kreuzberg 3.3.0__py3-none-any.whl → 3.4.0__py3-none-any.whl

kreuzberg/_api/main.py

@@ -0,0 +1,87 @@
+from __future__ import annotations
+
+from json import dumps
+from typing import TYPE_CHECKING, Annotated, Any
+
+from kreuzberg import (
+    ExtractionResult,
+    KreuzbergError,
+    MissingDependencyError,
+    ParsingError,
+    ValidationError,
+    batch_extract_bytes,
+)
+
+if TYPE_CHECKING:
+    from litestar.datastructures import UploadFile
+
+try:
+    from litestar import Litestar, Request, Response, get, post
+    from litestar.contrib.opentelemetry import OpenTelemetryConfig, OpenTelemetryPlugin
+    from litestar.enums import RequestEncodingType
+    from litestar.logging import StructLoggingConfig
+    from litestar.params import Body
+    from litestar.status_codes import (
+        HTTP_400_BAD_REQUEST,
+        HTTP_422_UNPROCESSABLE_ENTITY,
+        HTTP_500_INTERNAL_SERVER_ERROR,
+    )
+except ImportError as e:
+    raise MissingDependencyError.create_for_package(
+        dependency_group="litestar",
+        functionality="Litestar API and docker container",
+        package_name="litestar",
+    ) from e
+
+
+def exception_handler(request: Request[Any, Any, Any], exception: KreuzbergError) -> Response[Any]:
+    if isinstance(exception, ValidationError):
+        status_code = HTTP_400_BAD_REQUEST
+    elif isinstance(exception, ParsingError):
+        status_code = HTTP_422_UNPROCESSABLE_ENTITY
+    else:
+        status_code = HTTP_500_INTERNAL_SERVER_ERROR
+
+    message = str(exception)
+    details = dumps(exception.context)
+
+    if request.app.logger:
+        request.app.logger.error(
+            "API error",
+            method=request.method,
+            url=str(request.url),
+            status_code=status_code,
+            message=message,
+            context=exception.context,
+        )
+
+    return Response(
+        content={"message": message, "details": details},
+        status_code=status_code,
+    )
+
+
+@post("/extract", operation_id="ExtractFiles")
+async def handle_files_upload(
+    data: Annotated[list[UploadFile], Body(media_type=RequestEncodingType.MULTI_PART)],
+) -> list[ExtractionResult]:
+    """Extracts text content from an uploaded file."""
+    return await batch_extract_bytes(
+        [(await file.read(), file.content_type) for file in data],
+    )
+
+
+@get("/health", operation_id="HealthCheck")
+async def health_check() -> dict[str, str]:
+    """A simple health check endpoint."""
+    return {"status": "ok"}
+
+
+app = Litestar(
+    route_handlers=[handle_files_upload, health_check],
+    plugins=[OpenTelemetryPlugin(OpenTelemetryConfig())],
+    logging_config=StructLoggingConfig(),
+    exception_handlers={
+        KreuzbergError: exception_handler,
+    },
+)

kreuzberg/_types.py

@@ -114,6 +114,10 @@ class ExtractionResult:
     chunks: list[str] = field(default_factory=list)
     """The extracted content chunks. This is an empty list if 'chunk_content' is not set to True in the ExtractionConfig."""
 
+    def to_dict(self) -> dict[str, Any]:
+        """Converts the ExtractionResult to a dictionary."""
+        return asdict(self)
+
 
 PostProcessingHook = Callable[[ExtractionResult], Union[ExtractionResult, Awaitable[ExtractionResult]]]
 ValidationHook = Callable[[ExtractionResult], Union[None, Awaitable[None]]]

{kreuzberg-3.3.0.dist-info → kreuzberg-3.4.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kreuzberg
-Version: 3.3.0
+Version: 3.4.0
 Summary: A text extraction library supporting PDFs, images, office documents and more
 Project-URL: homepage, https://github.com/Goldziher/kreuzberg
 Author-email: Na'aman Hirschfeld <nhirschfed@gmail.com>
@@ -34,12 +34,15 @@ Provides-Extra: all
 Requires-Dist: click>=8.2.1; extra == 'all'
 Requires-Dist: easyocr>=1.7.2; extra == 'all'
 Requires-Dist: gmft>=0.4.2; extra == 'all'
+Requires-Dist: litestar[opentelemetry,standard,structlog]>=2.1.6; extra == 'all'
 Requires-Dist: paddleocr>=3.1.0; extra == 'all'
 Requires-Dist: paddlepaddle>=3.1.0; extra == 'all'
 Requires-Dist: rich>=14.0.0; extra == 'all'
 Requires-Dist: semantic-text-splitter>=0.27.0; extra == 'all'
 Requires-Dist: setuptools>=80.9.0; extra == 'all'
 Requires-Dist: tomli>=2.0.0; (python_version < '3.11') and extra == 'all'
+Provides-Extra: api
+Requires-Dist: litestar[opentelemetry,standard,structlog]>=2.1.6; extra == 'api'
 Provides-Extra: chunking
 Requires-Dist: semantic-text-splitter>=0.27.0; extra == 'chunking'
 Provides-Extra: cli
@@ -63,10 +66,14 @@ Description-Content-Type: text/markdown
 [![Documentation](https://img.shields.io/badge/docs-GitHub_Pages-blue)](https://goldziher.github.io/kreuzberg/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
-Kreuzberg is a Python library for text extraction from documents. It provides a unified interface for extracting text from PDFs, images, office documents, and more, with both async and sync APIs.
+Kreuzberg is a **high-performance** Python library for text extraction from documents. **Benchmarked as one of the fastest text extraction libraries available**, it provides a unified interface for extracting text from PDFs, images, office documents, and more, with both async and sync APIs optimized for speed and efficiency.
 
