mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +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 # For more details on the following options visit
# https://rapidai.github.io/RapidOCRDocs/install_usage/api/RapidOCR/ # 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 text_score: float = 0.5 # same default as rapidocr
use_det: Optional[bool] = None # 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: if self.enabled:
try: try:
from rapidocr_onnxruntime import RapidOCR # type: ignore from rapidocr import EngineType, RapidOCR # type: ignore
except ImportError: except ImportError:
raise 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." "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_cuda = str(AcceleratorDevice.CUDA.value).lower() in device
use_dml = accelerator_options.device == AcceleratorDevice.AUTO use_dml = accelerator_options.device == AcceleratorDevice.AUTO
intra_op_num_threads = accelerator_options.num_threads 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( self.reader = RapidOCR(
text_score=self.options.text_score, params={
cls_use_cuda=use_cuda, # Global settings (these are still correct)
rec_use_cuda=use_cuda, "Global.text_score": self.options.text_score,
det_use_cuda=use_cuda, # "Global.verbose": self.options.print_verbose,
det_use_dml=use_dml, # Detection model settings
cls_use_dml=use_dml, "Det.model_path": self.options.det_model_path,
rec_use_dml=use_dml, "Det.use_cuda": use_cuda,
intra_op_num_threads=intra_op_num_threads, "Det.use_dml": use_dml,
print_verbose=self.options.print_verbose, "Det.intra_op_num_threads": intra_op_num_threads,
det_model_path=self.options.det_model_path, # Classification model settings
cls_model_path=self.options.cls_model_path, "Cls.model_path": self.options.cls_model_path,
rec_model_path=self.options.rec_model_path, "Cls.use_cuda": use_cuda,
rec_keys_path=self.options.rec_keys_path, "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__( def __call__(
@@ -95,12 +113,15 @@ class RapidOcrModel(BaseOcrModel):
scale=self.scale, cropbox=ocr_rect scale=self.scale, cropbox=ocr_rect
) )
im = numpy.array(high_res_image) im = numpy.array(high_res_image)
result, _ = self.reader( result = self.reader(
im, im,
use_det=self.options.use_det, use_det=self.options.use_det,
use_cls=self.options.use_cls, use_cls=self.options.use_cls,
use_rec=self.options.use_rec, use_rec=self.options.use_rec,
) )
result = list(
zip(result.boxes.tolist(), result.txts, result.scores)
)
del high_res_image del high_res_image
del im del im

10
docs/examples/rapidocr_with_custom_models.py vendored
View File

@@ -1,6 +1,6 @@
import os import os
from huggingface_hub import snapshot_download from modelscope import snapshot_download
from docling.datamodel.pipeline_options import PdfPipelineOptions, RapidOcrOptions from docling.datamodel.pipeline_options import PdfPipelineOptions, RapidOcrOptions
from docling.document_converter import ( from docling.document_converter import (
@@ -17,17 +17,17 @@ def main():
# Download RappidOCR models from HuggingFace # Download RappidOCR models from HuggingFace
print("Downloading RapidOCR models") print("Downloading RapidOCR models")
download_path = snapshot_download(repo_id="SWHL/RapidOCR") download_path = snapshot_download(repo_id="RapidAI/RapidOCR")
# Setup RapidOcrOptions for english detection # Setup RapidOcrOptions for english detection
det_model_path = os.path.join( det_model_path = os.path.join(
download_path, "PP-OCRv4", "en_PP-OCRv3_det_infer.onnx" download_path, "onnx", "PP-OCRv5", "det", "ch_PP-OCRv5_server_det.onnx"
) )
rec_model_path = os.path.join( rec_model_path = os.path.join(
download_path, "PP-OCRv4", "ch_PP-OCRv4_rec_server_infer.onnx" download_path, "onnx", "PP-OCRv5", "rec", "ch_PP-OCRv5_rec_server_infer.onnx"
) )
cls_model_path = os.path.join( cls_model_path = os.path.join(
download_path, "PP-OCRv3", "ch_ppocr_mobile_v2.0_cls_train.onnx" download_path, "onnx", "PP-OCRv4", "cls", "ch_ppocr_mobile_v2.0_cls_infer.onnx"
) )
ocr_options = RapidOcrOptions( ocr_options = RapidOcrOptions(
det_model_path=det_model_path, det_model_path=det_model_path,

