kreuzberg 3.11.4__py3-none-any.whl → 3.13.0__py3-none-any.whl

kreuzberg/extraction.py

@@ -151,20 +151,22 @@ async def extract_file(
     """
     cache = get_document_cache()
     path = Path(file_path)
-    cached_result = cache.get(path, config)
-    if cached_result is not None:
-        return cached_result
 
-    if cache.is_processing(path, config):
-        event = cache.mark_processing(path, config)
-        await anyio.to_thread.run_sync(event.wait)  # pragma: no cover
-
-        # Try cache again after waiting for other process to complete  # ~keep
-        cached_result = cache.get(path, config)  # pragma: no cover
-        if cached_result is not None:  # pragma: no cover
+    if config.use_cache:
+        cached_result = cache.get(path, config)
+        if cached_result is not None:
             return cached_result
 
-    cache.mark_processing(path, config)
+        if cache.is_processing(path, config):
+            event = cache.mark_processing(path, config)
+            await anyio.to_thread.run_sync(event.wait)  # pragma: no cover
+
+            # Try cache again after waiting for other process to complete  # ~keep
+            cached_result = cache.get(path, config)  # pragma: no cover
+            if cached_result is not None:  # pragma: no cover
+                return cached_result
+
+        cache.mark_processing(path, config)
 
     try:
         if not path.exists():
@@ -183,11 +185,13 @@ async def extract_file(
 
         result = await _validate_and_post_process_async(result=result, config=config, file_path=path)
 
-        cache.set(path, config, result)
+        if config.use_cache:
+            cache.set(path, config, result)
 
         return result
     finally:
-        cache.mark_complete(path, config)
+        if config.use_cache:
+            cache.mark_complete(path, config)
 
 
 async def batch_extract_file(
@@ -224,7 +228,7 @@ async def batch_extract_file(
                     content=f"Error: {type(e).__name__}: {e!s}",
                     mime_type="text/plain",
                     metadata={  # type: ignore[typeddict-unknown-key]
-                        "error": True,
+                        "error": f"{type(e).__name__}: {e!s}",
                         "error_context": create_error_context(
                             operation="batch_extract_file",
                             file_path=path,
@@ -273,7 +277,7 @@ async def batch_extract_bytes(
                     content=f"Error: {type(e).__name__}: {e!s}",
                     mime_type="text/plain",
                     metadata={  # type: ignore[typeddict-unknown-key]
-                        "error": True,
+                        "error": f"{type(e).__name__}: {e!s}",
                         "error_context": create_error_context(
                             operation="batch_extract_bytes",
                             error=e,
@@ -336,20 +340,22 @@ def extract_file_sync(
     """
     cache = get_document_cache()
     path = Path(file_path)
-    cached_result = cache.get(path, config)
-    if cached_result is not None:
-        return cached_result
 
-    if cache.is_processing(path, config):
-        event = cache.mark_processing(path, config)
-        event.wait()  # pragma: no cover
-
-        # Try cache again after waiting for other process to complete  # ~keep
-        cached_result = cache.get(path, config)  # pragma: no cover
-        if cached_result is not None:  # pragma: no cover
+    if config.use_cache:
+        cached_result = cache.get(path, config)
+        if cached_result is not None:
             return cached_result
 
-    cache.mark_processing(path, config)
+        if cache.is_processing(path, config):
+            event = cache.mark_processing(path, config)
+            event.wait()  # pragma: no cover
+
+            # Try cache again after waiting for other process to complete  # ~keep
+            cached_result = cache.get(path, config)  # pragma: no cover
+            if cached_result is not None:  # pragma: no cover
+                return cached_result
+
+        cache.mark_processing(path, config)
 
     try:
         if not path.exists():
@@ -360,7 +366,7 @@ def extract_file_sync(
             result = extractor.extract_path_sync(Path(file_path))
         else:
             result = ExtractionResult(
-                content=Path(file_path).read_text(),
+                content=Path(file_path).read_text(encoding="utf-8"),
                 chunks=[],
                 mime_type=mime_type,
                 metadata={},
@@ -368,11 +374,13 @@ def extract_file_sync(
 
         result = _validate_and_post_process_sync(result=result, config=config, file_path=path)
 
