kreuzberg 3.10.1__tar.gz → 3.11.1__tar.gz

{kreuzberg-3.10.1 → kreuzberg-3.11.1}/.github/workflows/ci.yaml

@@ -15,7 +15,7 @@ jobs:
     timeout-minutes: 10
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
 
       - name: Install uv
         uses: astral-sh/setup-uv@v6
@@ -58,7 +58,7 @@ jobs:
     timeout-minutes: 20
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
 
       - name: Install uv
         uses: astral-sh/setup-uv@v6
@@ -151,7 +151,7 @@ jobs:
     timeout-minutes: 30
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
 
       - name: Install uv
         uses: astral-sh/setup-uv@v6

{kreuzberg-3.10.1 → kreuzberg-3.11.1}/.github/workflows/docs.yml

@@ -24,7 +24,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
         with:
           fetch-depth: 0
 

{kreuzberg-3.10.1 → kreuzberg-3.11.1}/.github/workflows/pr-title.yaml

@@ -15,6 +15,6 @@ jobs:
     name: Validate PR title
     runs-on: ubuntu-latest
     steps:
-      - uses: amannn/action-semantic-pull-request@v5
+      - uses: amannn/action-semantic-pull-request@v6
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

{kreuzberg-3.10.1 → kreuzberg-3.11.1}/.github/workflows/publish-docker.yml

@@ -46,7 +46,7 @@ jobs:
           df -h
 
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
         with:
           ref: ${{ github.ref }}
 

{kreuzberg-3.10.1 → kreuzberg-3.11.1}/.github/workflows/release.yaml

@@ -13,7 +13,7 @@ jobs:
       contents: read
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
 
       - name: Install uv
         uses: astral-sh/setup-uv@v6

{kreuzberg-3.10.1 → kreuzberg-3.11.1}/.pre-commit-config.yaml

@@ -5,13 +5,15 @@ repos:
       - id: commitlint
         stages: [commit-msg]
         additional_dependencies: ["@commitlint/config-conventional"]
-  - repo: https://github.com/Goldziher/ai-rulez
-    rev: v1.1.4
-    hooks:
-      - id: ai-rulez-validate
-      - id: ai-rulez-generate
+  # Temporarily disabled - ai-rulez Go build failing in CI
+  # TODO: Re-enable once ai-rulez v1.4.4+ Python migration is stable
+  # - repo: https://github.com/Goldziher/ai-rulez
+  #   rev: v1.4.3
+  #   hooks:
+  #     - id: ai-rulez-validate
+  #     - id: ai-rulez-generate
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v5.0.0
+    rev: v6.0.0
     hooks:
       - id: name-tests-test
         args:
@@ -53,7 +55,7 @@ repos:
     hooks:
       - id: pyproject-fmt
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.12.7
+    rev: v0.12.8
     hooks:
       - id: ruff
         args: ["--fix", "--unsafe-fixes"]

{kreuzberg-3.10.1 → kreuzberg-3.11.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kreuzberg
-Version: 3.10.1
+Version: 3.11.1
 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>=1.12.2
+Requires-Dist: mcp>=1.12.4
 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
@@ -45,25 +45,24 @@ Requires-Dist: mailparse>=1.0.15; extra == 'additional-extensions'
 Requires-Dist: tomli>=2.0.0; (python_version < '3.11') and extra == 'additional-extensions'
 Provides-Extra: all
 Requires-Dist: click>=8.2.1; extra == 'all'
+Requires-Dist: deep-translator>=1.11.4; extra == 'all'
 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: paddlepaddle>=3.1.0; extra == 'all'
-Requires-Dist: playa-pdf[crypto]>=0.6.4; extra == 'all'
+Requires-Dist: pandas>=2.3.1; 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'
-Provides-Extra: auto-classify-document-type
-Requires-Dist: deep-translator>=1.11.4; extra == 'auto-classify-document-type'
-Requires-Dist: pandas>=2.3.1; extra == 'auto-classify-document-type'
+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
@@ -71,7 +70,10 @@ 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'
 Provides-Extra: easyocr
 Requires-Dist: easyocr>=1.7.2; extra == 'easyocr'
 Provides-Extra: entity-extraction

