pembot 0.1.9__py2.py3-none-any.whl → 0.1.11__py2.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.

Potentially problematic release.


This version of pembot might be problematic. Click here for more details.

Files changed (33) hide show
  1. pembot/.git/COMMIT_EDITMSG +1 -1
  2. pembot/.git/ORIG_HEAD +1 -0
  3. pembot/.git/index +0 -0
  4. pembot/.git/logs/HEAD +4 -0
  5. pembot/.git/logs/refs/heads/main +4 -0
  6. pembot/.git/logs/refs/remotes/origin/main +2 -0
  7. pembot/.git/objects/15/16e2e3e4eb2a9a5304ed49c8405e19ac6ee3e5 +0 -0
  8. pembot/.git/objects/49/f51d334a46a3ca299c1d63b22af62bd3af5cd0 +0 -0
  9. pembot/.git/objects/5d/2259f832675fd5a5031ee436a1bc8909acd6c9 +0 -0
  10. pembot/.git/objects/7c/b239898298ddc45e5b1dfae1ae145b75e627bd +0 -0
  11. pembot/.git/objects/8c/122efcd19ed7f20b8e7ce8eaecdff8e67ca8fa +0 -0
  12. pembot/.git/objects/92/94065a10a11fe0ba233baeb658f605bacd1625 +0 -0
  13. pembot/.git/objects/95/5e4b9fb51a8891b972a85719a25b521bdaf97e +0 -0
  14. pembot/.git/objects/a2/8dc2ae0dec8333e8a24d1d195067acf2bc03fc +0 -0
  15. pembot/.git/objects/b9/633511cf991d84b40c4606b9d124c9beb22df1 +0 -0
  16. pembot/.git/objects/bd/e1d2d032cd63206ec22230ff3e3ba6dbee804f +0 -0
  17. pembot/.git/objects/d6/3c63232c606d61eaaa7acce7a7a07d134d04da +0 -0
  18. pembot/.git/objects/dd/d2e5c09eea11798956f2de7df33a9b1eee7e62 +0 -0
  19. pembot/.git/objects/e2/dc7f666268cf207253a15d55a7fc73093c6d3b +3 -0
  20. pembot/.git/objects/e5/0cd305278d92afa13f3876027fd52639368788 +0 -0
  21. pembot/.git/objects/f1/2d47700be1ed59a6f0be8d84c3ec9b4404ec00 +0 -0
  22. pembot/.git/refs/heads/main +1 -1
  23. pembot/.git/refs/remotes/origin/main +1 -1
  24. pembot/AnyToText/convertor.py +1 -0
  25. pembot/__init__.py +1 -1
  26. pembot/config/config.yaml +1 -1
  27. pembot/pdf2markdown/extract.py +5 -7
  28. pembot/pdf2markdown/logs/extract.log +0 -0
  29. pembot/requirements.txt +1 -1
  30. {pembot-0.1.9.dist-info → pembot-0.1.11.dist-info}/METADATA +1 -1
  31. {pembot-0.1.9.dist-info → pembot-0.1.11.dist-info}/RECORD +33 -16
  32. {pembot-0.1.9.dist-info → pembot-0.1.11.dist-info}/WHEEL +0 -0
  33. {pembot-0.1.9.dist-info → pembot-0.1.11.dist-info}/licenses/LICENSE +0 -0
@@ -1 +1 @@
1
- added DeepSeek-OCR as a model option to use spaces
1
+ raised error if gpu limit exceeded instead of returning empty
pembot/.git/ORIG_HEAD ADDED
@@ -0,0 +1 @@
1
+ 5d2259f832675fd5a5031ee436a1bc8909acd6c9
pembot/.git/index CHANGED
Binary file
pembot/.git/logs/HEAD CHANGED
@@ -21,3 +21,7 @@ e6adbc3c373070269f97ef82d4f63027d7878f67 81d01e1c63d48b096c77aae83471d42272ca9fc
21
21
  e89cb4f5af158d26dcff5eed03dba6671a818739 e3c62c141fc65ef2be0095c49b23e06263f0b734 cyto <silverstone965@gmail.com> 1758892053 +0530 commit: silly willy mistake
22
22
