kreuzberg 3.11.4__py3-none-any.whl → 3.13.1__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (51) hide show
  1. kreuzberg/__init__.py +14 -13
  2. kreuzberg/__main__.py +0 -2
  3. kreuzberg/_api/main.py +119 -9
  4. kreuzberg/_chunker.py +0 -15
  5. kreuzberg/_config.py +212 -292
  6. kreuzberg/_document_classification.py +20 -47
  7. kreuzberg/_entity_extraction.py +1 -122
  8. kreuzberg/_extractors/_base.py +4 -71
  9. kreuzberg/_extractors/_email.py +1 -15
  10. kreuzberg/_extractors/_html.py +9 -12
  11. kreuzberg/_extractors/_image.py +1 -25
  12. kreuzberg/_extractors/_pandoc.py +10 -147
  13. kreuzberg/_extractors/_pdf.py +38 -94
  14. kreuzberg/_extractors/_presentation.py +0 -99
  15. kreuzberg/_extractors/_spread_sheet.py +13 -55
  16. kreuzberg/_extractors/_structured.py +1 -4
  17. kreuzberg/_gmft.py +14 -199
  18. kreuzberg/_language_detection.py +1 -36
  19. kreuzberg/_mcp/__init__.py +0 -2
  20. kreuzberg/_mcp/server.py +3 -10
  21. kreuzberg/_mime_types.py +1 -19
  22. kreuzberg/_ocr/_base.py +4 -76
  23. kreuzberg/_ocr/_easyocr.py +124 -186
  24. kreuzberg/_ocr/_paddleocr.py +154 -224
  25. kreuzberg/_ocr/_table_extractor.py +184 -0
  26. kreuzberg/_ocr/_tesseract.py +797 -361
  27. kreuzberg/_playa.py +5 -31
  28. kreuzberg/_registry.py +0 -36
  29. kreuzberg/_types.py +588 -93
  30. kreuzberg/_utils/_cache.py +84 -138
  31. kreuzberg/_utils/_device.py +0 -74
  32. kreuzberg/_utils/_document_cache.py +0 -75
  33. kreuzberg/_utils/_errors.py +0 -50
  34. kreuzberg/_utils/_ocr_cache.py +136 -0
  35. kreuzberg/_utils/_pdf_lock.py +0 -16
  36. kreuzberg/_utils/_process_pool.py +17 -64
  37. kreuzberg/_utils/_quality.py +0 -60
  38. kreuzberg/_utils/_ref.py +32 -0
  39. kreuzberg/_utils/_serialization.py +0 -30
  40. kreuzberg/_utils/_string.py +9 -59
  41. kreuzberg/_utils/_sync.py +0 -77
  42. kreuzberg/_utils/_table.py +49 -101
  43. kreuzberg/_utils/_tmp.py +0 -9
  44. kreuzberg/cli.py +54 -74
  45. kreuzberg/extraction.py +39 -32
  46. {kreuzberg-3.11.4.dist-info → kreuzberg-3.13.1.dist-info}/METADATA +19 -15
  47. kreuzberg-3.13.1.dist-info/RECORD +57 -0
  48. kreuzberg-3.11.4.dist-info/RECORD +0 -54
  49. {kreuzberg-3.11.4.dist-info → kreuzberg-3.13.1.dist-info}/WHEEL +0 -0
  50. {kreuzberg-3.11.4.dist-info → kreuzberg-3.13.1.dist-info}/entry_points.txt +0 -0
  51. {kreuzberg-3.11.4.dist-info → kreuzberg-3.13.1.dist-info}/licenses/LICENSE +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: kreuzberg
3
- Version: 3.11.4
3
+ Version: 3.13.1
4
4
  Summary: Document intelligence framework for Python - Extract text, metadata, and structured data from diverse file formats
5
5
  Project-URL: documentation, https://kreuzberg.dev
6
6
  Project-URL: homepage, https://github.com/Goldziher/kreuzberg
@@ -31,15 +31,17 @@ Requires-Python: >=3.10
31
31
  Requires-Dist: anyio>=4.10.0
32
32
  Requires-Dist: chardetng-py>=0.3.5
33
33
  Requires-Dist: exceptiongroup>=1.2.2; python_version < '3.11'
34
- Requires-Dist: html-to-markdown[lxml]>=1.9.0
34
+ Requires-Dist: html-to-markdown[lxml]>=1.9.1
