@
from pathlib import Path from pathlib import Path
from docling.backend.docling_parse_backend import DoclingParseDocumentBackend from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
from docling.datamodel.base_models import PipelineOptions
from docling.datamodel.document import ConversionResult from docling.datamodel.document import ConversionResult
from docling.datamodel.pipeline_options import PipelineOptions
from docling.document_converter import DocumentConverter from docling.document_converter import DocumentConverter
from .verify_utils import verify_conversion_result from .verify_utils import verify_conversion_result

3
tests/test_interfaces.py
View File

@ -5,8 +5,9 @@ import pytest
from docling.backend.docling_parse_backend import DoclingParseDocumentBackend from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
from docling.datamodel.base_models import DocumentStream, PipelineOptions from docling.datamodel.base_models import DocumentStream
from docling.datamodel.document import ConversionResult, DocumentConversionInput from docling.datamodel.document import ConversionResult, DocumentConversionInput
from docling.datamodel.pipeline_options import PipelineOptions
from docling.document_converter import DocumentConverter from docling.document_converter import DocumentConverter
from .verify_utils import verify_conversion_result from .verify_utils import verify_conversion_result