  e3c62c141fc65ef2be0095c49b23e06263f0b734 d440b20aae1265dabbd3ddaafb24c35e40e3ab3c cyto <silverstone965@gmail.com> 1759127664 +0530 commit: cyto/fixed the excel file input bug, in the conversion method; added exceptions where there is invalid input
23
23
  d440b20aae1265dabbd3ddaafb24c35e40e3ab3c 8d58ec13be39949ecfe7211b42c56acd2a83dc72 cyto <silverstone965@gmail.com> 1761392079 +0530 commit: added DeepSeek-OCR as a model option to use spaces
24
+ 8d58ec13be39949ecfe7211b42c56acd2a83dc72 e2dc7f666268cf207253a15d55a7fc73093c6d3b cyto <silverstone965@gmail.com> 1761539934 +0530 commit: added logs; fixed typo
25
+ e2dc7f666268cf207253a15d55a7fc73093c6d3b 5d2259f832675fd5a5031ee436a1bc8909acd6c9 cyto <silverstone965@gmail.com> 1761794401 +0530 commit: raised error if gpu limit exceeded instead of returning empty
26
+ 5d2259f832675fd5a5031ee436a1bc8909acd6c9 e2dc7f666268cf207253a15d55a7fc73093c6d3b cyto <silverstone965@gmail.com> 1761794509 +0530 reset: moving to HEAD~
27
+ e2dc7f666268cf207253a15d55a7fc73093c6d3b ddd2e5c09eea11798956f2de7df33a9b1eee7e62 cyto <silverstone965@gmail.com> 1761794413 +0530 commit: raised error if gpu limit exceeded instead of returning empty
@@ -21,3 +21,7 @@ e6adbc3c373070269f97ef82d4f63027d7878f67 81d01e1c63d48b096c77aae83471d42272ca9fc
21
21
  e89cb4f5af158d26dcff5eed03dba6671a818739 e3c62c141fc65ef2be0095c49b23e06263f0b734 cyto <silverstone965@gmail.com> 1758892053 +0530 commit: silly willy mistake
22
22
  e3c62c141fc65ef2be0095c49b23e06263f0b734 d440b20aae1265dabbd3ddaafb24c35e40e3ab3c cyto <silverstone965@gmail.com> 1759127664 +0530 commit: cyto/fixed the excel file input bug, in the conversion method; added exceptions where there is invalid input
23
23
  d440b20aae1265dabbd3ddaafb24c35e40e3ab3c 8d58ec13be39949ecfe7211b42c56acd2a83dc72 cyto <silverstone965@gmail.com> 1761392079 +0530 commit: added DeepSeek-OCR as a model option to use spaces
24
+ 8d58ec13be39949ecfe7211b42c56acd2a83dc72 e2dc7f666268cf207253a15d55a7fc73093c6d3b cyto <silverstone965@gmail.com> 1761539934 +0530 commit: added logs; fixed typo
25
+ e2dc7f666268cf207253a15d55a7fc73093c6d3b 5d2259f832675fd5a5031ee436a1bc8909acd6c9 cyto <silverstone965@gmail.com> 1761794401 +0530 commit: raised error if gpu limit exceeded instead of returning empty
26
+ 5d2259f832675fd5a5031ee436a1bc8909acd6c9 e2dc7f666268cf207253a15d55a7fc73093c6d3b cyto <silverstone965@gmail.com> 1761794509 +0530 reset: moving to HEAD~
27
+ e2dc7f666268cf207253a15d55a7fc73093c6d3b ddd2e5c09eea11798956f2de7df33a9b1eee7e62 cyto <silverstone965@gmail.com> 1761794413 +0530 commit: raised error if gpu limit exceeded instead of returning empty
@@ -20,3 +20,5 @@ e6adbc3c373070269f97ef82d4f63027d7878f67 81d01e1c63d48b096c77aae83471d42272ca9fc
20
20
  e89cb4f5af158d26dcff5eed03dba6671a818739 e3c62c141fc65ef2be0095c49b23e06263f0b734 cyto <silverstone965@gmail.com> 1758892065 +0530 update by push
21
21
  e3c62c141fc65ef2be0095c49b23e06263f0b734 d440b20aae1265dabbd3ddaafb24c35e40e3ab3c cyto <silverstone965@gmail.com> 1759127680 +0530 update by push
22
22
  d440b20aae1265dabbd3ddaafb24c35e40e3ab3c 8d58ec13be39949ecfe7211b42c56acd2a83dc72 cyto <silverstone965@gmail.com> 1761392127 +0530 update by push
23
+ 8d58ec13be39949ecfe7211b42c56acd2a83dc72 e2dc7f666268cf207253a15d55a7fc73093c6d3b cyto <silverstone965@gmail.com> 1761539997 +0530 update by push
24
+ e2dc7f666268cf207253a15d55a7fc73093c6d3b ddd2e5c09eea11798956f2de7df33a9b1eee7e62 cyto <silverstone965@gmail.com> 1761794465 +0530 update by push
@@ -0,0 +1,3 @@
1
+ x��A
2
+ �0E]����t� �x�I2���HEoo�����}^*�:W���
3
+ L�}�1J����@Y,E�����<e�G��)hB�1��iToco
@@ -1 +1 @@
1
- 8d58ec13be39949ecfe7211b42c56acd2a83dc72
1
+ ddd2e5c09eea11798956f2de7df33a9b1eee7e62
@@ -1 +1 @@
1
- 8d58ec13be39949ecfe7211b42c56acd2a83dc72
1
+ ddd2e5c09eea11798956f2de7df33a9b1eee7e62
@@ -53,6 +53,7 @@ class Convertor():
53
53
  myfile.write_bytes(file_bytes)
54
54
 
55
55
  if file_type == 'pdf':
56
+ print("PDF extraction model is: ", model_name)
56
57
  extractor = MarkdownPDFExtractor(str(myfile), output_path=str(output_dir), page_delimiter="-- NEXT PAGE --", model_name=model_name)
57
58
  extractor.extract()
58
59
  with open(output_dir / (myfile.stem + '.md')) as output_file:
pembot/__init__.py CHANGED
@@ -1,6 +1,6 @@
1
1
  """
2
2
  A Python Package to convert PEM blog content to usseful information by leveraging LLMs
3
3
  """
4
- __version__ = '0.1.9'
4
+ __version__ = '0.1.11'
5
5
  from .main import save_to_json_file, make_query
6
6
  __all__ = ["save_to_json_file", "make_query"]
pembot/config/config.yaml CHANGED
@@ -2,4 +2,4 @@ OUTPUT_DIR: /home/cyto/dev/pembotdir
2
2
  PAGE_DELIMITER: ___________________________ NEXT PAGE ___________________________
3
3
  app:
4
4
  name: pembot
5
- version: 0.1.9
5
+ version: 0.1.11
@@ -3,8 +3,7 @@ import pdfplumber
3
3
  import re
4
4
  import yaml
5
5
  import pytesseract
6
- import numpy as np
7
- from typing import Literal, final
6
+ from typing import Literal
8
7
  from PIL import Image
9
8
  import os
10
9
  import logging
@@ -18,7 +17,6 @@ from google import genai
18
17
  from google.genai import types
19
18
  import mimetypes
20
19
  from gradio_client import Client, handle_file
21
- import gradio as gr
22
20
  import tempfile
23
21
 
24
22
 
@@ -153,7 +151,7 @@ class MarkdownPDFExtractor(PDFExtractor):
153
151
  )
154
152
  # print("response :", response)
155
153
  return response.text
156
- elif 'nanonet' in model_name or 'DeepSeek-OCR' in model_name:
154
+ elif 'nanonet' in model_name or 'deepseek' in model_name:
157
155
 
158
156
  result= ""
159
157
  try:
@@ -187,11 +185,11 @@ class MarkdownPDFExtractor(PDFExtractor):
187
185
  prompt_type= 'markdown',
188
186
 
189
187
  # spaces zerogpu
190
- api_name="/predict"
188
+ # api_name="/predict"
191
189
  )
192
190
  print("ocr'd: ", result[:100] + "...")
193
191
  except Exception as e:
194
- print("Error during nanonet inference", e)
192
+ print("Error during HF OCR inference", e)
195
193
  error_message = str(e)
196
194
  if "You have exceeded your Pro GPU quota" in error_message:
197
195
  # print("\n\n\nFALLING BACK TO TESS\n\n\n")
@@ -426,7 +424,7 @@ class MarkdownPDFExtractor(PDFExtractor):
426
424
  except Exception as e:
427
425
  self.logger.error(f"Error performing OCR: {e}")
428
426
  self.logger.exception(traceback.format_exc())
429
- return ""
427
+ raise e
430
428
 
431
429
  def caption_image(self, image, image_bytes):
432
430
  """Generate a caption for the given image."""
File without changes
pembot/requirements.txt CHANGED
@@ -45,7 +45,7 @@ pandas==2.3.0
45
45
  pathlib==1.0.1
46
46
  pdfminer.six==20250506
47
47
  pdfplumber==0.11.7
48
- pembot==0.1.9
48
+ pembot==0.1.11
49
49
  pillow==11.3.0
50
50
  primp==0.15.0
51
51
  pyasn1==0.6.1
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: pembot
3
- Version: 0.1.9
3
+ Version: 0.1.11
4
4
  Summary: A Python Package to convert PEM blog content to usseful information by leveraging LLMs
5
5
  Author-email: cyto <aryan_sidhwani@protonmail.com>
6
6
  License-Expression: MIT
@@ -1,19 +1,20 @@
1
1
  pembot/.gitignore,sha256=yyDEUmeqZekG4AOrU9Zvu2ZQhJvEzEg_lQp2CDfBhXM,92
2
2
  pembot/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
3
- pembot/__init__.py,sha256=smnlaO-5RkabqARB-idge6rJg8yodM3L9mzVPS6qHUs,211
3
+ pembot/__init__.py,sha256=-HYLaaM5nX2ZXnOJqwEGKLyyie_LTNgL_geiqIeP0UI,212
4
4
  pembot/gartner.py,sha256=3ALknQ5mSXIimmwCa3JFDzB_EW2hHEcQO1T2odyBquk,5408
5
5
  pembot/main.py,sha256=lZLIV8XPonvNoY4LVS-5fct1y9URMXWoSGJUKMw3Yg8,9667
6
6
  pembot/output_structure_local.py,sha256=YfpHzfTNeLMSsB_CjAamha9D6Iz7E1IC-tW9xPCMWFc,3000
7
7
  pembot/pem.py,sha256=mv6iGcN1peSY7z2dtCQ_BKj31EFBNfczBhps_d-0XDo,6377
8
8
  pembot/pyrightconfig.json,sha256=j2O2tc8Z-Zu7hEnhN9neoKk6-iLkAlp4qOmAxFyHB7Y,368
9
9
  pembot/query.py,sha256=zgfIJsSMDatFPl0Fw3MhK7fO8uBB0Yj4rxEAExqGyGA,18054
10
- pembot/requirements.txt,sha256=ds-Oa7buELYeuYmmk_m7Ue2AXFfODHkL7oD-U_uiACc,1548
10
+ pembot/requirements.txt,sha256=D_n0NWiwBufGVz9mrDF-WQsQcU4SGbm_rA9LlHgFyRw,1549
11
11
  pembot/search.py,sha256=IW0F8QjE-HSYP47v5P9EqfnzKgFEf5CGxeICtHDDrkE,9137
12
- pembot/.git/COMMIT_EDITMSG,sha256=-sRwEF42WGCK3nwVw43YEXAN7ezI3j0LfpddK1HWff8,51
12
+ pembot/.git/COMMIT_EDITMSG,sha256=UJlFANM0XG3tY_EISjBVlgKuwvEV9TmPcxOpBRcYQ7Y,62
13
13
  pembot/.git/HEAD,sha256=KNJb-Cr0wOK3L1CVmyvrhZ4-YLljCl6MYD2tTdsrboA,21
14
+ pembot/.git/ORIG_HEAD,sha256=T44IhlfPN_kQxI_HGT9K31LM7I400z-O8FjqSLavfWg,41
14
15
  pembot/.git/config,sha256=ZFl9d2GyxirgRXRsv8iULIieKxwGC9P6SAjB_AmTkmQ,271
15
16
  pembot/.git/description,sha256=hatsFj1DoX6pz3eIMIvKFGbxsKjRzJLibpv2PaQGKu4,73
16
- pembot/.git/index,sha256=DVip8TexqW-hFAlcFVfCUupKN3pTLAsb1zJ1tBLUbO4,2054
17
+ pembot/.git/index,sha256=D_ChOY3ZpxYNjWKN60VLfI6lNKlZq8A9xSri259U8pI,2054
17
18
  pembot/.git/packed-refs,sha256=7DECsr7q7vJ6Gw6a2gS3dE4v-YzbxGiWYoSWM43DgsQ,112
18
19
  pembot/.git/hooks/applypatch-msg.sample,sha256=AiNJeguLAzqlijpSG4YphpOGz3qw4vEBlj0yiqYhk_c,478
19
20
  pembot/.git/hooks/commit-msg.sample,sha256=H3TV6SkpebVz69WXQdRsuT_zkazdCD00C5Q3B1PZJDc,896
@@ -30,10 +31,10 @@ pembot/.git/hooks/push-to-checkout.sample,sha256=pT0HQXmLKHxt16-mSu5HPzBeZdP0lGO
30
31
  pembot/.git/hooks/sendemail-validate.sample,sha256=ROv8kj3FRmvACWAvDs8Ge5xlRZq_6IaN3Em3jmztepI,2308
31
32
  pembot/.git/hooks/update.sample,sha256=jV8vqD4QPPCLV-qmdSHfkZT0XL28s32lKtWGCXoU0QY,3650
32
33
  pembot/.git/info/exclude,sha256=ZnH-g7egfIky7okWTR8nk7IxgFjri5jcXAbuClo7DsE,240
33
- pembot/.git/logs/HEAD,sha256=1bmHS5n4N0g5a9FoGTyCcjLjOLjUokarBu41xIuX2VA,5456
34
- pembot/.git/logs/refs/heads/main,sha256=1bmHS5n4N0g5a9FoGTyCcjLjOLjUokarBu41xIuX2VA,5456
34
+ pembot/.git/logs/HEAD,sha256=8waldt7d6LLCOPmV0NNBEqxARigx4oJDq1KHz6g1e44,6174
35
+ pembot/.git/logs/refs/heads/main,sha256=8waldt7d6LLCOPmV0NNBEqxARigx4oJDq1KHz6g1e44,6174
35
36
  pembot/.git/logs/refs/remotes/origin/HEAD,sha256=OrkNquczPPh6fEGtutFKva_-_JhAdwnvXpCCPC4N6jk,194
36
- pembot/.git/logs/refs/remotes/origin/main,sha256=YloiqLDHJGSAiRvtvpfH5YuPME6B2BTuTzqOgG6EKtU,3212
37
+ pembot/.git/logs/refs/remotes/origin/main,sha256=NNaWIMLDJy_40Xe3BnXxFooDnG5QxIPZOuirjuW9Cag,3504
37
38
  pembot/.git/objects/00/3ba85af0ed7b9f6ab099ca298c3d0c18fb002b,sha256=pnk_IbjhUJWavx5BKSlXX8CEvWEMoSm8Dv1tQrUmzn4,169
38
39
  pembot/.git/objects/01/5f71967c525963c827d7fe5415ae2c040c4a64,sha256=-qlT-5utWcwFnO3ADkH2SA2LBsdcph6wE2iePxJxkHs,170
39
40
  pembot/.git/objects/05/5e82e69847a636258cb994bb920c03a93b5ff4,sha256=eNZTNvT7qgsLCfJvRfTETWZIkk_vBEEroLNbPC8RRa4,90
@@ -53,6 +54,7 @@ pembot/.git/objects/0f/ccea3d0db4864a854f8b2c13b9f76b3601d200,sha256=Fq6qF_9lqg1
53
54
  pembot/.git/objects/10/9d1ca0463ea42bbbc435bcb43a90711211cf49,sha256=vR33_Raw-LpnaXGQc1MhSk_ZgEROO2Xa9n97YmA3gtQ,56
54
55
  pembot/.git/objects/10/d1fb81ceede7365dbe132a770a49026e86e9a5,sha256=OhI6pEx_G6KbujS7idkp5MxJd1Aw92Wn3Sl-JBgU2VU,115
55
56
  pembot/.git/objects/14/22c2d0cf79fd928ff7e2d77f96ad5b40cc2a31,sha256=2INSnjkW4KTAcfO2aLYVzjnpT89NXxx8TBJj4iU9e3Y,170
57
+ pembot/.git/objects/15/16e2e3e4eb2a9a5304ed49c8405e19ac6ee3e5,sha256=ZhNTAoIneijLZ3Xjn_mlNpfo64AYQSLl-_AvKlNToVA,55
56
58
  pembot/.git/objects/18/28e18ab80aa64d334b26428708140e280cbc63,sha256=PTF8WLVhzxBDTZhwU_PBHrkQBbijHbKvttSr0XVTOcU,3936
57
59
  pembot/.git/objects/19/f61df7dbd562d04f561288677bbf2f18f5dff7,sha256=zg8IdUSnMYpJ6HsfY2LQbXQTMwlT1IPWRSEiY2uDwyE,392
58
60
  pembot/.git/objects/1f/1fe55f9a705cce752d77718eb870b2c5160138,sha256=YGu15dmNYYWp30eUzWiJh68q_D8lVKEujWHAZ6f2Knw,904
@@ -82,6 +84,7 @@ pembot/.git/objects/42/f03e1b66aa56bbb36a1c3a8dea9e1e727faffa,sha256=n4W2gcagesj
82
84
  pembot/.git/objects/44/86da0f89c566c3bae8abf435d37aeca87f1632,sha256=S2hY860Ep-0c7gQcbgrH6ioG7-Hw9a3BwYHcCkwy1Hg,3884
83
85
  pembot/.git/objects/44/9dea1ca63d6f1e47d119b36576acc94822a37c,sha256=gVL6GHxMRFhlOnyUCO1dSxnsBlMd4Jx90eNZFrv32UQ,6490
84
86
  pembot/.git/objects/48/b71bba3a3f9887828863521c13901eceb54331,sha256=Kx2Tcs17_chpF5rbY3AB34Cj1S3DGnr7Y1tZOTxvrdM,80
87
+ pembot/.git/objects/49/f51d334a46a3ca299c1d63b22af62bd3af5cd0,sha256=8ShNtsbptSHb427IqgFdQkvLIYOYCqN_3o2w1BwJQfI,526
85
88
  pembot/.git/objects/4b/c4370a037feed828cca0915ebb0bb94b24a9d4,sha256=jt9lsSz8c3dw9PyfEEtkReCC_8YLXSKuc6ykSJCKZPM,487
86
89
  pembot/.git/objects/4d/a03134f70896f72053fbdc0cd4f4c76d4ac1d8,sha256=GBhAvxM1omIt-PN6mNXYlIJMN5nx2AUE0ZOf68El5pc,117
87
90
  pembot/.git/objects/50/39b29fda67743a044993436df6a4a1db7b8888,sha256=NYNmYtOq8IMmH32GaQSOBpTRTTm6jEJfY3vytVpzfKM,115