-        cache.set(path, config, result)
+        if config.use_cache:
+            cache.set(path, config, result)
 
         return result
     finally:
-        cache.mark_complete(path, config)
+        if config.use_cache:
+            cache.mark_complete(path, config)
 
 
 def batch_extract_file_sync(
@@ -404,7 +412,7 @@ def batch_extract_file_sync(
                 content=f"Error: {type(e).__name__}: {e!s}",
                 mime_type="text/plain",
                 metadata={  # type: ignore[typeddict-unknown-key]
-                    "error": True,
+                    "error": f"{type(e).__name__}: {e!s}",
                     "error_context": create_error_context(
                         operation="batch_extract_file_sync",
                         file_path=file_path,
@@ -455,7 +463,7 @@ def batch_extract_bytes_sync(
                 content=f"Error: {type(e).__name__}: {e!s}",
                 mime_type="text/plain",
                 metadata={  # type: ignore[typeddict-unknown-key]
-                    "error": True,
+                    "error": f"{type(e).__name__}: {e!s}",
                     "error_context": create_error_context(
                         operation="batch_extract_bytes_sync",
                         error=e,
@@ -469,7 +477,6 @@ def batch_extract_bytes_sync(
             return (index, error_result)
 
     with ThreadPoolExecutor(max_workers=max_workers) as executor:
-        # Avoid creating intermediate list, use enumerate directly
         future_to_index = {executor.submit(extract_single, (i, content)): i for i, content in enumerate(contents)}
 
         results: list[ExtractionResult] = [None] * len(contents)  # type: ignore[list-item]

{kreuzberg-3.11.4.dist-info → kreuzberg-3.13.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kreuzberg
-Version: 3.11.4
+Version: 3.13.0
 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
@@ -31,15 +31,16 @@ Requires-Python: >=3.10
 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: html-to-markdown[lxml]>=1.9.1
 Requires-Dist: mcp>=1.13.0
 Requires-Dist: msgspec>=0.18.0
 Requires-Dist: playa-pdf>=0.7.0
+Requires-Dist: polars>=1.33.0
 Requires-Dist: psutil>=7.0.0
 Requires-Dist: pypdfium2==4.30.0
 Requires-Dist: python-calamine>=0.3.2
 Requires-Dist: python-pptx>=1.0.2
-Requires-Dist: typing-extensions>=4.14.0; python_version < '3.12'
+Requires-Dist: typing-extensions>=4.15.0; python_version < '3.12'
 Provides-Extra: additional-extensions
 Requires-Dist: mailparse>=1.0.15; extra == 'additional-extensions'
 Requires-Dist: tomli>=2.0.0; (python_version < '3.11') and extra == 'additional-extensions'
@@ -54,7 +55,6 @@ Requires-Dist: litestar[opentelemetry,standard,structlog]>=2.17.0; extra == 'all
 Requires-Dist: mailparse>=1.0.15; extra == 'all'
 Requires-Dist: paddleocr>=3.2.0; extra == 'all'
 Requires-Dist: paddlepaddle>=3.1.1; extra == 'all'
-Requires-Dist: pandas>=2.3.2; 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'
@@ -73,7 +73,6 @@ Provides-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>=2.3.2; extra == 'document-classification'
 Provides-Extra: easyocr
 Requires-Dist: easyocr>=1.7.2; extra == 'easyocr'
 Provides-Extra: entity-extraction
@@ -109,8 +108,7 @@ Description-Content-Type: text/markdown
 - **Text Extraction**: High-fidelity text extraction preserving document structure and formatting
 - **Metadata Extraction**: Comprehensive metadata including author, creation date, language, and document properties
 - **Format Support**: 18 document types including PDF, Microsoft Office, images, HTML, and structured data formats
-- **OCR Integration**: Multiple OCR engines (Tesseract, EasyOCR, PaddleOCR) with automatic fallback
-- **Table Detection**: Structured table extraction with cell-level precision via GMFT integration
+- **OCR Integration**: Tesseract OCR with markdown output (default) and table extraction from scanned documents
 - **Document Classification**: Automatic document type detection (contracts, forms, invoices, receipts, reports)
 