2
docs/installation/index.md vendored
View File

@@ -31,7 +31,7 @@ Works on macOS, Linux, and Windows, with support for both x86_64 and arm64 archi
| Tesseract | System dependency. See description for Tesseract and Tesserocr below. | `TesseractOcrOptions` | | Tesseract | System dependency. See description for Tesseract and Tesserocr below. | `TesseractOcrOptions` |
| Tesseract CLI | System dependency. See description below. | `TesseractCliOcrOptions` | | Tesseract CLI | System dependency. See description below. | `TesseractCliOcrOptions` |
| OcrMac | System dependency. See description below. | `OcrMacOptions` | | OcrMac | System dependency. See description below. | `OcrMacOptions` |
| [RapidOCR](https://github.com/RapidAI/RapidOCR) | Extra feature not included in Default Docling installation can be installed via `pip install rapidocr_onnxruntime` | `RapidOcrOptions` | | [RapidOCR](https://github.com/RapidAI/RapidOCR) | Extra feature not included in Default Docling installation can be installed via `pip install rapidocr onnxruntime` | `RapidOcrOptions` |
| [OnnxTR](https://github.com/felixdittrich92/OnnxTR) | Can be installed via the plugin system `pip install "docling-ocr-onnxtr[cpu]"`. Please take a look at [docling-OCR-OnnxTR](https://github.com/felixdittrich92/docling-OCR-OnnxTR).| `OnnxtrOcrOptions` | | [OnnxTR](https://github.com/felixdittrich92/OnnxTR) | Can be installed via the plugin system `pip install "docling-ocr-onnxtr[cpu]"`. Please take a look at [docling-OCR-OnnxTR](https://github.com/felixdittrich92/docling-OCR-OnnxTR).| `OnnxtrOcrOptions` |
The Docling `DocumentConverter` allows to choose the OCR engine with the `ocr_options` settings. For example The Docling `DocumentConverter` allows to choose the OCR engine with the `ocr_options` settings. For example

3
pyproject.toml
View File

@@ -96,8 +96,9 @@ vlm = [
'vllm (>=0.10.0,<1.0.0) ; python_version >= "3.10" and sys_platform == "linux" and platform_machine == "x86_64"', 'vllm (>=0.10.0,<1.0.0) ; python_version >= "3.10" and sys_platform == "linux" and platform_machine == "x86_64"',
] ]
rapidocr = [ rapidocr = [
'rapidocr-onnxruntime (>=1.4.0,<2.0.0) ; python_version < "3.13"', 'rapidocr (>=3.3,<4.0.0) ; python_version < "3.14"',
'onnxruntime (>=1.7.0,<2.0.0)', 'onnxruntime (>=1.7.0,<2.0.0)',
"modelscope>=1.29.0",
# 'onnxruntime (>=1.7.0,<2.0.0) ; python_version >= "3.10"', # 'onnxruntime (>=1.7.0,<2.0.0) ; python_version >= "3.10"',
# 'onnxruntime (>=1.7.0,<1.20.0) ; python_version < "3.10"', # 'onnxruntime (>=1.7.0,<1.20.0) ; python_version < "3.10"',
] ]

4
tests/test_backend_webp.py
View File

@@ -55,8 +55,8 @@ def test_e2e_webp_conversions():
TesseractCliOcrOptions(force_full_page_ocr=True, lang=["auto"]), TesseractCliOcrOptions(force_full_page_ocr=True, lang=["auto"]),
] ]
# rapidocr is only available for Python >=3.6,<3.13 # rapidocr is only available for Python >=3.6,<3.14
if sys.version_info < (3, 13): if sys.version_info < (3, 14):
engines.append(RapidOcrOptions()) engines.append(RapidOcrOptions())
engines.append(RapidOcrOptions(force_full_page_ocr=True)) engines.append(RapidOcrOptions(force_full_page_ocr=True))

1331
uv.lock generated
View File

File diff suppressed because it is too large Load Diff