vlm4ocr 0.1.0__py3-none-any.whl → 0.2.0__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.
- vlm4ocr/__init__.py +3 -1
- vlm4ocr/cli.py +276 -287
- vlm4ocr/data_types.py +109 -0
- vlm4ocr/ocr_engines.py +343 -192
- vlm4ocr/utils.py +332 -39
- vlm4ocr/vlm_engines.py +316 -190
- {vlm4ocr-0.1.0.dist-info → vlm4ocr-0.2.0.dist-info}/METADATA +3 -1
- {vlm4ocr-0.1.0.dist-info → vlm4ocr-0.2.0.dist-info}/RECORD +10 -9
- {vlm4ocr-0.1.0.dist-info → vlm4ocr-0.2.0.dist-info}/WHEEL +0 -0
- {vlm4ocr-0.1.0.dist-info → vlm4ocr-0.2.0.dist-info}/entry_points.txt +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
2
|
Name: vlm4ocr
|
|
3
|
-
Version: 0.
|
|
3
|
+
Version: 0.2.0
|
|
4
4
|
Summary: Python package and Web App for OCR with vision language models.
|
|
5
5
|
License: MIT
|
|
6
6
|
Author: Enshuo (David) Hsu
|
|
@@ -9,8 +9,10 @@ Classifier: License :: OSI Approved :: MIT License
|
|
|
9
9
|
Classifier: Programming Language :: Python :: 3
|
|
10
10
|
Classifier: Programming Language :: Python :: 3.11
|
|
11
11
|
Classifier: Programming Language :: Python :: 3.12
|
|
12
|
+
Provides-Extra: tesseract
|
|
12
13
|
Requires-Dist: pdf2image (>=1.16.0)
|
|
13
14
|
Requires-Dist: pillow (>=10.0.0)
|
|
15
|
+
Requires-Dist: pytesseract (>=0.3.13) ; extra == "tesseract"
|
|
14
16
|
Description-Content-Type: text/markdown
|
|
15
17
|
|
|
16
18
|
This is the readme for vlm4ocr Python package.
|
|
@@ -1,15 +1,16 @@
|
|
|
1
|
-
vlm4ocr/__init__.py,sha256=
|
|
1
|
+
vlm4ocr/__init__.py,sha256=k5TZY0LmRnjGyjHD0H5AxJHJMw_cS2SzGxTJ0NQbQsc,315
|
|
2
2
|
vlm4ocr/assets/default_prompt_templates/ocr_HTML_system_prompt.txt,sha256=igPOntiLDZXTB71-QrTmMJveb6XC1TgArg1serPc9V8,547
|
|
3
3
|
vlm4ocr/assets/default_prompt_templates/ocr_HTML_user_prompt.txt,sha256=cVn538JojZfCtIhfrcOPWt0dO7dtDqgB9xdS_5VvAqo,41
|
|
4
4
|
vlm4ocr/assets/default_prompt_templates/ocr_markdown_system_prompt.txt,sha256=pIsYO2G3jkZ5EWg7MJixre3Itz1oPqJSduUZT34_RNY,436
|
|
5
5
|
vlm4ocr/assets/default_prompt_templates/ocr_markdown_user_prompt.txt,sha256=61EJv8POsQGIIUVwCjDU73lMXJE7F3qhPIYl6zSbl1Q,45
|
|
6
6
|
vlm4ocr/assets/default_prompt_templates/ocr_text_system_prompt.txt,sha256=WbLSOerqFjlYGaGWJ-w2enhky1WhnPl011s0fgRPgnQ,398
|
|
7
7
|
vlm4ocr/assets/default_prompt_templates/ocr_text_user_prompt.txt,sha256=ftgNAIPy_UlrcY6m7-IkH2ApHkCzRnymra1w2wg60Ks,47
|
|
8
|
-
vlm4ocr/cli.py,sha256=
|
|
9
|
-
vlm4ocr/
|
|
10
|
-
vlm4ocr/
|
|
11
|
-
vlm4ocr/
|
|
12
|
-
vlm4ocr
|
|
13
|
-
vlm4ocr-0.
|
|
14
|
-
vlm4ocr-0.
|
|
15
|
-
vlm4ocr-0.
|
|
8
|
+
vlm4ocr/cli.py,sha256=b13WswreFxTNLA7n2F2jPR7Wrb2Onb06zFnvf7MOLi0,20268
|
|
9
|
+
vlm4ocr/data_types.py,sha256=OnbI5IFonp5jPUgq0RIHHSzR9EypJ3jaGoPxtbBpS04,3919
|
|
10
|
+
vlm4ocr/ocr_engines.py,sha256=KDU70U-SWkFUZR5fV0vKlnP_9HE0pE5ghzU7ihdTMjc,23605
|
|
11
|
+
vlm4ocr/utils.py,sha256=mwp3YDQaoS7YObXtLeuinSEGQ0fJ5KeQMAZmONIKvcg,11907
|
|
12
|
+
vlm4ocr/vlm_engines.py,sha256=jQuRZ5HlJtTtJXESiFcoYQXwX-lYu0gc-KKOpRLuW6A,22331
|
|
13
|
+
vlm4ocr-0.2.0.dist-info/METADATA,sha256=bpANMPUizxAnWDgrUO3bqNFHnlK72FnCX-7Q7x2bSpA,638
|
|
14
|
+
vlm4ocr-0.2.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
|
|
15
|
+
vlm4ocr-0.2.0.dist-info/entry_points.txt,sha256=qzWUk_QTZ12cH4DLjjfqce89EAlOydD85dreRRZF3K4,44
|
|
16
|
+
vlm4ocr-0.2.0.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|