kreuzberg 3.11.0__py3-none-any.whl → 3.11.2__py3-none-any.whl

kreuzberg/_gmft.py

@@ -444,14 +444,26 @@ def _extract_tables_in_process(
                 cropped_image.save(img_bytes, format="PNG")
                 img_bytes.seek(0)
 
-                results.append(
-                    {
-                        "cropped_image_bytes": img_bytes.getvalue(),
-                        "page_number": cropped_table.page.page_number,
-                        "text": data_frame.to_markdown(),
-                        "df_csv": data_frame.to_csv(index=False),
-                    }
-                )
+                if data_frame.empty:
+                    results.append(
+                        {
+                            "cropped_image_bytes": img_bytes.getvalue(),
+                            "page_number": cropped_table.page.page_number,
+                            "text": data_frame.to_markdown(),
+                            "df_columns": data_frame.columns.tolist(),
+                            "df_csv": None,
+                        }
+                    )
+                else:
+                    results.append(
+                        {
+                            "cropped_image_bytes": img_bytes.getvalue(),
+                            "page_number": cropped_table.page.page_number,
+                            "text": data_frame.to_markdown(),
+                            "df_columns": None,
+                            "df_csv": data_frame.to_csv(index=False),
+                        }
+                    )
 
             result_queue.put((True, results))
 
@@ -532,7 +544,10 @@ def _extract_tables_isolated(
                 img = Image.open(io.BytesIO(table_dict["cropped_image_bytes"]))
                 import pandas as pd  # noqa: PLC0415
 
-                df = pd.read_csv(StringIO(table_dict["df_csv"]))
+                if table_dict["df_csv"] is None:
+                    df = pd.DataFrame(columns=table_dict["df_columns"])
+                else:
+                    df = pd.read_csv(StringIO(table_dict["df_csv"]))
 
                 tables.append(
                     TableData(
@@ -638,7 +653,10 @@ async def _extract_tables_isolated_async(
                 img = Image.open(io.BytesIO(table_dict["cropped_image_bytes"]))
                 import pandas as pd  # noqa: PLC0415
 
-                df = pd.read_csv(StringIO(table_dict["df_csv"]))
+                if table_dict["df_csv"] is None:
+                    df = pd.DataFrame(columns=table_dict["df_columns"])
+                else:
+                    df = pd.read_csv(StringIO(table_dict["df_csv"]))
 
                 tables.append(
                     TableData(

kreuzberg/_ocr/_easyocr.py

@@ -4,7 +4,6 @@ import warnings
 from dataclasses import dataclass
 from typing import TYPE_CHECKING, Any, ClassVar, Final, Literal
 
-import numpy as np
 from PIL import Image
 
 from kreuzberg._mime_types import PLAIN_TEXT_MIME_TYPE
@@ -188,6 +187,9 @@ class EasyOCRBackend(OCRBackend[EasyOCRConfig]):
 
         kwargs.pop("language", None)
         kwargs.pop("use_gpu", None)
+        kwargs.pop("device", None)
+        kwargs.pop("gpu_memory_limit", None)
+        kwargs.pop("fallback_to_cpu", None)
 
         try:
             result = await run_sync(
@@ -455,11 +457,16 @@ class EasyOCRBackend(OCRBackend[EasyOCRConfig]):
         Raises:
             OCRError: If OCR processing fails.
         """
+        import numpy as np  # noqa: PLC0415
+
         self._init_easyocr_sync(**kwargs)
 
         beam_width = kwargs.pop("beam_width")
         kwargs.pop("language", None)
         kwargs.pop("use_gpu", None)
+        kwargs.pop("device", None)
+        kwargs.pop("gpu_memory_limit", None)
+        kwargs.pop("fallback_to_cpu", None)
 
         try:
             result = self._reader.readtext(

kreuzberg/_ocr/_paddleocr.py

@@ -7,7 +7,6 @@ from importlib.util import find_spec
 from pathlib import Path
 from typing import TYPE_CHECKING, Any, ClassVar, Final, Literal
 
-import numpy as np
 from PIL import Image
 
 from kreuzberg._mime_types import PLAIN_TEXT_MIME_TYPE
@@ -380,6 +379,8 @@ class PaddleBackend(OCRBackend[PaddleOCRConfig]):
         Raises:
             OCRError: If OCR processing fails.
         """
+        import numpy as np  # noqa: PLC0415
+
         self._init_paddle_ocr_sync(**kwargs)
 
         if image.mode != "RGB":

{kreuzberg-3.11.0.dist-info → kreuzberg-3.11.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kreuzberg
-Version: 3.11.0
+Version: 3.11.2
 Summary: Document intelligence framework for Python - Extract text, metadata, and structured data from diverse file formats
 Project-URL: documentation, https://kreuzberg.dev
 Project-URL: homepage, https://github.com/Goldziher/kreuzberg
@@ -28,13 +28,13 @@ Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Topic :: Text Processing :: General
 Classifier: Typing :: Typed
 Requires-Python: >=3.10
-Requires-Dist: anyio>=4.9.0
+Requires-Dist: anyio>=4.10.0
 Requires-Dist: chardetng-py>=0.3.5
 Requires-Dist: exceptiongroup>=1.2.2; python_version < '3.11'
 Requires-Dist: html-to-markdown[lxml]>=1.9.0
-Requires-Dist: mcp>=1.12.3
+Requires-Dist: mcp>=1.13.0
 Requires-Dist: msgspec>=0.18.0
-Requires-Dist: playa-pdf>=0.6.4
+Requires-Dist: playa-pdf>=0.7.0
 Requires-Dist: psutil>=7.0.0
 Requires-Dist: pypdfium2==4.30.0
 Requires-Dist: python-calamine>=0.3.2
@@ -50,19 +50,19 @@ Requires-Dist: easyocr>=1.7.2; extra == 'all'
 Requires-Dist: fast-langdetect>=0.3.2; extra == 'all'
 Requires-Dist: gmft>=0.4.2; extra == 'all'
 Requires-Dist: keybert>=0.9.0; extra == 'all'
-Requires-Dist: litestar[opentelemetry,standard,structlog]>=2.16.0; extra == 'all'
+Requires-Dist: litestar[opentelemetry,standard,structlog]>=2.17.0; extra == 'all'
 Requires-Dist: mailparse>=1.0.15; extra == 'all'
-Requires-Dist: paddleocr>=3.1.0; extra == 'all'
+Requires-Dist: paddleocr>=3.1.1; extra == 'all'
 Requires-Dist: paddlepaddle>=3.1.0; extra == 'all'
 Requires-Dist: pandas>=2.3.1; extra == 'all'
-Requires-Dist: playa-pdf[crypto]>=0.6.4; extra == 'all'
+Requires-Dist: playa-pdf[crypto]>=0.7.0; extra == 'all'
 Requires-Dist: rich>=14.1.0; extra == 'all'
 Requires-Dist: semantic-text-splitter>=0.27.0; extra == 'all'
 Requires-Dist: setuptools>=80.9.0; extra == 'all'
 Requires-Dist: spacy>=3.8.7; extra == 'all'
 Requires-Dist: tomli>=2.0.0; (python_version < '3.11') and extra == 'all'
 Provides-Extra: api
-Requires-Dist: litestar[opentelemetry,standard,structlog]>=2.16.0; extra == 'api'
+Requires-Dist: litestar[opentelemetry,standard,structlog]>=2.17.0; extra == 'api'
 Provides-Extra: chunking
 Requires-Dist: semantic-text-splitter>=0.27.0; extra == 'chunking'
 Provides-Extra: cli
@@ -70,7 +70,7 @@ Requires-Dist: click>=8.2.1; extra == 'cli'
 Requires-Dist: rich>=14.1.0; extra == 'cli'
 Requires-Dist: tomli>=2.0.0; (python_version < '3.11') and extra == 'cli'
 Provides-Extra: crypto
-Requires-Dist: playa-pdf[crypto]>=0.6.4; extra == 'crypto'
+Requires-Dist: playa-pdf[crypto]>=0.7.0; extra == 'crypto'
 Provides-Extra: document-classification
 Requires-Dist: deep-translator>=1.11.4; extra == 'document-classification'
 Requires-Dist: pandas>=2.3.1; extra == 'document-classification'
@@ -84,7 +84,7 @@ Requires-Dist: gmft>=0.4.2; extra == 'gmft'
 Provides-Extra: langdetect
 Requires-Dist: fast-langdetect>=0.3.2; extra == 'langdetect'
 Provides-Extra: paddleocr
-Requires-Dist: paddleocr>=3.1.0; extra == 'paddleocr'
+Requires-Dist: paddleocr>=3.1.1; extra == 'paddleocr'
 Requires-Dist: paddlepaddle>=3.1.0; extra == 'paddleocr'
 Requires-Dist: setuptools>=80.9.0; extra == 'paddleocr'
 Description-Content-Type: text/markdown

{kreuzberg-3.11.0.dist-info → kreuzberg-3.11.2.dist-info}/RECORD

@@ -5,7 +5,7 @@ kreuzberg/_config.py,sha256=Au521UiR7vcQs_8_hhoWIfmDDMJIrDM3XZUB_qHfCmo,14035
 kreuzberg/_constants.py,sha256=Bxc8oiN-wHwnWXT9bEiJhTUcu1ygPpra5qHirAif3b4,191
 kreuzberg/_document_classification.py,sha256=qFGmwvUMhnNAvNNJO7E-huPx-Ps-_DWxdNxsozIzgaw,6870
 kreuzberg/_entity_extraction.py,sha256=Oa1T-9mptimpOHtcda-GtrVYH9PFy7DSJj3thJZUD7k,7902
-kreuzberg/_gmft.py,sha256=HdQ7Xpuixxl2Y0jY8C3KfyQEU0mN4yQdqErWCv4TnFY,25573
+kreuzberg/_gmft.py,sha256=6P4gSSmU39puaYAKmdGr9ALf0USYTwRDuvvhG1LmI24,26441
 kreuzberg/_language_detection.py,sha256=_Ng2aHgPxOHFgd507gVNiIGVmnxxbpgYwsO0bD0yTzg,3315
 kreuzberg/_mime_types.py,sha256=2warRVqfBUNIg8JBg8yP4pRqaMPvwINosHMkJwtH_Fc,8488
 kreuzberg/_playa.py,sha256=_IPrUSWwSfDQlWXOpKlauV0D9MhGrujGP5kmQ0U3L0g,12188
@@ -31,8 +31,8 @@ kreuzberg/_mcp/__init__.py,sha256=8PYV-omC8Rln7Cove8C3rHu3d7sR1FuiwSBG1O7vkAE,92
 kreuzberg/_mcp/server.py,sha256=Dxed80MqZsYCFyYo0QdArpKE4H8DhpKY34fijdzV5uw,8731
 kreuzberg/_ocr/__init__.py,sha256=grshVFwVQl2rMvH1hg1JNlYXjy5-Tdb_rusLD1Cselk,706
 kreuzberg/_ocr/_base.py,sha256=IkONqwG6zxZoVMni1JlYugBoyONahlRny7J2_7Dy69c,3953
-kreuzberg/_ocr/_easyocr.py,sha256=dWfoj5fPIGqJPGTVeZ0W59TrW3DpNwF0bcfgt6FwQUw,17238
-kreuzberg/_ocr/_paddleocr.py,sha256=Is_iJQaSUeCMfCvg5RnuG_pmBRjBt0b3dCBPY1IAc3A,17583
+kreuzberg/_ocr/_easyocr.py,sha256=eU4MA_B_-cvq_IhpCeYUruL_kqcfm8maNZKP7zvVQHI,17512
+kreuzberg/_ocr/_paddleocr.py,sha256=I7ns6L56a2Ol460Bge6e0hpc2AkkwDepLcpCsABj5Dc,17609
 kreuzberg/_ocr/_tesseract.py,sha256=teLMH1pBhpcmEXDcyZlv56hYINLGMuaKZ0CQtcu_czQ,31510
 kreuzberg/_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 kreuzberg/_utils/_cache.py,sha256=hYd_a5Ni5VJBE1XU_eN9gvQ5gg0FRsdbRgmJe-OIJHM,15253
@@ -47,8 +47,8 @@ kreuzberg/_utils/_string.py,sha256=bCzO3UO6nXupxvtMWvHqfp1Vd9CTzEH9jmpJXQ7upAU,6
 kreuzberg/_utils/_sync.py,sha256=7LSavBmxVKQUzdjfx9fYRAI9IbJtRw8iGf_Q8B7RX9g,4923
 kreuzberg/_utils/_table.py,sha256=IomrfQBP85DZI8RmQjOVs2Siq7VP9FUTYPaZR4t3yRw,8199
 kreuzberg/_utils/_tmp.py,sha256=hVn-VVijIg2FM7EZJ899gc7wZg-TGoJZoeAcxMX-Cxg,1044
-kreuzberg-3.11.0.dist-info/METADATA,sha256=pvyRM3TAmXE3TnYaNOZ1chD_IQTgWn254wxnqDsy6EM,12135
-kreuzberg-3.11.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-kreuzberg-3.11.0.dist-info/entry_points.txt,sha256=GplGhFryCP7kyAG_k-Mdahznvo2fwi73qLFg5yQfH_A,91
-kreuzberg-3.11.0.dist-info/licenses/LICENSE,sha256=-8caMvpCK8SgZ5LlRKhGCMtYDEXqTKH9X8pFEhl91_4,1066
-kreuzberg-3.11.0.dist-info/RECORD,,
+kreuzberg-3.11.2.dist-info/METADATA,sha256=J-UWkai5WTH0ECDX_kcp-1H45Qxa1rFgYlgcRbdE4zE,12136
+kreuzberg-3.11.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+kreuzberg-3.11.2.dist-info/entry_points.txt,sha256=GplGhFryCP7kyAG_k-Mdahznvo2fwi73qLFg5yQfH_A,91
+kreuzberg-3.11.2.dist-info/licenses/LICENSE,sha256=-8caMvpCK8SgZ5LlRKhGCMtYDEXqTKH9X8pFEhl91_4,1066
+kreuzberg-3.11.2.dist-info/RECORD,,