 ## Why Kreuzberg?
 
+- **🚀 Substantially Faster**: Extraction speeds that significantly outperform other text extraction libraries
+- **⚡ Unique Dual API**: The only framework supporting both sync and async APIs for maximum flexibility
+- **💾 Memory Efficient**: Lower memory footprint compared to competing libraries
+- **📊 Proven Performance**: [Comprehensive benchmarks](https://github.com/Goldziher/python-text-extraction-libs-benchmarks) demonstrate superior performance across formats
 - **Simple and Hassle-Free**: Clean API that just works, without complex configuration
 - **Local Processing**: No external API calls or cloud dependencies required
 - **Resource Efficient**: Lightweight processing without GPU requirements
@@ -85,6 +92,9 @@ pip install kreuzberg
 
 # Or install with CLI support
 pip install "kreuzberg[cli]"
+
+# Or install with API server
+pip install "kreuzberg[api]"
 ```
 
 Install pandoc:
@@ -134,6 +144,31 @@ async def main():
 asyncio.run(main())
 ```
 
+## Docker
+
+Docker images are available for easy deployment:
+
+```bash
+# Run the API server
+docker run -p 8000:8000 goldziher/kreuzberg:latest
+
+# Extract files via API
+curl -X POST http://localhost:8000/extract -F "data=@document.pdf"
+```
+
+See the [Docker documentation](https://goldziher.github.io/kreuzberg/user-guide/docker/) for more options.
+
+## REST API
+
+Run Kreuzberg as a REST API server:
+
+```bash
+pip install "kreuzberg[api]"
+litestar --app kreuzberg._api.main:app run
+```
+
+See the [API documentation](https://goldziher.github.io/kreuzberg/user-guide/api-server/) for endpoints and usage.
+
 ## Command Line Interface
 
 Kreuzberg includes a powerful CLI for processing documents from the command line:
@@ -208,7 +243,31 @@ For comparison and selection guidance, see the [OCR Backends](https://goldziher.
 
 ## Performance
 
-Kreuzberg offers both sync and async APIs. Choose the right one based on your use case:
+Kreuzberg delivers **exceptional performance** compared to other text extraction libraries:
+
+### 🏆 Competitive Benchmarks
+
+[Comprehensive benchmarks](https://github.com/Goldziher/python-text-extraction-libs-benchmarks) comparing Kreuzberg against other popular Python text extraction libraries show:
+
+- **Fastest Extraction**: Consistently fastest processing times across file formats
+- **Lowest Memory Usage**: Most memory-efficient text extraction solution
+- **100% Success Rate**: Reliable extraction across all tested document types
+- **Optimal for High-Throughput**: Designed for real-time, production applications
+
+### 💾 Installation Size Efficiency
+
+Kreuzberg delivers maximum performance with minimal overhead:
+
+1. **Kreuzberg**: 71.0 MB (20 deps) - Most lightweight
+1. **Unstructured**: 145.8 MB (54 deps) - Moderate footprint
+1. **MarkItDown**: 250.7 MB (25 deps) - ML inference overhead
+1. **Docling**: 1,031.9 MB (88 deps) - Full ML stack included
+
+**Kreuzberg is up to 14x smaller** than competing solutions while delivering superior performance.
+
+### ⚡ Sync vs Async Performance
+
+Kreuzberg is the only library offering both sync and async APIs. Choose based on your use case:
 
 | Operation              | Sync Time | Async Time | Async Advantage    |
 | ---------------------- | --------- | ---------- | ------------------ |
@@ -218,11 +277,7 @@ Kreuzberg offers both sync and async APIs. Choose the right one based on your us
 | OCR processing         | 0.4s      | 0.7s       | **✅ 1.7x faster** |
 | Batch operations       | 38.6s     | 8.5s       | **✅ 4.5x faster** |
 
-**Rule of thumb:**
-
-- Use **sync** for simple documents and CLI applications
-- Use **async** for complex PDFs, OCR, and batch processing
-- Use **batch operations** for multiple files
+**Rule of thumb:** Use async for complex documents, OCR, batch processing, and backend APIs.
 
