From f6edd926fc12d8f91f713dfaab9245fd4b493d23 Mon Sep 17 00:00:00 2001 From: Christoph Auer Date: Thu, 19 Sep 2024 17:00:05 +0200 Subject: [PATCH] Cleanup Signed-off-by: Christoph Auer --- Dockerfile | 2 +- docling/cli/main.py | 3 ++- docling/datamodel/document.py | 4 ++-- tests/test_e2e_conversion.py | 3 +-- tests/test_interfaces.py | 3 ++- 5 files changed, 8 insertions(+), 7 deletions(-) diff --git a/Dockerfile b/Dockerfile index a7e9bc6f..298291e9 100644 --- a/Dockerfile +++ b/Dockerfile @@ -16,7 +16,7 @@ ENV TORCH_HOME=/tmp/ 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);' # On container environments, always set a thread budget to avoid undesired thread congestion. diff --git a/docling/cli/main.py b/docling/cli/main.py index c8a8f3ac..ab541b3b 100644 --- a/docling/cli/main.py +++ b/docling/cli/main.py @@ -12,8 +12,9 @@ from pydantic import AnyUrl from docling.backend.docling_parse_backend import DoclingParseDocumentBackend 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.pipeline_options import PipelineOptions from docling.document_converter import DocumentConverter warnings.filterwarnings(action="ignore", category=UserWarning, module="pydantic|torch") diff --git a/docling/datamodel/document.py b/docling/datamodel/document.py index 6669b5b6..19fc40cd 100644 --- a/docling/datamodel/document.py +++ b/docling/datamodel/document.py @@ -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 Table as DsSchemaTable from docling_core.types import TableCell -from docling_core.types.legacy.base import BoundingBox as DsBoundingBox -from docling_core.types.legacy.base import Figure +from docling_core.types.doc.base import BoundingBox as DsBoundingBox +from docling_core.types.doc.base import Figure from pydantic import BaseModel from typing_extensions import deprecated diff --git a/tests/test_e2e_conversion.py b/tests/test_e2e_conversion.py index a4ecff16..c37c027a 100644 --- a/tests/test_e2e_conversion.py +++ b/tests/test_e2e_conversion.py @@ -1,9 +1,8 @@ from pathlib import Path 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.pipeline_options import PipelineOptions from docling.document_converter import DocumentConverter from .verify_utils import verify_conversion_result diff --git a/tests/test_interfaces.py b/tests/test_interfaces.py index 9475bcef..0572c50e 100644 --- a/tests/test_interfaces.py +++ b/tests/test_interfaces.py @@ -5,8 +5,9 @@ import pytest from docling.backend.docling_parse_backend import DoclingParseDocumentBackend 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.pipeline_options import PipelineOptions from docling.document_converter import DocumentConverter from .verify_utils import verify_conversion_result