 ### Technical Architecture
@@ -138,8 +136,8 @@ Kreuzberg leverages established open source technologies:
 # Extract text from any file to text format
 uvx kreuzberg extract document.pdf > output.txt
 
-# With all features (OCR, table extraction, etc.)
-uvx --from "kreuzberg[all]" kreuzberg extract invoice.pdf --ocr-backend tesseract --output-format text
+# With all features (chunking, language detection, etc.)
+uvx kreuzberg extract invoice.pdf --ocr-backend tesseract --output-format text
 
 # Extract with rich metadata
 uvx kreuzberg extract report.pdf --show-metadata --output-format json
@@ -179,10 +177,15 @@ print(f"Keywords: {result.metadata.keywords}")
 
 ### Docker
 
+Two optimized images available:
+
 ```bash
-# Run the REST API
+# Base image (API + CLI + multilingual OCR)
 docker run -p 8000:8000 goldziher/kreuzberg
 
+# Core image (+ chunking + crypto + document classification + language detection)
+docker run -p 8000:8000 goldziher/kreuzberg-core:latest
+
 # Extract via API
 curl -X POST -F "file=@document.pdf" http://localhost:8000/extract
 ```
@@ -196,7 +199,7 @@ curl -X POST -F "file=@document.pdf" http://localhost:8000/extract
 **Add to Claude Desktop with one command:**
 
 ```bash
-claude mcp add kreuzberg uvx -- --from "kreuzberg[all]" kreuzberg-mcp
+claude mcp add kreuzberg uvx kreuzberg-mcp
 ```
 
 **Or configure manually in `claude_desktop_config.json`:**
@@ -206,7 +209,7 @@ claude mcp add kreuzberg uvx -- --from "kreuzberg[all]" kreuzberg-mcp
   "mcpServers": {
     "kreuzberg": {
       "command": "uvx",
-      "args": ["--from", "kreuzberg[all]", "kreuzberg-mcp"]
+      "args": ["kreuzberg-mcp"]
     }
   }
 }
@@ -215,8 +218,8 @@ claude mcp add kreuzberg uvx -- --from "kreuzberg[all]" kreuzberg-mcp
 **MCP capabilities:**
 
 - Extract text from PDFs, images, Office docs, and more
-- Full OCR support with multiple engines
-- Table extraction and metadata parsing
+- Multilingual OCR support with Tesseract
+- Metadata parsing and language detection
 