 For detailed benchmarks and methodology, see our [Performance Documentation](https://goldziher.github.io/kreuzberg/advanced/performance/).
 

{kreuzberg-3.3.0.dist-info → kreuzberg-3.4.0.dist-info}/RECORD

@@ -7,11 +7,13 @@ kreuzberg/_gmft.py,sha256=6liCjedPxH5Xbe7V-AmrZIq5Y9Dejn7D-LSCbgYs2Sg,14762
 kreuzberg/_mime_types.py,sha256=QgX-k8aI4lTKArObDM0TFPt7DUjUVwWrdIaIZDh_XQY,7815
 kreuzberg/_playa.py,sha256=rU6ii2Qnrj8tkDYlSiab5h-BCYLJnUg4QwSLVDEXF5g,11883
 kreuzberg/_registry.py,sha256=c2B_PJbaL0q3ab2eNmj_0jldeyMaqgvRwkZqUU4MM5Q,3290
-kreuzberg/_types.py,sha256=G7UQ5ZUWcpgwHoasexW7f2te3gKe3PHHi_3Fm1cju-w,7503
+kreuzberg/_types.py,sha256=8kwDjQjBdiTbNcRwJmH4vijNpf9Ml9WNW85Uxv2alDw,7634
 kreuzberg/cli.py,sha256=S0w2nGXBWPFn1NhxppW7dpUwB9f_3ymFuWSAB2aRu9g,12465
 kreuzberg/exceptions.py,sha256=xRaiJh11i8E6Nc-gAQPgNW5xvhiiFBhRS-CBbCEbHQM,2881
 kreuzberg/extraction.py,sha256=z8sht8Yw9v6bE_WgLdWx-phu4T58eExME296DV_41VU,16551
 kreuzberg/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kreuzberg/_api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kreuzberg/_api/main.py,sha256=kZCMPPzP4BGzEege9pdhQTJPKKVjCaC6kZdMMeaqP2M,2599
 kreuzberg/_extractors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 kreuzberg/_extractors/_base.py,sha256=YUr6A2n34LlFzbYQkiKqhXAphL9RYrvAls5SlkoQqNg,3028
 kreuzberg/_extractors/_html.py,sha256=L_vcKyv1ObI6irPaD3-WTKqxeRfZA4Rhsl3zUiAe_ws,1312
@@ -41,8 +43,8 @@ kreuzberg/_utils/_serialization.py,sha256=AhZvyAu4KsjAqyZDh--Kn2kSWGgCuH7udio8lT
 kreuzberg/_utils/_string.py,sha256=owIVkUtP0__GiJD9RIJzPdvyIigT5sQho3mOXPbsnW0,958
 kreuzberg/_utils/_sync.py,sha256=IsKkR_YmseZKY6Asz6w3k-dgMXcrVaI06jWfDY7Bol4,4842
 kreuzberg/_utils/_tmp.py,sha256=5rqG_Nlb9xweaLqJA8Kc5csHDase9_eY_Fq93rNQGWc,1044
-kreuzberg-3.3.0.dist-info/METADATA,sha256=beRlFJzCsZNcQ_DsRyzRc2WDT-UkBCfBvY6vTWiOxp0,8748
-kreuzberg-3.3.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-kreuzberg-3.3.0.dist-info/entry_points.txt,sha256=VdoFaTl3QSvVWOZcIlPpDd47o6kn7EvmXSs8FI0ExLc,48
-kreuzberg-3.3.0.dist-info/licenses/LICENSE,sha256=-8caMvpCK8SgZ5LlRKhGCMtYDEXqTKH9X8pFEhl91_4,1066
-kreuzberg-3.3.0.dist-info/RECORD,,
+kreuzberg-3.4.0.dist-info/METADATA,sha256=Rg939xe9b-H0TExRcJKkf9MFg7-kWM_fvzGvV6VDG0Q,11215
+kreuzberg-3.4.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+kreuzberg-3.4.0.dist-info/entry_points.txt,sha256=VdoFaTl3QSvVWOZcIlPpDd47o6kn7EvmXSs8FI0ExLc,48
+kreuzberg-3.4.0.dist-info/licenses/LICENSE,sha256=-8caMvpCK8SgZ5LlRKhGCMtYDEXqTKH9X8pFEhl91_4,1066
+kreuzberg-3.4.0.dist-info/RECORD,,