{kreuzberg-3.10.1 → kreuzberg-3.11.1}/docs/contributing.md

@@ -34,7 +34,7 @@ All commands run through `uv run`:
 # Testing
 uv run pytest                      # Run all tests
 uv run pytest tests/foo_test.py    # Run specific test
-uv run pytest --cov                # With coverage (must be ≥95%)
+uv run pytest --cov                # With coverage (must be ≥85%)
 
 # Code quality
 uv run ruff format                 # Format code

{kreuzberg-3.10.1 → kreuzberg-3.11.1}/docs/examples/extraction-examples.md

@@ -132,15 +132,15 @@ async def extract_tables_from_pdf():
     # Process extracted tables
     print(f"Found {len(result.tables)} tables")
     for i, table in enumerate(result.tables):
-        print(f"Table {i+1} on page {table.page_number}:")
-        print(table.text)  # Markdown formatted table
+        print(f"Table {i+1} on page {table['page_number']}:")
+        print(table["text"])  # Markdown formatted table
 
         # Work with the pandas DataFrame
-        df = table.df
+        df = table["df"]
         print(f"Table shape: {df.shape}")
 
         # The cropped table image is also available
-        # table.cropped_image.save(f"table_{i+1}.png")
+        # table['cropped_image'].save(f"table_{i+1}.png")
 
     # With custom GMFT configuration
     custom_config = ExtractionConfig(

{kreuzberg-3.10.1 → kreuzberg-3.11.1}/docs/getting-started/installation.md

@@ -134,6 +134,16 @@ python -m spacy download es_core_news_sm  # Spanish
 
     spaCy language models are large (50-500MB each) and are downloaded separately. Only download the models for languages you actually need to process. See the [spaCy models documentation](https://spacy.io/models) for a complete list of available models.
 
+### Document Classification
+
+For automatic document type detection (invoice, contract, receipt, etc.), install the document classification extra:
+
+```shell
+pip install "kreuzberg[document-classification]"
+```
+
+This feature uses Google Translate for multi-language support and requires explicit opt-in by setting `auto_detect_document_type=True` in your configuration.
+
 ### All Optional Dependencies
 
 To install Kreuzberg with all optional dependencies, you can use the `all` extra group:
@@ -145,5 +155,5 @@ pip install "kreuzberg[all]"
 This is equivalent to:
 
 ```shell
-pip install "kreuzberg[chunking,easyocr,entity-extraction,gmft,langdetect,paddleocr]"
+pip install "kreuzberg[chunking,document-classification,easyocr,entity-extraction,gmft,langdetect,paddleocr]"
 ```

{kreuzberg-3.10.1 → kreuzberg-3.11.1}/docs/index.md

@@ -22,7 +22,7 @@ Kreuzberg addresses the complete document intelligence pipeline through a modula
 
 ### Engineering Principles
 
-- **Test Coverage**: 95%+ coverage with comprehensive test suites
+- **Test Coverage**: Comprehensive test suites ensuring code reliability
 - **API Design**: True async/await implementation alongside synchronous APIs
 - **Error Handling**: Consistent exception hierarchy with detailed context
 - **Type Safety**: Full type annotations for enhanced developer experience

{kreuzberg-3.10.1 → kreuzberg-3.11.1}/docs/user-guide/document-classification.md

@@ -2,9 +2,17 @@
 
 Kreuzberg can automatically classify documents into common types like invoices, contracts, and receipts. This allows you to build custom processing pipelines tailored to each document type.
 
+## Installation
+
+Document classification requires the `document-classification` extra to be installed:
+
+```bash
+pip install "kreuzberg[document-classification]"
+```
+
 ## Enabling Document Classification
 
-To enable this feature, set `auto_detect_document_type=True` in your `ExtractionConfig`:
+Document classification is disabled by default. To enable this feature, set `auto_detect_document_type=True` in your `ExtractionConfig`:
 
 ```python
 from kreuzberg import ExtractionConfig, extract_file

{kreuzberg-3.10.1 → kreuzberg-3.11.1}/docs/user-guide/extraction-configuration.md

@@ -237,10 +237,10 @@ result = await extract_file("document_with_tables.pdf", config=config)
 
 # Access extracted tables
 for i, table in enumerate(result.tables):
-    print(f"Table {i+1} on page {table.page_number}:")
-    print(table.text)  # Markdown formatted table text
+    print(f"Table {i+1} on page {table['page_number']}:")
+    print(table["text"])  # Markdown formatted table text
     # You can also access the pandas DataFrame directly
-    df = table.df
+    df = table["df"]
     print(df.shape)  # (rows, columns)
 ```
 

