mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-27 04:24:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

add GlmOptions

Browse Source 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi 2024-10-11 13:03:38 +02:00
parent 786b89efd9
commit 94b5e1532d
2 changed files with 15 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
docling/models/ds_glm_model.py
View File

@ -14,23 +14,24 @@ from docling_core.types import Ref
from docling_core.types.experimental import BoundingBox, CoordOrigin from docling_core.types.experimental import BoundingBox, CoordOrigin
from docling_core.types.experimental.document import DoclingDocument from docling_core.types.experimental.document import DoclingDocument
from PIL import ImageDraw from PIL import ImageDraw
from pydantic import BaseModel
from docling.datamodel.base_models import Cluster from docling.datamodel.base_models import Cluster
from docling.datamodel.document import ConversionResult from docling.datamodel.document import ConversionResult
class GlmModel: class GlmOptions(BaseModel):
def __init__(self, config): create_legacy_output: bool = True
self.config = config model_names: str = "" # e.g. "language;term;reference"
self.create_legacy_output = config.get("create_legacy_output", True)
class GlmModel:
def __init__(self, options: GlmOptions):
self.options = options
self.create_legacy_output = self.options.create_legacy_output
self.model_names = self.config.get(
"model_names", ""
) # "language;term;reference"
load_pretrained_nlp_models() load_pretrained_nlp_models()
# model = init_nlp_model(model_names="language;term;reference") self.model = init_nlp_model(model_names=self.options.model_names)
model = init_nlp_model(model_names=self.model_names)
self.model = model
def __call__( def __call__(
self, conv_res: ConversionResult self, conv_res: ConversionResult

6
docling/pipeline/standard_pdf_model_pipeline.py
View File

@ -13,7 +13,7 @@ from docling.datamodel.pipeline_options import (
TesseractOcrOptions, TesseractOcrOptions,
) )
from docling.models.base_ocr_model import BaseOcrModel from docling.models.base_ocr_model import BaseOcrModel
from docling.models.ds_glm_model import GlmModel from docling.models.ds_glm_model import GlmModel, GlmOptions
from docling.models.easyocr_model import EasyOcrModel from docling.models.easyocr_model import EasyOcrModel
from docling.models.layout_model import LayoutModel from docling.models.layout_model import LayoutModel
from docling.models.page_assemble_model import PageAssembleModel, PageAssembleOptions from docling.models.page_assemble_model import PageAssembleModel, PageAssembleOptions
@ -42,7 +42,9 @@ class StandardPdfModelPipeline(PaginatedModelPipeline):
self.artifacts_path = Path(artifacts_path) self.artifacts_path = Path(artifacts_path)
self.glm_model = GlmModel( self.glm_model = GlmModel(
config={"create_legacy_output": pipeline_options.create_legacy_output} options=GlmOptions(
create_legacy_output=pipeline_options.create_legacy_output
)
) )
if ocr_model := self.get_ocr_model() is None: if ocr_model := self.get_ocr_model() is None: