vlmparse 0.1.0__tar.gz → 0.1.3__tar.gz

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 (63) hide show
  1. {vlmparse-0.1.0/vlmparse.egg-info → vlmparse-0.1.3}/PKG-INFO +12 -1
  2. {vlmparse-0.1.0 → vlmparse-0.1.3}/README.md +10 -0
  3. {vlmparse-0.1.0 → vlmparse-0.1.3}/pyproject.toml +3 -2
  4. vlmparse-0.1.3/vlmparse/benchpdf2md/bench_tests/benchmark_tsts.py +1763 -0
  5. vlmparse-0.1.3/vlmparse/benchpdf2md/bench_tests/utils.py +0 -0
  6. vlmparse-0.1.3/vlmparse/benchpdf2md/create_dataset.py +60 -0
  7. vlmparse-0.1.3/vlmparse/benchpdf2md/olmocrbench/katex/__init__.py +1 -0
  8. vlmparse-0.1.3/vlmparse/benchpdf2md/olmocrbench/katex/render.py +592 -0
  9. vlmparse-0.1.3/vlmparse/benchpdf2md/olmocrbench/repeatdetect.py +175 -0
  10. vlmparse-0.1.3/vlmparse/benchpdf2md/olmocrbench/run_olmocr_bench.py +256 -0
  11. vlmparse-0.1.3/vlmparse/benchpdf2md/olmocrbench/tests.py +1334 -0
  12. vlmparse-0.1.3/vlmparse/benchpdf2md/run_benchmark.py +296 -0
  13. vlmparse-0.1.3/vlmparse/benchpdf2md/st_visu_benchmark/app.py +271 -0
  14. vlmparse-0.1.3/vlmparse/benchpdf2md/st_visu_benchmark/highligh_text.py +117 -0
  15. vlmparse-0.1.3/vlmparse/benchpdf2md/st_visu_benchmark/test_form.py +95 -0
  16. vlmparse-0.1.3/vlmparse/benchpdf2md/st_visu_benchmark/ui_elements.py +20 -0
  17. vlmparse-0.1.3/vlmparse/benchpdf2md/st_visu_benchmark/utils.py +50 -0
  18. vlmparse-0.1.3/vlmparse/benchpdf2md/utils.py +56 -0
  19. vlmparse-0.1.3/vlmparse/clients/chandra.py +323 -0
  20. vlmparse-0.1.3/vlmparse/clients/deepseekocr.py +52 -0
  21. vlmparse-0.1.3/vlmparse/clients/docling.py +146 -0
  22. vlmparse-0.1.3/vlmparse/clients/dotsocr.py +277 -0
  23. vlmparse-0.1.3/vlmparse/clients/granite_docling.py +132 -0
  24. vlmparse-0.1.3/vlmparse/clients/hunyuanocr.py +45 -0
  25. vlmparse-0.1.3/vlmparse/clients/lightonocr.py +43 -0
  26. vlmparse-0.1.3/vlmparse/clients/mineru.py +119 -0
  27. vlmparse-0.1.3/vlmparse/clients/nanonetocr.py +29 -0
  28. vlmparse-0.1.3/vlmparse/clients/olmocr.py +46 -0
  29. vlmparse-0.1.3/vlmparse/clients/openai_converter.py +173 -0
  30. vlmparse-0.1.3/vlmparse/clients/paddleocrvl.py +48 -0
  31. vlmparse-0.1.3/vlmparse/clients/pipe_utils/cleaner.py +74 -0
  32. vlmparse-0.1.3/vlmparse/clients/pipe_utils/html_to_md_conversion.py +136 -0
  33. vlmparse-0.1.3/vlmparse/clients/pipe_utils/utils.py +12 -0
  34. vlmparse-0.1.3/vlmparse/clients/prompts.py +66 -0
  35. vlmparse-0.1.3/vlmparse/data_model/box.py +551 -0
  36. vlmparse-0.1.3/vlmparse/data_model/document.py +148 -0
  37. vlmparse-0.1.3/vlmparse/servers/docker_server.py +199 -0
  38. vlmparse-0.1.3/vlmparse/servers/utils.py +250 -0
  39. vlmparse-0.1.3/vlmparse/st_viewer/fs_nav.py +53 -0
  40. vlmparse-0.1.3/vlmparse/st_viewer/st_viewer.py +80 -0
  41. {vlmparse-0.1.0 → vlmparse-0.1.3/vlmparse.egg-info}/PKG-INFO +12 -1
  42. vlmparse-0.1.3/vlmparse.egg-info/SOURCES.txt +60 -0
  43. {vlmparse-0.1.0 → vlmparse-0.1.3}/vlmparse.egg-info/requires.txt +1 -0
  44. vlmparse-0.1.0/vlmparse.egg-info/SOURCES.txt +0 -23
  45. {vlmparse-0.1.0 → vlmparse-0.1.3}/LICENSE +0 -0
  46. {vlmparse-0.1.0 → vlmparse-0.1.3}/setup.cfg +0 -0
  47. {vlmparse-0.1.0 → vlmparse-0.1.3}/tests/test_all_converters_mocked.py +0 -0
  48. {vlmparse-0.1.0 → vlmparse-0.1.3}/tests/test_batch_parser.py +0 -0
  49. {vlmparse-0.1.0 → vlmparse-0.1.3}/tests/test_benchmark_tests.py +0 -0
  50. {vlmparse-0.1.0 → vlmparse-0.1.3}/tests/test_cli.py +0 -0
  51. {vlmparse-0.1.0 → vlmparse-0.1.3}/tests/test_end2end.py +0 -0
  52. {vlmparse-0.1.0 → vlmparse-0.1.3}/tests/test_process_and_run_benchmark.py +0 -0
  53. {vlmparse-0.1.0 → vlmparse-0.1.3}/tests/test_table_tests.py +0 -0
  54. {vlmparse-0.1.0 → vlmparse-0.1.3}/vlmparse/base_model.py +0 -0
  55. {vlmparse-0.1.0 → vlmparse-0.1.3}/vlmparse/build_doc.py +0 -0
  56. {vlmparse-0.1.0 → vlmparse-0.1.3}/vlmparse/cli.py +0 -0
  57. {vlmparse-0.1.0 → vlmparse-0.1.3}/vlmparse/converter.py +0 -0
  58. {vlmparse-0.1.0 → vlmparse-0.1.3}/vlmparse/converter_with_server.py +0 -0
  59. {vlmparse-0.1.0 → vlmparse-0.1.3}/vlmparse/registries.py +0 -0
  60. {vlmparse-0.1.0 → vlmparse-0.1.3}/vlmparse/utils.py +0 -0
  61. {vlmparse-0.1.0 → vlmparse-0.1.3}/vlmparse.egg-info/dependency_links.txt +0 -0
  62. {vlmparse-0.1.0 → vlmparse-0.1.3}/vlmparse.egg-info/entry_points.txt +0 -0
  63. {vlmparse-0.1.0 → vlmparse-0.1.3}/vlmparse.egg-info/top_level.txt +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: vlmparse
3
- Version: 0.1.0
3
+ Version: 0.1.3
4
4
  Requires-Python: >=3.12.0
5
5
  Description-Content-Type: text/markdown
6
6
  License-File: LICENSE
@@ -19,6 +19,7 @@ Requires-Dist: pypdfium2>=4.30.0
19
19
  Requires-Dist: fire>=0.7.1
20
20
  Requires-Dist: lxml>=6.0.2
21
21
  Requires-Dist: tabulate>=0.9.0
22
+ Requires-Dist: beautifulsoup4>=4.14.2
22
23
  Provides-Extra: dev
23
24
  Requires-Dist: jupyter; extra == "dev"
24
25
  Provides-Extra: docling-core
@@ -182,3 +183,13 @@ server.start()
182
183
 