{kreuzberg-3.10.1 → kreuzberg-3.11.1}/kreuzberg/_config.py

@@ -97,19 +97,21 @@ def parse_ocr_backend_config(
     if not isinstance(backend_config, dict):
         return None
 
-    if backend == "tesseract":
-        # Convert psm integer to PSMMode enum if needed
-        processed_config = backend_config.copy()
-        if "psm" in processed_config and isinstance(processed_config["psm"], int):
-            from kreuzberg._ocr._tesseract import PSMMode  # noqa: PLC0415
-
-            processed_config["psm"] = PSMMode(processed_config["psm"])
-        return TesseractConfig(**processed_config)
-    if backend == "easyocr":
-        return EasyOCRConfig(**backend_config)
-    if backend == "paddleocr":
-        return PaddleOCRConfig(**backend_config)
-    return None
+    match backend:
+        case "tesseract":
+            # Convert psm integer to PSMMode enum if needed
+            processed_config = backend_config.copy()
+            if "psm" in processed_config and isinstance(processed_config["psm"], int):
+                from kreuzberg._ocr._tesseract import PSMMode  # noqa: PLC0415
+
+                processed_config["psm"] = PSMMode(processed_config["psm"])
+            return TesseractConfig(**processed_config)
+        case "easyocr":
+            return EasyOCRConfig(**backend_config)
+        case "paddleocr":
+            return PaddleOCRConfig(**backend_config)
+        case _:
+            return None
 
 
 def build_extraction_config_from_dict(config_dict: dict[str, Any]) -> ExtractionConfig:
@@ -140,7 +142,9 @@ def build_extraction_config_from_dict(config_dict: dict[str, Any]) -> Extraction
         "document_classification_mode",
         "keyword_count",
     }
-    extraction_config.update({field: config_dict[field] for field in basic_fields if field in config_dict})
+    extraction_config = extraction_config | {
+        field: config_dict[field] for field in basic_fields if field in config_dict
+    }
 
     # Handle OCR backend configuration
     ocr_backend = extraction_config.get("ocr_backend")

{kreuzberg-3.10.1 → kreuzberg-3.11.1}/kreuzberg/_document_classification.py

@@ -62,7 +62,7 @@ def _get_translated_text(result: ExtractionResult) -> str:
         from deep_translator import GoogleTranslator  # noqa: PLC0415
     except ImportError as e:  # pragma: no cover
         raise MissingDependencyError(
-            "The 'deep-translator' library is not installed. Please install it with: pip install 'kreuzberg[auto-classify-document-type]'"
+            "The 'deep-translator' library is not installed. Please install it with: pip install 'kreuzberg[document-classification]'"
         ) from e
 
     try:

{kreuzberg-3.10.1 → kreuzberg-3.11.1}/kreuzberg/_extractors/_base.py

@@ -116,8 +116,7 @@ class Extractor(ABC):
         quality_score = calculate_quality_score(cleaned_content, dict(result.metadata) if result.metadata else None)
 
         # Add quality metadata
-        enhanced_metadata = dict(result.metadata) if result.metadata else {}
-        enhanced_metadata["quality_score"] = quality_score
+        enhanced_metadata = (dict(result.metadata) if result.metadata else {}) | {"quality_score": quality_score}
 
         # Return enhanced result
         return ExtractionResult(

{kreuzberg-3.10.1 → kreuzberg-3.11.1}/kreuzberg/_extractors/_image.py

@@ -85,23 +85,24 @@ class ImageExtractor(Extractor):
 
         backend = get_ocr_backend(self.config.ocr_backend)
 
-        if self.config.ocr_backend == "tesseract":
-            config = (
-                self.config.ocr_config if isinstance(self.config.ocr_config, TesseractConfig) else TesseractConfig()
-            )
-            result = backend.process_file_sync(path, **asdict(config))
-        elif self.config.ocr_backend == "paddleocr":
-            paddle_config = (
-                self.config.ocr_config if isinstance(self.config.ocr_config, PaddleOCRConfig) else PaddleOCRConfig()
-            )
-            result = backend.process_file_sync(path, **asdict(paddle_config))
-        elif self.config.ocr_backend == "easyocr":
-            easy_config = (
-                self.config.ocr_config if isinstance(self.config.ocr_config, EasyOCRConfig) else EasyOCRConfig()
-            )
-            result = backend.process_file_sync(path, **asdict(easy_config))
-        else:
-            raise NotImplementedError(f"Sync OCR not implemented for {self.config.ocr_backend}")
+        match self.config.ocr_backend:
+            case "tesseract":
+                config = (
+                    self.config.ocr_config if isinstance(self.config.ocr_config, TesseractConfig) else TesseractConfig()
+                )
+                result = backend.process_file_sync(path, **asdict(config))
+            case "paddleocr":
+                paddle_config = (
+                    self.config.ocr_config if isinstance(self.config.ocr_config, PaddleOCRConfig) else PaddleOCRConfig()
+                )
+                result = backend.process_file_sync(path, **asdict(paddle_config))
+            case "easyocr":
+                easy_config = (
+                    self.config.ocr_config if isinstance(self.config.ocr_config, EasyOCRConfig) else EasyOCRConfig()
+                )
+                result = backend.process_file_sync(path, **asdict(easy_config))
+            case _:
+                raise NotImplementedError(f"Sync OCR not implemented for {self.config.ocr_backend}")
         return self._apply_quality_processing(result)
 
     def _get_extension_from_mime_type(self, mime_type: str) -> str:

{kreuzberg-3.10.1 → kreuzberg-3.11.1}/kreuzberg/_extractors/_pdf.py

@@ -88,14 +88,12 @@ class PDFExtractor(Extractor):
             # Enhance metadata with table information
             if result.tables:
                 table_summary = generate_table_summary(result.tables)
-                result.metadata.update(
-                    {
-                        "table_count": table_summary["table_count"],
-                        "tables_summary": f"Document contains {table_summary['table_count']} tables "
-                        f"across {table_summary['pages_with_tables']} pages with "
-                        f"{table_summary['total_rows']} total rows",
-                    }
-                )
+                result.metadata = result.metadata | {
+                    "table_count": table_summary["table_count"],
+                    "tables_summary": f"Document contains {table_summary['table_count']} tables "
+                    f"across {table_summary['pages_with_tables']} pages with "
+                    f"{table_summary['total_rows']} total rows",
+                }
 
         return self._apply_quality_processing(result)
 
@@ -153,14 +151,12 @@ class PDFExtractor(Extractor):
         # Enhance metadata with table information
         if tables:
             table_summary = generate_table_summary(tables)
-            result.metadata.update(
-                {
-                    "table_count": table_summary["table_count"],
-                    "tables_summary": f"Document contains {table_summary['table_count']} tables "
-                    f"across {table_summary['pages_with_tables']} pages with "
-                    f"{table_summary['total_rows']} total rows",
-                }
-            )
+            result.metadata = result.metadata | {
+                "table_count": table_summary["table_count"],
+                "tables_summary": f"Document contains {table_summary['table_count']} tables "
+                f"across {table_summary['pages_with_tables']} pages with "
+                f"{table_summary['total_rows']} total rows",
+            }
 
         # Apply quality processing
         return self._apply_quality_processing(result)
@@ -386,23 +382,24 @@ class PDFExtractor(Extractor):
         backend = get_ocr_backend(self.config.ocr_backend)
         paths = [Path(p) for p in image_paths]
 
