NeoAnd/Docling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

perf: Move expensive imports closer to usage (#1863)

Browse Source 
* Move expensive imports closer to usage

Signed-off-by: William Easton <bill.easton@elastic.co>

* DCO Remediation Commit for William Easton <bill.easton@elastic.co>

I, William Easton <bill.easton@elastic.co>, hereby add my Signed-off-by to this commit: 8a7412ce5bb131a01bb6403067aeb948c9093b0b

Signed-off-by: William Easton <bill.easton@elastic.co>

* formatting fixes

Signed-off-by: William Easton <bill.easton@elastic.co>

* DCO Remediation Commit for William Easton <bill.easton@elastic.co>

I, William Easton <bill.easton@elastic.co>, hereby add my Signed-off-by to this commit: 8a7412ce5bb131a01bb6403067aeb948c9093b0b
I, William Easton <bill.easton@elastic.co>, hereby add my Signed-off-by to this commit: 963e34325071db5e844841f10c27b396a054a0a1

Signed-off-by: William Easton <bill.easton@elastic.co>

* Fix baseocrmodel test issue

Signed-off-by: William Easton <bill.easton@elastic.co>

---------

Signed-off-by: William Easton <bill.easton@elastic.co>
This commit is contained in:
William Easton
2025-07-01 15:27:17 -05:00
committed by GitHub
parent 56a0e104f7
commit 3089cf2d26
5 changed files with 22 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
docling/models/base_ocr_model.py
View File

@@ -3,14 +3,13 @@ import logging
from abc import abstractmethod
from collections.abc import Iterable
from pathlib import Path
from typing import List, Optional, Type
from typing import TYPE_CHECKING, List, Optional, Type
import numpy as np
from docling_core.types.doc import BoundingBox, CoordOrigin
from docling_core.types.doc.page import TextCell
from PIL import Image, ImageDraw
from rtree import index
from scipy.ndimage import binary_dilation, find_objects, label
from docling.datamodel.accelerator_options import AcceleratorOptions
from docling.datamodel.base_models import Page
@@ -31,11 +30,16 @@ class BaseOcrModel(BasePageModel, BaseModelWithOptions):
options: OcrOptions,
accelerator_options: AcceleratorOptions,
):
# Make sure any delay/error from import occurs on ocr model init and not first use
from scipy.ndimage import binary_dilation, find_objects, label
self.enabled = enabled
self.options = options
# Computes the optimum amount and coordinates of rectangles to OCR on a given page
def get_ocr_rects(self, page: Page) -> List[BoundingBox]:
from scipy.ndimage import binary_dilation, find_objects, label
BITMAP_COVERAGE_TRESHOLD = 0.75
assert page.size is not None