 📖 **[MCP Documentation](https://kreuzberg.dev/user-guide/mcp-server/)**
 

kreuzberg-3.13.0.dist-info/RECORD

@@ -0,0 +1,56 @@
+kreuzberg/__init__.py,sha256=Oh_NTp8wf0BlvD8CSBad2A493nEWH4jTE0x8v7v1Y9w,1341
+kreuzberg/__main__.py,sha256=3cIDdzTggj2kj8uKx4WShWHmCWqdZazdM3BxUGbAuSI,104
+kreuzberg/_chunker.py,sha256=y4-dX6ILjjBkkC1gkCzXb7v7vbi8844m7vz1gIzbmv4,1952
+kreuzberg/_config.py,sha256=dSTumnpleMeUjUabWgAH7WlhTkdNG3eeMv8FSFmUaEI,15776
+kreuzberg/_constants.py,sha256=Bxc8oiN-wHwnWXT9bEiJhTUcu1ygPpra5qHirAif3b4,191
+kreuzberg/_document_classification.py,sha256=NZ-6tQtVa1OgigC7xf30hAsnL5_gi9ak9X2XYdsCfTI,6361
+kreuzberg/_entity_extraction.py,sha256=QFIPQ_fovEnEezpS6W4pwpjTA2PqS7TUCD9AKf8sAyc,4666
+kreuzberg/_gmft.py,sha256=60WpPTf7jocU-kmkBe-pBytl7l58aQzd-Aw2_Hlioug,21481
+kreuzberg/_language_detection.py,sha256=yLUliJOUyofVma_q6FwzG9Ck4-XX3AEjxleTHrqi8R4,2445
+kreuzberg/_mime_types.py,sha256=fwtPKtp2XhCLT686qF26PBMeOqcVJroKPwkp7JgaM0E,8462
+kreuzberg/_playa.py,sha256=1viLRqgcDWvaPo5ZsDPO2gqHFSBApOYortTV_SPVK9k,12190
+kreuzberg/_registry.py,sha256=wGSlkS0U1zqruWQCLE95vj4a2mw1yyvf0j6rgz80sJg,3473
+kreuzberg/_types.py,sha256=WFUFY1S7SL7kTfHCX-zGASLYT94FxLD71C9vGUzFOiA,38922
+kreuzberg/cli.py,sha256=MLeWoMcLoN6WnkbyRbOY-2dqp-vNZf7Nb-K_R5F5CoU,12730
+kreuzberg/exceptions.py,sha256=PTiAZgQwcG9hXbgYg2W7sfxksFhq5_wzOFgZGnTJAoc,2991
+kreuzberg/extraction.py,sha256=jiMKiDyTf3sHyk76sMffHR-eH-_yg-DFRMuXEKufRYI,17649
+kreuzberg/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kreuzberg/_api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kreuzberg/_api/main.py,sha256=JALYRD0qwyoZloWk5dNNuslBtG4GlVNc0G2oADm6cAc,7578
+kreuzberg/_extractors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kreuzberg/_extractors/_base.py,sha256=EZTEJzwJxwu_yYFQ5QlZVNQMPCcli7yyUB4T5mFotCY,4209
+kreuzberg/_extractors/_email.py,sha256=mVi_VDmiFhe6NgiWxJDYt4DQiP6jVs5dP8BsPClm3WQ,6108
+kreuzberg/_extractors/_html.py,sha256=NyQKChNLvaSUC_5x1qTYlIQGwL4lEbgUF7BgH9ejEVY,1583
+kreuzberg/_extractors/_image.py,sha256=UZEOmKNAS4KjaX38iYq2Ux6Mta3juCF1MzWNeBxpPE8,3414
+kreuzberg/_extractors/_pandoc.py,sha256=zumwImIXwD3ziPhYxt0EQct5sSMy5lQiY6KnPSDxBTU,24183
+kreuzberg/_extractors/_pdf.py,sha256=766O7rXAeAJ42vPpWbGpW_WgHXm48eWwX09l3aqjKeM,18064
+kreuzberg/_extractors/_presentation.py,sha256=BJdEM9jsuAd0vb-PIRwNMcRj4xVjItb5kpOpnjsCBi0,10175
+kreuzberg/_extractors/_spread_sheet.py,sha256=wqAV-Stqfd4hXs5ock-chqBEdzv4voSgT1uFUO1cIU0,12075