35
35
  Requires-Dist: mcp>=1.13.0
36
36
  Requires-Dist: msgspec>=0.18.0
37
+ Requires-Dist: numpy>=1.24.0
37
38
  Requires-Dist: playa-pdf>=0.7.0
39
+ Requires-Dist: polars>=1.33.0
38
40
  Requires-Dist: psutil>=7.0.0
39
41
  Requires-Dist: pypdfium2==4.30.0
40
- Requires-Dist: python-calamine>=0.3.2
42
+ Requires-Dist: python-calamine>=0.5.2
41
43
  Requires-Dist: python-pptx>=1.0.2
42
- Requires-Dist: typing-extensions>=4.14.0; python_version < '3.12'
44
+ Requires-Dist: typing-extensions>=4.15.0; python_version < '3.12'
43
45
  Provides-Extra: additional-extensions
44
46
  Requires-Dist: mailparse>=1.0.15; extra == 'additional-extensions'
45
47
  Requires-Dist: tomli>=2.0.0; (python_version < '3.11') and extra == 'additional-extensions'
@@ -54,7 +56,6 @@ Requires-Dist: litestar[opentelemetry,standard,structlog]>=2.17.0; extra == 'all
54
56
  Requires-Dist: mailparse>=1.0.15; extra == 'all'
55
57
  Requires-Dist: paddleocr>=3.2.0; extra == 'all'
56
58
  Requires-Dist: paddlepaddle>=3.1.1; extra == 'all'
57
- Requires-Dist: pandas>=2.3.2; extra == 'all'
58
59
  Requires-Dist: playa-pdf[crypto]>=0.7.0; extra == 'all'
59
60
  Requires-Dist: rich>=14.1.0; extra == 'all'
60
61
  Requires-Dist: semantic-text-splitter>=0.27.0; extra == 'all'
@@ -73,7 +74,6 @@ Provides-Extra: crypto
73
74
  Requires-Dist: playa-pdf[crypto]>=0.7.0; extra == 'crypto'
74
75
  Provides-Extra: document-classification
75
76
  Requires-Dist: deep-translator>=1.11.4; extra == 'document-classification'
76
- Requires-Dist: pandas>=2.3.2; extra == 'document-classification'
77
77
  Provides-Extra: easyocr
78
78
  Requires-Dist: easyocr>=1.7.2; extra == 'easyocr'
79
79
  Provides-Extra: entity-extraction
@@ -109,8 +109,7 @@ Description-Content-Type: text/markdown
109
109
  - **Text Extraction**: High-fidelity text extraction preserving document structure and formatting
110
110
  - **Metadata Extraction**: Comprehensive metadata including author, creation date, language, and document properties
111
111
  - **Format Support**: 18 document types including PDF, Microsoft Office, images, HTML, and structured data formats
112
- - **OCR Integration**: Multiple OCR engines (Tesseract, EasyOCR, PaddleOCR) with automatic fallback
113
- - **Table Detection**: Structured table extraction with cell-level precision via GMFT integration
112
+ - **OCR Integration**: Tesseract OCR with markdown output (default) and table extraction from scanned documents
114
113
  - **Document Classification**: Automatic document type detection (contracts, forms, invoices, receipts, reports)
115
114
 
116
115
  ### Technical Architecture
@@ -138,8 +137,8 @@ Kreuzberg leverages established open source technologies:
138
137
  # Extract text from any file to text format
139
138
  uvx kreuzberg extract document.pdf > output.txt
140
139
 
141
- # With all features (OCR, table extraction, etc.)
142
- uvx --from "kreuzberg[all]" kreuzberg extract invoice.pdf --ocr-backend tesseract --output-format text
140
+ # With all features (chunking, language detection, etc.)
141
+ uvx kreuzberg extract invoice.pdf --ocr-backend tesseract --output-format text
143
142
 
144
143
  # Extract with rich metadata
145
144
  uvx kreuzberg extract report.pdf --show-metadata --output-format json
@@ -179,10 +178,15 @@ print(f"Keywords: {result.metadata.keywords}")
179
178
 
180
179
  ### Docker
181
180
 
181
+ Two optimized images available:
182
+
182
183
  ```bash
183
- # Run the REST API
184
+ # Base image (API + CLI + multilingual OCR)
184
185
  docker run -p 8000:8000 goldziher/kreuzberg
185
186
 
187
+ # Core image (+ chunking + crypto + document classification + language detection)
188
+ docker run -p 8000:8000 goldziher/kreuzberg-core:latest
189
+
186
190
  # Extract via API
187
191
  curl -X POST -F "file=@document.pdf" http://localhost:8000/extract
188
192
  ```
@@ -196,7 +200,7 @@ curl -X POST -F "file=@document.pdf" http://localhost:8000/extract
196
200
  **Add to Claude Desktop with one command:**
197
201
 
198
202
  ```bash
199
- claude mcp add kreuzberg uvx -- --from "kreuzberg[all]" kreuzberg-mcp
203
+ claude mcp add kreuzberg uvx kreuzberg-mcp
200
204
  ```
201
205
 
202
206
  **Or configure manually in `claude_desktop_config.json`:**
@@ -206,7 +210,7 @@ claude mcp add kreuzberg uvx -- --from "kreuzberg[all]" kreuzberg-mcp
206
210
  "mcpServers": {
207
211
  "kreuzberg": {
208
212
  "command": "uvx",
209
- "args": ["--from", "kreuzberg[all]", "kreuzberg-mcp"]
213
+ "args": ["kreuzberg-mcp"]
210
214
  }
211
215
  }
212
216
  }
@@ -215,8 +219,8 @@ claude mcp add kreuzberg uvx -- --from "kreuzberg[all]" kreuzberg-mcp
215
219
  **MCP capabilities:**
216
220
 
217
221
  - Extract text from PDFs, images, Office docs, and more
218
- - Full OCR support with multiple engines
219
- - Table extraction and metadata parsing
222
+ - Multilingual OCR support with Tesseract
223
+ - Metadata parsing and language detection
220
224
 
221
225
  📖 **[MCP Documentation](https://kreuzberg.dev/user-guide/mcp-server/)**
222
226
 
@@ -0,0 +1,57 @@
1
+ kreuzberg/__init__.py,sha256=Oh_NTp8wf0BlvD8CSBad2A493nEWH4jTE0x8v7v1Y9w,1341
2
+ kreuzberg/__main__.py,sha256=3cIDdzTggj2kj8uKx4WShWHmCWqdZazdM3BxUGbAuSI,104
3
+ kreuzberg/_chunker.py,sha256=tr9_KUYTSLauFois3MsB-A-0hGcTT8hTQFrqNRTii-I,1373
4
+ kreuzberg/_config.py,sha256=Q5oiJE1XRf8ITuYcO8LZAOB3G2zNlXz2458rgPSth-U,12257
5
+ kreuzberg/_constants.py,sha256=Bxc8oiN-wHwnWXT9bEiJhTUcu1ygPpra5qHirAif3b4,191
6
+ kreuzberg/_document_classification.py,sha256=Mz_s2GJGsEl7MQ-67BPoGYCZibTy9Sw0PScUZKBjKOA,5736
7
+ kreuzberg/_entity_extraction.py,sha256=5YpPnqoJ5aiHd_sy4bN4-Ngiq79RhCV6yaUQE8joGXo,3503
8
+ kreuzberg/_gmft.py,sha256=jKbD7V_KP9XTLjT9SBgSgE3CyDjqbRDm9BAiWV2sAC0,19542
9
+ kreuzberg/_language_detection.py,sha256=T9p6aimB7QFXAQiEntIMZeH_Z62E52E8fBQ43hWuyhs,1960
10
+ kreuzberg/_mime_types.py,sha256=kGBDSMO4XPgzUKC7iaBeChCtRQXZ9_zXq6eJydejX_k,7739
11
+ kreuzberg/_playa.py,sha256=p4G5ymSSCbQoDeXJjH-yuVzdd4y-wKcolqDthjPtqok,11413
12
+ kreuzberg/_registry.py,sha256=8cPpz3oZVnMwWDT2v_Q7wf-GHd5YuHmc-nkLtvPfE1I,2433
13
+ kreuzberg/_types.py,sha256=D-2d_WG8HyByA163izGhjk7t-e4FL_N-_6UzlVso8Dg,36020
14
+ kreuzberg/cli.py,sha256=MLeWoMcLoN6WnkbyRbOY-2dqp-vNZf7Nb-K_R5F5CoU,12730
15
+ kreuzberg/exceptions.py,sha256=PTiAZgQwcG9hXbgYg2W7sfxksFhq5_wzOFgZGnTJAoc,2991
16
+ kreuzberg/extraction.py,sha256=jiMKiDyTf3sHyk76sMffHR-eH-_yg-DFRMuXEKufRYI,17649
17
+ kreuzberg/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
18
+ kreuzberg/_api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
19
+ kreuzberg/_api/main.py,sha256=JALYRD0qwyoZloWk5dNNuslBtG4GlVNc0G2oADm6cAc,7578
20
+ kreuzberg/_extractors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
21
+ kreuzberg/_extractors/_base.py,sha256=i2FvAhRnamEtBb4a-C7pfcdWIXnkEBw0saMQu7h1_RQ,2069
22
+ kreuzberg/_extractors/_email.py,sha256=jn_8J4BASKJ7zFHBG0PgxNe3OT4pjmEM2tTKX8y_0AE,5887
23
+ kreuzberg/_extractors/_html.py,sha256=NyQKChNLvaSUC_5x1qTYlIQGwL4lEbgUF7BgH9ejEVY,1583
24
+ kreuzberg/_extractors/_image.py,sha256=UqPoYfvDRX6Rd1yPhcLHJLDw6d2cUzgkqOGjh2eleJM,3301
25
+ kreuzberg/_extractors/_pandoc.py,sha256=-Ai4S1cXs7F6yeonb_7Y7_ZoWHn29E2oP1WlPtM-4HM,22505
26
+ kreuzberg/_extractors/_pdf.py,sha256=Yv_c3xYzrGAjgTbwCGqbiQTDLjIUP_Pu7Z3GmMOqgqg,17865
27
+ kreuzberg/_extractors/_presentation.py,sha256=ULGkt7dzeA9sYSEhpAucKZmkdv9EubzeZtOjoLP3Z2E,6994
28
+ kreuzberg/_extractors/_spread_sheet.py,sha256=x25u2M-ufxpDd7_qrjhMEz1yFftIcOISE1qwPW09Zm0,11962
29
+ kreuzberg/_extractors/_structured.py,sha256=PpefI_GDrdLyUgnElrbdB-MeTMKVWium4Ckxm5Zg100,5536
30
+ kreuzberg/_mcp/__init__.py,sha256=h6DgLFO4TMUk7_wCJ2jn2Y6IkFmfzb-Z7jX-G5UCYVc,43
31
+ kreuzberg/_mcp/server.py,sha256=iYJG6g0u7I6mWtC4R1XlxydBrPpgnp5dGJzpm9QAZig,8438
32
+ kreuzberg/_ocr/__init__.py,sha256=grshVFwVQl2rMvH1hg1JNlYXjy5-Tdb_rusLD1Cselk,706
33
+ kreuzberg/_ocr/_base.py,sha256=5ef2g8JuSaZF2sDiAmoaODHbeG4MT0LtNzbtW0n9BnU,1445
34
+ kreuzberg/_ocr/_easyocr.py,sha256=XbgpGt5tkE4xHleIGvV1cHlpOQTp43rSXBO1CyIyKTg,14599
35
+ kreuzberg/_ocr/_paddleocr.py,sha256=58sKOHfKCHGFJNlRLrJwey8G_7xbsAAPBXB4n3hKc7k,14052
36
+ kreuzberg/_ocr/_table_extractor.py,sha256=LhBiCX8R_xR-uK1FH3ONA_vqOmqUWANZJ2HMCBLsmNY,5513
37
+ kreuzberg/_ocr/_tesseract.py,sha256=xGML3ygY5xMN5T3YznrKDVAH_DWfaFiteFBo_-GpjCs,48931
38
+ kreuzberg/_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
39
+ kreuzberg/_utils/_cache.py,sha256=S6Oc4TJamiuuWeJ2ABxDFbbQh4o8w38AUyZeBEc1NN8,12767
40
+ kreuzberg/_utils/_device.py,sha256=UxGkSTN3Up-Zn43CSyvf8CozW2xAF05Cm01LWA2FZmg,8263
41
+ kreuzberg/_utils/_document_cache.py,sha256=tfk9_Yc1cQkT5_uM5R1uaI4w-2SjNn7QyAd6AmWkSz8,4851
42
+ kreuzberg/_utils/_errors.py,sha256=aQYEnp8oJ-WJVmCNo7YY-25y1KZZFEwjAmxVRfw4a_M,4920
43
+ kreuzberg/_utils/_ocr_cache.py,sha256=8_-qmPlK2adQKsH4OO4Mlk8wmqBMl3XxkcV_NsXVyFs,3501
44
+ kreuzberg/_utils/_pdf_lock.py,sha256=Ytvds30aZf3yXeZFo27ZenrhUoU-GZlR2rKEkhJ_wlk,1349
45
+ kreuzberg/_utils/_process_pool.py,sha256=9dPMD_gBocQ5VaeCIrlSJfPXKyXNuyKaATmqOPExxiE,6723
46
+ kreuzberg/_utils/_quality.py,sha256=f7NbyZysyJQD8jKCNWhogvluU9A7GdEYhMsDBeMbGAA,5412
47
+ kreuzberg/_utils/_ref.py,sha256=iOflvjTUc_F0XaL28Bd6fpvL6qkeoURGA4B77Nqky7I,840
48
+ kreuzberg/_utils/_serialization.py,sha256=97iIgdcxdbym-BEvy0J6HAduBCUXyCGwhuEHCT_l7I4,1513
49
+ kreuzberg/_utils/_string.py,sha256=wVyvEHByHBeu_6evmqJGv9Ml-NAwkyz60n8l-7L5Cw0,4366
50
+ kreuzberg/_utils/_sync.py,sha256=OWiciXPTGHIxgiGoHI2AglZ1siTNT-nU_JCgHPNzzHk,2196
51
+ kreuzberg/_utils/_table.py,sha256=R-6owHjvcvHGhem_vDsFH7S2yMHGoUUO2PFcj-Idptk,6361
52
+ kreuzberg/_utils/_tmp.py,sha256=wnOInBkcuQoxI1vBLvNv9NqbRCEu9Y03qfOjqQuAk3s,841
53
+ kreuzberg-3.13.1.dist-info/METADATA,sha256=tle3wdEqeitG4inON0f59QltYcZW_xTW5iyggasDEz0,12127
54
+ kreuzberg-3.13.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
55
+ kreuzberg-3.13.1.dist-info/entry_points.txt,sha256=GplGhFryCP7kyAG_k-Mdahznvo2fwi73qLFg5yQfH_A,91
56
+ kreuzberg-3.13.1.dist-info/licenses/LICENSE,sha256=-8caMvpCK8SgZ5LlRKhGCMtYDEXqTKH9X8pFEhl91_4,1066
57
+ kreuzberg-3.13.1.dist-info/RECORD,,
@@ -1,54 +0,0 @@
1
- kreuzberg/__init__.py,sha256=0OJ_jNKbS6GxzWC5-EfRCiE80as_ya0-wwyNsTYbxzY,1721
2
- kreuzberg/__main__.py,sha256=s2qM1nPEkRHAQP-G3P7sf5l6qA_KJeIEHS5LpPz04lg,183
3
- kreuzberg/_chunker.py,sha256=y4-dX6ILjjBkkC1gkCzXb7v7vbi8844m7vz1gIzbmv4,1952
4
- kreuzberg/_config.py,sha256=Au521UiR7vcQs_8_hhoWIfmDDMJIrDM3XZUB_qHfCmo,14035
5
- kreuzberg/_constants.py,sha256=Bxc8oiN-wHwnWXT9bEiJhTUcu1ygPpra5qHirAif3b4,191
6
- kreuzberg/_document_classification.py,sha256=qFGmwvUMhnNAvNNJO7E-huPx-Ps-_DWxdNxsozIzgaw,6870
7
- kreuzberg/_entity_extraction.py,sha256=Oa1T-9mptimpOHtcda-GtrVYH9PFy7DSJj3thJZUD7k,7902
8
- kreuzberg/_gmft.py,sha256=6P4gSSmU39puaYAKmdGr9ALf0USYTwRDuvvhG1LmI24,26441
9
- kreuzberg/_language_detection.py,sha256=_Ng2aHgPxOHFgd507gVNiIGVmnxxbpgYwsO0bD0yTzg,3315
10
- kreuzberg/_mime_types.py,sha256=2warRVqfBUNIg8JBg8yP4pRqaMPvwINosHMkJwtH_Fc,8488
11
- kreuzberg/_playa.py,sha256=_IPrUSWwSfDQlWXOpKlauV0D9MhGrujGP5kmQ0U3L0g,12188
12
- kreuzberg/_registry.py,sha256=wGSlkS0U1zqruWQCLE95vj4a2mw1yyvf0j6rgz80sJg,3473
13
- kreuzberg/_types.py,sha256=bMaU6VuoqwOpW6ufshA-DWpNw6t9EokjEDEfFsznvdo,15389
14
- kreuzberg/cli.py,sha256=nG1CD_h50EWLmDbrb0_DffRl25uTCKeCS6_gRVpjEdU,12578
15
- kreuzberg/exceptions.py,sha256=PTiAZgQwcG9hXbgYg2W7sfxksFhq5_wzOFgZGnTJAoc,2991
16
- kreuzberg/extraction.py,sha256=Kt1mOxdlOb35yVOdpdhiRPuTgA9BW_TTG9qwCkSxSkc,17332
17
- kreuzberg/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
18
- kreuzberg/_api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
19
- kreuzberg/_api/main.py,sha256=8VwxRlIXwnPs7ZYm0saUZsNOjevEAWJQpNreG-X7ZpE,3273
20
- kreuzberg/_extractors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
21
- kreuzberg/_extractors/_base.py,sha256=H_nwynBX3fozncVjV13c329x5eCLl5r7nyVTLQyDAzI,4396
22
- kreuzberg/_extractors/_email.py,sha256=Jpr4NFef640uVgNFkR1or-omy8RVt-NOHUYgWRDjyBo,6753
23
- kreuzberg/_extractors/_html.py,sha256=lOM1Tgrrvd7vpEeFAxC1dp0Tibr6N2FEHCjgFx0FK64,1745
24
- kreuzberg/_extractors/_image.py,sha256=Iz1JpvGqcYyh9g4zO_bMZG3E9S39KNHFu8PrXDRXeOk,4513
25
- kreuzberg/_extractors/_pandoc.py,sha256=51k7XISfKaPorhapG7aIeQb94KGsfozxKyT2rwhk9Bk,26553
26
- kreuzberg/_extractors/_pdf.py,sha256=OflyvwEkuFLmw8E3si35MCGH31fvd5o50VdMmu5QRVs,19884
27
- kreuzberg/_extractors/_presentation.py,sha256=CUlqZl_QCdJdumsZh0BpROkFbvi9uq7yMoIt3bRTUeE,10859
28
