mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-08-02 15:32:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

more renaming

Browse Source 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi 2025-02-07 10:12:38 +01:00
parent b6ed0b34cd
commit 90f0428a62
6 changed files with 11 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docling/datamodel/pipeline_options.py
View File

@ -218,7 +218,7 @@ class PictureDescriptionVlmOptions(PictureDescriptionBaseOptions):
smolvlm_picture_description = PictureDescriptionVlmOptions( smolvlm_picture_description = PictureDescriptionVlmOptions(
repo_id="HuggingFaceTB/SmolVLM-256M-Instruct" repo_id="HuggingFaceTB/SmolVLM-256M-Instruct"
) )
# phi_pic_desc = PictureDescriptionVlmOptions(repo_id="microsoft/Phi-3-vision-128k-instruct") # phi_picture_description = PictureDescriptionVlmOptions(repo_id="microsoft/Phi-3-vision-128k-instruct")
granite_picture_description = PictureDescriptionVlmOptions( granite_picture_description = PictureDescriptionVlmOptions(
repo_id="ibm-granite/granite-vision-3.1-2b-preview", repo_id="ibm-granite/granite-vision-3.1-2b-preview",
prompt="What is shown in this image?", prompt="What is shown in this image?",

2
docling/models/pic_description_api_model.py → docling/models/picture_description_api_model.py
View File

@ -12,7 +12,7 @@ from PIL import Image
from pydantic import BaseModel, ConfigDict from pydantic import BaseModel, ConfigDict
from docling.datamodel.pipeline_options import PictureDescriptionApiOptions from docling.datamodel.pipeline_options import PictureDescriptionApiOptions
from docling.models.pic_description_base_model import PictureDescriptionBaseModel from docling.models.picture_description_base_model import PictureDescriptionBaseModel
_log = logging.getLogger(__name__) _log = logging.getLogger(__name__)

0
docling/models/pic_description_base_model.py → docling/models/picture_description_base_model.py
View File

5
docling/models/pic_description_vlm_model.py → docling/models/picture_description_vlm_model.py
View File

@ -1,6 +1,5 @@
import json
from pathlib import Path from pathlib import Path
from typing import Iterable, List, Optional, Union from typing import Iterable, Optional, Union
from PIL import Image from PIL import Image
@ -8,7 +7,7 @@ from docling.datamodel.pipeline_options import (
AcceleratorOptions, AcceleratorOptions,
PictureDescriptionVlmOptions, PictureDescriptionVlmOptions,
) )
from docling.models.pic_description_base_model import PictureDescriptionBaseModel from docling.models.picture_description_base_model import PictureDescriptionBaseModel
from docling.utils.accelerator_utils import decide_device from docling.utils.accelerator_utils import decide_device

12
docling/pipeline/standard_pdf_pipeline.py
View File

@ -36,9 +36,9 @@ from docling.models.page_preprocessing_model import (
PagePreprocessingModel, PagePreprocessingModel,
PagePreprocessingOptions, PagePreprocessingOptions,
) )
from docling.models.pic_description_api_model import PictureDescriptionApiModel from docling.models.picture_description_api_model import PictureDescriptionApiModel
from docling.models.pic_description_base_model import PictureDescriptionBaseModel from docling.models.picture_description_base_model import PictureDescriptionBaseModel
from docling.models.pic_description_vlm_model import PictureDescriptionVlmModel from docling.models.picture_description_vlm_model import PictureDescriptionVlmModel
from docling.models.rapid_ocr_model import RapidOcrModel from docling.models.rapid_ocr_model import RapidOcrModel
from docling.models.table_structure_model import TableStructureModel from docling.models.table_structure_model import TableStructureModel
from docling.models.tesseract_ocr_cli_model import TesseractOcrCliModel from docling.models.tesseract_ocr_cli_model import TesseractOcrCliModel
@ -101,7 +101,7 @@ class StandardPdfPipeline(PaginatedPipeline):
] ]
# Picture description model # Picture description model
if (pic_desc_model := self.get_pic_description_model()) is None: if (picture_description_model := self.get_picture_description_model()) is None:
raise RuntimeError( raise RuntimeError(
f"The specified picture description kind is not supported: {pipeline_options.picture_description_options.kind}." f"The specified picture description kind is not supported: {pipeline_options.picture_description_options.kind}."
) )
@ -126,7 +126,7 @@ class StandardPdfPipeline(PaginatedPipeline):
accelerator_options=pipeline_options.accelerator_options, accelerator_options=pipeline_options.accelerator_options,
), ),
# Document Picture description # Document Picture description
pic_desc_model, picture_description_model,
] ]
if ( if (
@ -188,7 +188,7 @@ class StandardPdfPipeline(PaginatedPipeline):
) )
return None return None
def get_pic_description_model( def get_picture_description_model(
self, artifacts_path: Optional[Path] = None self, artifacts_path: Optional[Path] = None
) -> Optional[PictureDescriptionBaseModel]: ) -> Optional[PictureDescriptionBaseModel]:
if isinstance( if isinstance(

2
docs/examples/pictures_description.py
View File

@ -20,7 +20,7 @@ def main():
pipeline_options = PdfPipelineOptions() pipeline_options = PdfPipelineOptions()
pipeline_options.do_picture_description = True pipeline_options.do_picture_description = True
pipeline_options.picture_description_options = smolvlm_picture_description pipeline_options.picture_description_options = smolvlm_picture_description
# pipeline_options.picture_description_options = granite_pic_desc # pipeline_options.picture_description_options = granite_picture_description
pipeline_options.picture_description_options.prompt = ( pipeline_options.picture_description_options.prompt = (
"Describe the image in three sentences. Be consise and accurate." "Describe the image in three sentences. Be consise and accurate."