mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-10 13:48:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: Upgrade to RapidOCR 3.x (#2088)

Browse Source 
* feat: exploring new version

* DCO Remediation Commit for Georg Heiler <georg.kf.heiler@gmail.com>

I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 5815c8f81b0e5ce400332597b6795e5a97ecf775

Signed-off-by: Georg Heiler <georg.kf.heiler@gmail.com>

* chore: autoformat

DCO Remediation Commit for Georg Heiler <georg.kf.heiler@gmail.com>

I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 5815c8f81b0e5ce400332597b6795e5a97ecf775

* feat: enable configurable runtime for rapidocr and handle new result better;

Signed-off-by: Georg Heiler <georg.kf.heiler@gmail.com>

* chore: fix linter

Signed-off-by: Georg Heiler <georg.kf.heiler@gmail.com>

* chore: use new server model

* chore:  change default engine type to onnx

* chore: tests update for new rapidocr

* fix: rebase from main and fix clashes

* DCO Remediation Commit for Georg Heiler <georg.kf.heiler@gmail.com>

I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 5815c8f81b0e5ce400332597b6795e5a97ecf775
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 02f9db85f562e5cdfda40c52fee55cfd4030d70a
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: a7bcb205faedb881f94a89b3bbd29cb31ccd54f0
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: a39482a98cbcff7a825c8321134732af0c65930a
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 63e9d717fa26951566b02761f3fdfc752c31f805
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: ef12a6ec1ea2846a8a8e2e776eeaa59c2a0c4dfe

Signed-off-by: Georg Heiler <georg.kf.heiler@gmail.com>

* DCO Remediation Commit for Georg Heiler <georg.kf.heiler@gmail.com>

I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 2222d2340387f8d9d66f3ca9d8e21a0945a44e7a
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: bc6a1dc507d7f146ec4797a2d3840414f46ac64d
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 56e0d67da7c57d4b5caf8eaef8dff7056c3efd32
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 871ca21271412006c76acf3c19426140efed3d50
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 7b1b77159da729d483a581a86c7309acba1712a7
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: a792a714a43e19a91b2b782f54621c1c5efda632

Signed-off-by: Georg Heiler <georg.kf.heiler@gmail.com>

* DCO Remediation Commit for Georg Heiler <georg.kf.heiler@gmail.com>

I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: d1fed26323ff829b716bc667fe69532839363e45
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 346ec1cad943765f886e5d17fb0a54221124689c
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 4d0bbe5bd6e9f7261b97362ff8823af244267089
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 34a5ad53892a7064a6bf35f890d344d464c78b2f
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 9151959db3ad53535011d1cfdcf9181fdf936bb1
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 8ef5536f2c098826c6c0a05190f8a80614c3f3cb

Signed-off-by: Georg Heiler <georg.kf.heiler@gmail.com>

* DCO Remediation Commit for Georg Heiler <georg.kf.heiler@gmail.com>

I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 7e18637a35
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 63fb8ff599
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 0cb9444fb8
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: 38940d9978
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: b6d461ac42
I, Georg Heiler <georg.kf.heiler@gmail.com>, hereby add my Signed-off-by to this commit: ee55eb3408

Signed-off-by: Georg Heiler <georg.kf.heiler@gmail.com>

---------

Signed-off-by: Georg Heiler <georg.kf.heiler@gmail.com>
This commit is contained in:
geoHeil
2025-08-25 13:10:33 +03:00
committed by GitHub
parent 2aef5cf328
commit 3f60a0fa78
7 changed files with 744 additions and 661 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docling/datamodel/pipeline_options.py
View File

@@ -99,6 +99,8 @@ class RapidOcrOptions(OcrOptions):
# For more details on the following options visit
# https://rapidai.github.io/RapidOCRDocs/install_usage/api/RapidOCR/
# https://rapidai.github.io/RapidOCRDocs/main/install_usage/rapidocr/usage/#__tabbed_3_4
backend: Literal["onnxruntime", "openvino", "paddle", "torch"] = "onnxruntime"
text_score: float = 0.5 # same default as rapidocr
use_det: Optional[bool] = None # same default as rapidocr

53
docling/models/rapid_ocr_model.py
View File

@@ -42,10 +42,10 @@ class RapidOcrModel(BaseOcrModel):
if self.enabled:
try:
from rapidocr_onnxruntime import RapidOCR # type: ignore
from rapidocr import EngineType, RapidOCR # type: ignore
except ImportError:
raise ImportError(
"RapidOCR is not installed. Please install it via `pip install rapidocr_onnxruntime` to use this OCR engine. "
"RapidOCR is not installed. Please install it via `pip install rapidocr onnxruntime` to use this OCR engine. "
"Alternatively, Docling has support for other OCR engines. See the documentation."
)
@@ -54,21 +54,39 @@ class RapidOcrModel(BaseOcrModel):
use_cuda = str(AcceleratorDevice.CUDA.value).lower() in device
use_dml = accelerator_options.device == AcceleratorDevice.AUTO
intra_op_num_threads = accelerator_options.num_threads
_ALIASES = {
"onnxruntime": EngineType.ONNXRUNTIME,
"openvino": EngineType.OPENVINO,
"paddle": EngineType.PADDLE,
"torch": EngineType.TORCH,
}
backend_enum = _ALIASES.get(self.options.backend, EngineType.ONNXRUNTIME)
self.reader = RapidOCR(
text_score=self.options.text_score,
cls_use_cuda=use_cuda,
rec_use_cuda=use_cuda,
det_use_cuda=use_cuda,
det_use_dml=use_dml,
cls_use_dml=use_dml,
rec_use_dml=use_dml,
intra_op_num_threads=intra_op_num_threads,
print_verbose=self.options.print_verbose,
det_model_path=self.options.det_model_path,
cls_model_path=self.options.cls_model_path,
rec_model_path=self.options.rec_model_path,
rec_keys_path=self.options.rec_keys_path,
params={
# Global settings (these are still correct)
"Global.text_score": self.options.text_score,
# "Global.verbose": self.options.print_verbose,
# Detection model settings
"Det.model_path": self.options.det_model_path,
"Det.use_cuda": use_cuda,
"Det.use_dml": use_dml,
"Det.intra_op_num_threads": intra_op_num_threads,
# Classification model settings
"Cls.model_path": self.options.cls_model_path,
"Cls.use_cuda": use_cuda,
"Cls.use_dml": use_dml,
"Cls.intra_op_num_threads": intra_op_num_threads,
# Recognition model settings
"Rec.model_path": self.options.rec_model_path,
"Rec.keys_path": self.options.rec_keys_path,
"Rec.use_cuda": use_cuda,
"Rec.use_dml": use_dml,
"Rec.intra_op_num_threads": intra_op_num_threads,
"Det.engine_type": backend_enum,
"Cls.engine_type": backend_enum,
"Rec.engine_type": backend_enum,
}
)
def __call__(
@@ -95,12 +113,15 @@ class RapidOcrModel(BaseOcrModel):
scale=self.scale, cropbox=ocr_rect
)
im = numpy.array(high_res_image)
result, _ = self.reader(
result = self.reader(
im,
use_det=self.options.use_det,
use_cls=self.options.use_cls,
use_rec=self.options.use_rec,
)
result = list(
zip(result.boxes.tolist(), result.txts, result.scores)
)
del high_res_image
del im