- kreuzberg/_extractors/_spread_sheet.py,sha256=iagiyJsnl-89OP1eqmEv8jWl7gZBJm2x0YOyqBgLasA,13733
29
- kreuzberg/_extractors/_structured.py,sha256=PbNaXd-_PUPsE0yZkISod_vLBokbWdVTKEPpEmqaEMM,5787
30
- kreuzberg/_mcp/__init__.py,sha256=8PYV-omC8Rln7Cove8C3rHu3d7sR1FuiwSBG1O7vkAE,92
31
- kreuzberg/_mcp/server.py,sha256=Dxed80MqZsYCFyYo0QdArpKE4H8DhpKY34fijdzV5uw,8731
32
- kreuzberg/_ocr/__init__.py,sha256=grshVFwVQl2rMvH1hg1JNlYXjy5-Tdb_rusLD1Cselk,706
33
- kreuzberg/_ocr/_base.py,sha256=IkONqwG6zxZoVMni1JlYugBoyONahlRny7J2_7Dy69c,3953
34
- kreuzberg/_ocr/_easyocr.py,sha256=eU4MA_B_-cvq_IhpCeYUruL_kqcfm8maNZKP7zvVQHI,17512
35
- kreuzberg/_ocr/_paddleocr.py,sha256=I7ns6L56a2Ol460Bge6e0hpc2AkkwDepLcpCsABj5Dc,17609
36
- kreuzberg/_ocr/_tesseract.py,sha256=teLMH1pBhpcmEXDcyZlv56hYINLGMuaKZ0CQtcu_czQ,31510
37
- kreuzberg/_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
38
- kreuzberg/_utils/_cache.py,sha256=hYd_a5Ni5VJBE1XU_eN9gvQ5gg0FRsdbRgmJe-OIJHM,15253
39
- kreuzberg/_utils/_device.py,sha256=JI9p9TGSfQHEi2SL-ovOXMr9RUnVq-RrEly89OvmQ5w,10485
40
- kreuzberg/_utils/_document_cache.py,sha256=ka90JIT-FXUMOv8z2u3fztQgZZb2XQDHTMnBi32mySA,7005
41
- kreuzberg/_utils/_errors.py,sha256=UsktQ_p7eOj9crPsFDg8HgRSE5-IpuFC7y1e6dDI_fY,6503
42
- kreuzberg/_utils/_pdf_lock.py,sha256=nqxAYCNlfWDrJtP4ZNu57st1YnkDl-gYXdr0q8nv0kA,1961
43
- kreuzberg/_utils/_process_pool.py,sha256=4BqhmRspwMyPT2EBfTu_rrn7v722wlMLD8qlYvYsc00,8621
44
- kreuzberg/_utils/_quality.py,sha256=-nKzj5n7yJDYrvl556oq2T5S5oKMEOrjpcRMlZ00Jqo,7668
45
- kreuzberg/_utils/_serialization.py,sha256=cqqxqN2cmtndBhIr4v2wqiMwnNadnKhvuN7EUj3i18M,2290
46
- kreuzberg/_utils/_string.py,sha256=bCzO3UO6nXupxvtMWvHqfp1Vd9CTzEH9jmpJXQ7upAU,6800
47
- kreuzberg/_utils/_sync.py,sha256=7LSavBmxVKQUzdjfx9fYRAI9IbJtRw8iGf_Q8B7RX9g,4923
48
- kreuzberg/_utils/_table.py,sha256=IomrfQBP85DZI8RmQjOVs2Siq7VP9FUTYPaZR4t3yRw,8199
49
- kreuzberg/_utils/_tmp.py,sha256=hVn-VVijIg2FM7EZJ899gc7wZg-TGoJZoeAcxMX-Cxg,1044
50
- kreuzberg-3.11.4.dist-info/METADATA,sha256=l3d8PyVfX_aEgXl5ykkuRHJi-8Qzhu4_KcHDYOK2RYg,12136
51
- kreuzberg-3.11.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
52
- kreuzberg-3.11.4.dist-info/entry_points.txt,sha256=GplGhFryCP7kyAG_k-Mdahznvo2fwi73qLFg5yQfH_A,91
53
- kreuzberg-3.11.4.dist-info/licenses/LICENSE,sha256=-8caMvpCK8SgZ5LlRKhGCMtYDEXqTKH9X8pFEhl91_4,1066
54
- kreuzberg-3.11.4.dist-info/RECORD,,