183
184
  server.stop()
184
185
  ```
186
+
187
+
188
+ Converter with automatic server deployment:
189
+
190
+ ```python
191
+ from vlmparse.converter_with_server import ConverterWithServer
192
+
193
+ converter_with_server = ConverterWithServer(model="mineru2.5")
194
+ documents = converter_with_server.parse(inputs=["file1.pdf", "file2.pdf"], out_folder="./output")
195
+ ```
@@ -129,3 +129,13 @@ server.start()
129
129
 
130
130
  server.stop()
131
131
  ```
132
+
133
+
134
+ Converter with automatic server deployment:
135
+
136
+ ```python
137
+ from vlmparse.converter_with_server import ConverterWithServer
138
+
139
+ converter_with_server = ConverterWithServer(model="mineru2.5")
140
+ documents = converter_with_server.parse(inputs=["file1.pdf", "file2.pdf"], out_folder="./output")
141
+ ```
@@ -8,7 +8,7 @@ version = "0.1.0"
8
8
 
9
9
  [project]
10
10
  name = "vlmparse"
11
- version = "0.1.0"
11
+ version = "0.1.3"
12
12
  authors = []
13
13
  description = ""
14
14
  readme = "README.md"
@@ -29,6 +29,7 @@ dependencies = [
29
29
  "fire>=0.7.1",
30
30
  "lxml>=6.0.2",
31
31
  "tabulate>=0.9.0",
32
+ "beautifulsoup4>=4.14.2",
32
33
  ]
33
34
 
34
35
  [project.optional-dependencies]
@@ -69,7 +70,7 @@ test = [
69
70
  ]
70
71
 
71
72
  [tool.setuptools.packages.find]
72
- include = ["vlmparse"]
73
+ include = ["vlmparse", "vlmparse.*"]
73
74
 
74
75
  [project.scripts]
75
76
  vlmparse = "vlmparse.cli:main"