+kreuzberg/_extractors/_structured.py,sha256=PpefI_GDrdLyUgnElrbdB-MeTMKVWium4Ckxm5Zg100,5536
+kreuzberg/_mcp/__init__.py,sha256=h6DgLFO4TMUk7_wCJ2jn2Y6IkFmfzb-Z7jX-G5UCYVc,43
+kreuzberg/_mcp/server.py,sha256=iYJG6g0u7I6mWtC4R1XlxydBrPpgnp5dGJzpm9QAZig,8438
+kreuzberg/_ocr/__init__.py,sha256=grshVFwVQl2rMvH1hg1JNlYXjy5-Tdb_rusLD1Cselk,706
+kreuzberg/_ocr/_base.py,sha256=IkONqwG6zxZoVMni1JlYugBoyONahlRny7J2_7Dy69c,3953
+kreuzberg/_ocr/_easyocr.py,sha256=CtiHGx_BmuUwZhC7bScYF9mwnAxRrLWJ-X70fuwFTjk,14079
+kreuzberg/_ocr/_paddleocr.py,sha256=wCuIQ_yxPWE9hukiehYNRdt00Rb2h6pWdfqPS8hI2s0,14297
+kreuzberg/_ocr/_table_extractor.py,sha256=MeQLQn_bRco5OAcUoy613ZbZLCDBRJY8uHH_bUBSP8I,7613
+kreuzberg/_ocr/_tesseract.py,sha256=i_UTjOmrFxZbtmXxrQIsE78wtZLTyZph0i0jDQc4EMA,56916
+kreuzberg/_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kreuzberg/_utils/_cache.py,sha256=fDqFp_54-Kyn3_4VkXkhovvNIB2osKqXlS13MlORrU8,14539
+kreuzberg/_utils/_device.py,sha256=35xQvrLSPISJlWicQGknoBjkwdalwVxiJbzyxwuwOVo,9747
+kreuzberg/_utils/_document_cache.py,sha256=CpCdJVd8SYLjfwm0ozSM8mx5x8i9vVDet3BlEUpzuZY,6920
+kreuzberg/_utils/_errors.py,sha256=ctD-s1q7vbEgqHQ3OVJiEOODDLTd2LvrM3z6o37zrGI,6395
+kreuzberg/_utils/_pdf_lock.py,sha256=mHB1A4Fo_nSfgdqUNEWODH9b5tNFqpEHcNE6rT41dGE,1886
+kreuzberg/_utils/_process_pool.py,sha256=ebuMPmHXPkWaLWjgAkeaONvAZo974PhfENN8pnPTCco,8415
+kreuzberg/_utils/_quality.py,sha256=m3SIXGDY9pfRmh3XeKdZWT1vBz7issH0SfKsutEuRxw,5833
+kreuzberg/_utils/_ref.py,sha256=uP_S3x0AQH2Nyjo1tYEj7N_u9hGzYVewdjch6a8Fv5I,1458
+kreuzberg/_utils/_serialization.py,sha256=duKP5OuBvi-m6ljQOhoyuJU7sl2WPnov8yJDpYuDArw,2052
+kreuzberg/_utils/_string.py,sha256=yrcwHHl23FxWrNoFXkmR3icgivfvbLRvkqQek8F3qqI,5020
+kreuzberg/_utils/_sync.py,sha256=mc-K2y_sc6mG-HOswlHTXAWaEzgisEERvq9PPw2dAw4,4869
+kreuzberg/_utils/_table.py,sha256=dYM_dWNHRCXcWOhSQBnahOJaBXyuQFyYX9arHrH4TF8,7555
+kreuzberg/_utils/_tmp.py,sha256=hVn-VVijIg2FM7EZJ899gc7wZg-TGoJZoeAcxMX-Cxg,1044
+kreuzberg-3.13.0.dist-info/METADATA,sha256=896BWDLD6ApGiOQFKXMqQezC4qgKRUxjMqbZVWxBoJ0,12098
+kreuzberg-3.13.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+kreuzberg-3.13.0.dist-info/entry_points.txt,sha256=GplGhFryCP7kyAG_k-Mdahznvo2fwi73qLFg5yQfH_A,91
+kreuzberg-3.13.0.dist-info/licenses/LICENSE,sha256=-8caMvpCK8SgZ5LlRKhGCMtYDEXqTKH9X8pFEhl91_4,1066
+kreuzberg-3.13.0.dist-info/RECORD,,