-        if self.config.ocr_backend == "tesseract":
-            config = (
-                self.config.ocr_config if isinstance(self.config.ocr_config, TesseractConfig) else TesseractConfig()
-            )
-            results = backend.process_batch_sync(paths, **asdict(config))
-        elif self.config.ocr_backend == "paddleocr":
-            paddle_config = (
-                self.config.ocr_config if isinstance(self.config.ocr_config, PaddleOCRConfig) else PaddleOCRConfig()
-            )
-            results = backend.process_batch_sync(paths, **asdict(paddle_config))
-        elif self.config.ocr_backend == "easyocr":
-            easy_config = (
-                self.config.ocr_config if isinstance(self.config.ocr_config, EasyOCRConfig) else EasyOCRConfig()
-            )
-            results = backend.process_batch_sync(paths, **asdict(easy_config))
-        else:
-            raise NotImplementedError(f"Sync OCR not implemented for {self.config.ocr_backend}")
+        match self.config.ocr_backend:
+            case "tesseract":
+                config = (
+                    self.config.ocr_config if isinstance(self.config.ocr_config, TesseractConfig) else TesseractConfig()
+                )
+                results = backend.process_batch_sync(paths, **asdict(config))
+            case "paddleocr":
+                paddle_config = (
+                    self.config.ocr_config if isinstance(self.config.ocr_config, PaddleOCRConfig) else PaddleOCRConfig()
+                )
+                results = backend.process_batch_sync(paths, **asdict(paddle_config))
+            case "easyocr":
+                easy_config = (
+                    self.config.ocr_config if isinstance(self.config.ocr_config, EasyOCRConfig) else EasyOCRConfig()
+                )
+                results = backend.process_batch_sync(paths, **asdict(easy_config))
+            case _:
+                raise NotImplementedError(f"Sync OCR not implemented for {self.config.ocr_backend}")
 
         # Use list comprehension and join for efficient string building
         return "\n\n".join(result.content for result in results)

{kreuzberg-3.10.1 → kreuzberg-3.11.1}/kreuzberg/_mcp/server.py

@@ -51,7 +51,7 @@ def _create_config_with_overrides(**kwargs: Any) -> ExtractionConfig:
     }
 
     # Override with provided parameters
-    config_dict.update(kwargs)
+    config_dict = config_dict | kwargs
 
     return ExtractionConfig(**config_dict)
 

{kreuzberg-3.10.1 → kreuzberg-3.11.1}/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-3.10.1 → kreuzberg-3.11.1}/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-3.10.1 → kreuzberg-3.11.1}/kreuzberg/_types.py

@@ -349,7 +349,7 @@ class ExtractionConfig:
     """Configuration for language detection. If None, uses default settings."""
     spacy_entity_extraction_config: SpacyEntityExtractionConfig | None = None
     """Configuration for spaCy entity extraction. If None, uses default settings."""
-    auto_detect_document_type: bool = True
+    auto_detect_document_type: bool = False
     """Whether to automatically detect the document type."""
     document_type_confidence_threshold: float = 0.5
     """Confidence threshold for document type detection."""
@@ -398,15 +398,16 @@ class ExtractionConfig:
             return asdict(self.ocr_config)
 
         # Lazy load and cache default configs instead of creating new instances
-        if self.ocr_backend == "tesseract":
-            from kreuzberg._ocr._tesseract import TesseractConfig  # noqa: PLC0415
+        match self.ocr_backend:
+            case "tesseract":
+                from kreuzberg._ocr._tesseract import TesseractConfig  # noqa: PLC0415
 
-            return asdict(TesseractConfig())
-        if self.ocr_backend == "easyocr":
-            from kreuzberg._ocr._easyocr import EasyOCRConfig  # noqa: PLC0415
+                return asdict(TesseractConfig())
+            case "easyocr":
+                from kreuzberg._ocr._easyocr import EasyOCRConfig  # noqa: PLC0415
 
-            return asdict(EasyOCRConfig())
-        # paddleocr
-        from kreuzberg._ocr._paddleocr import PaddleOCRConfig  # noqa: PLC0415
+                return asdict(EasyOCRConfig())
+            case _:  # paddleocr or any other backend
+                from kreuzberg._ocr._paddleocr import PaddleOCRConfig  # noqa: PLC0415
 
-        return asdict(PaddleOCRConfig())
+                return asdict(PaddleOCRConfig())

{kreuzberg-3.10.1 → kreuzberg-3.11.1}/mkdocs.yaml

@@ -158,4 +158,3 @@ nav:
       - Custom Hooks: advanced/custom-hooks.md
       - Custom Extractors: advanced/custom-extractors.md
   - Contributing: contributing.md
-  - Changelog: changelog.md