kreuzberg-3.11.4.dist-info/RECORD

@@ -1,54 +0,0 @@
-kreuzberg/__init__.py,sha256=0OJ_jNKbS6GxzWC5-EfRCiE80as_ya0-wwyNsTYbxzY,1721
-kreuzberg/__main__.py,sha256=s2qM1nPEkRHAQP-G3P7sf5l6qA_KJeIEHS5LpPz04lg,183
-kreuzberg/_chunker.py,sha256=y4-dX6ILjjBkkC1gkCzXb7v7vbi8844m7vz1gIzbmv4,1952
-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=6P4gSSmU39puaYAKmdGr9ALf0USYTwRDuvvhG1LmI24,26441
-kreuzberg/_language_detection.py,sha256=_Ng2aHgPxOHFgd507gVNiIGVmnxxbpgYwsO0bD0yTzg,3315
-kreuzberg/_mime_types.py,sha256=2warRVqfBUNIg8JBg8yP4pRqaMPvwINosHMkJwtH_Fc,8488
-kreuzberg/_playa.py,sha256=_IPrUSWwSfDQlWXOpKlauV0D9MhGrujGP5kmQ0U3L0g,12188
-kreuzberg/_registry.py,sha256=wGSlkS0U1zqruWQCLE95vj4a2mw1yyvf0j6rgz80sJg,3473
-kreuzberg/_types.py,sha256=bMaU6VuoqwOpW6ufshA-DWpNw6t9EokjEDEfFsznvdo,15389
-kreuzberg/cli.py,sha256=nG1CD_h50EWLmDbrb0_DffRl25uTCKeCS6_gRVpjEdU,12578
-kreuzberg/exceptions.py,sha256=PTiAZgQwcG9hXbgYg2W7sfxksFhq5_wzOFgZGnTJAoc,2991
-kreuzberg/extraction.py,sha256=Kt1mOxdlOb35yVOdpdhiRPuTgA9BW_TTG9qwCkSxSkc,17332
-kreuzberg/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-kreuzberg/_api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-kreuzberg/_api/main.py,sha256=8VwxRlIXwnPs7ZYm0saUZsNOjevEAWJQpNreG-X7ZpE,3273
-kreuzberg/_extractors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-kreuzberg/_extractors/_base.py,sha256=H_nwynBX3fozncVjV13c329x5eCLl5r7nyVTLQyDAzI,4396
-kreuzberg/_extractors/_email.py,sha256=Jpr4NFef640uVgNFkR1or-omy8RVt-NOHUYgWRDjyBo,6753
-kreuzberg/_extractors/_html.py,sha256=lOM1Tgrrvd7vpEeFAxC1dp0Tibr6N2FEHCjgFx0FK64,1745
-kreuzberg/_extractors/_image.py,sha256=Iz1JpvGqcYyh9g4zO_bMZG3E9S39KNHFu8PrXDRXeOk,4513
-kreuzberg/_extractors/_pandoc.py,sha256=51k7XISfKaPorhapG7aIeQb94KGsfozxKyT2rwhk9Bk,26553
-kreuzberg/_extractors/_pdf.py,sha256=OflyvwEkuFLmw8E3si35MCGH31fvd5o50VdMmu5QRVs,19884
-kreuzberg/_extractors/_presentation.py,sha256=CUlqZl_QCdJdumsZh0BpROkFbvi9uq7yMoIt3bRTUeE,10859
-kreuzberg/_extractors/_spread_sheet.py,sha256=iagiyJsnl-89OP1eqmEv8jWl7gZBJm2x0YOyqBgLasA,13733
-kreuzberg/_extractors/_structured.py,sha256=PbNaXd-_PUPsE0yZkISod_vLBokbWdVTKEPpEmqaEMM,5787
-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=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
-kreuzberg/_utils/_device.py,sha256=JI9p9TGSfQHEi2SL-ovOXMr9RUnVq-RrEly89OvmQ5w,10485
-kreuzberg/_utils/_document_cache.py,sha256=ka90JIT-FXUMOv8z2u3fztQgZZb2XQDHTMnBi32mySA,7005
-kreuzberg/_utils/_errors.py,sha256=UsktQ_p7eOj9crPsFDg8HgRSE5-IpuFC7y1e6dDI_fY,6503
-kreuzberg/_utils/_pdf_lock.py,sha256=nqxAYCNlfWDrJtP4ZNu57st1YnkDl-gYXdr0q8nv0kA,1961
-kreuzberg/_utils/_process_pool.py,sha256=4BqhmRspwMyPT2EBfTu_rrn7v722wlMLD8qlYvYsc00,8621
-kreuzberg/_utils/_quality.py,sha256=-nKzj5n7yJDYrvl556oq2T5S5oKMEOrjpcRMlZ00Jqo,7668
-kreuzberg/_utils/_serialization.py,sha256=cqqxqN2cmtndBhIr4v2wqiMwnNadnKhvuN7EUj3i18M,2290
-kreuzberg/_utils/_string.py,sha256=bCzO3UO6nXupxvtMWvHqfp1Vd9CTzEH9jmpJXQ7upAU,6800
-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-3.11.4.dist-info/METADATA,sha256=l3d8PyVfX_aEgXl5ykkuRHJi-8Qzhu4_KcHDYOK2RYg,12136
-kreuzberg-3.11.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-kreuzberg-3.11.4.dist-info/entry_points.txt,sha256=GplGhFryCP7kyAG_k-Mdahznvo2fwi73qLFg5yQfH_A,91
-kreuzberg-3.11.4.dist-info/licenses/LICENSE,sha256=-8caMvpCK8SgZ5LlRKhGCMtYDEXqTKH9X8pFEhl91_4,1066
-kreuzberg-3.11.4.dist-info/RECORD,,