@@ -90,6 +93,7 @@ pembot/.git/objects/55/a26fb846654d84aacea136307a35fb0c46c9c8,sha256=ufE1kt8BOEf
90
93
  pembot/.git/objects/59/69ac8b9d6b44a601385c3ed8c710a69d05216e,sha256=3IOcUn5myiozgeId1iWJZX-r7cS65xXnzQCEjrc-1ZA,168
91
94
  pembot/.git/objects/5b/efa3b2f18d2b5d332c6de503a7054f4af0569f,sha256=g84QcQu-1NZ4-MfLHRosIUOnlK0VItVBqqFW5ffGDNI,882
92
95
  pembot/.git/objects/5c/4f01d3ce9e243bbb8a693f97e5c7d13a857cb7,sha256=BnHoA5JBo5NY2ReemhwmZ-dOdx6CwXWY1TQsc-FSM5o,242
96
+ pembot/.git/objects/5d/2259f832675fd5a5031ee436a1bc8909acd6c9,sha256=lsJmlbNoXeox2YUxNM_zhnEOXjtvNTC7ufydiRaiQ1M,192
93
97
  pembot/.git/objects/5d/d4656bca3d7605598a799d93fcbf23a789d91a,sha256=PTJdqKEqdnlzSoF4rEsu-gWEgfA3tsQJkH_P-01J57g,2850
94
98
  pembot/.git/objects/61/46a371b9c1bd9f51af273f11f986cfd1bedeba,sha256=KZvfnjxuriY54uWZQOM-GLovAvHs1k8_KwhpjNA5lW4,128
95
99
  pembot/.git/objects/63/1700a51c8fa97b543991f5f61bfcd1e7e1327d,sha256=sYkhBkrSPQ8klX2gPrXJUZVt2a0iaF7KC7NFGBuxgeY,4360
@@ -107,6 +111,7 @@ pembot/.git/objects/75/321fbcd2be44a548400fbacbf5bcb71e3810fd,sha256=7AXaYVgItbw
107
111
  pembot/.git/objects/78/4aa28d912b66e07748483efe0326c70d7541a5,sha256=6ut1I6cMnpRs6EK2CZZv50W25yNc0Ha6nC_cj9tSQjI,249
108
112
  pembot/.git/objects/79/4431c1d34c60b4f3fb963823f77f33bd947cc7,sha256=4jqvkfzW3aDywzoNIkWN3zE1rIAceE33trsU9jiF9AM,56
109
113
  pembot/.git/objects/7a/7d28b0313a3d9d509823faaae31949af8610ef,sha256=X59k-p9VNLBpmJlL53qIz8mntLeCSpnjw-rq9u9z_6I,90
114
+ pembot/.git/objects/7c/b239898298ddc45e5b1dfae1ae145b75e627bd,sha256=LdvzG76SpFBaf854usSNcFhZvLfqPjjLT7MKWsOI96A,116
110
115
  pembot/.git/objects/7e/0907822f7d316ebe0be07e1f6918bef412c80b,sha256=lFc55Bu-vEXF8In553gHxlEsB47Vg2qFXHiJqepWEqg,5167
111
116
  pembot/.git/objects/81/d01e1c63d48b096c77aae83471d42272ca9fce,sha256=dPITERwChdrVyBsZnhkOBblW83G0w3Zm7Y6e1CnodtA,216
112
117
  pembot/.git/objects/82/f733fe4edc22fe2f4caa889d2533b24a7bf9df,sha256=1fhgN9PebFoGr-0k49nbV0ztRH5OrSu1K43arcakiI0,3046
@@ -115,18 +120,22 @@ pembot/.git/objects/87/d6df5217a4a374f8c1211a05f9bd657f72c9a7,sha256=OGq5-x1lFa9
115
120
  pembot/.git/objects/88/0c3d45ac59940344dfb6c45005f7e908173138,sha256=7VMQzB6baLdC2Uj5f84w-X6XLM3GinXGBQjewhXupAc,914
116
121
  pembot/.git/objects/89/d2439385c82b98104f27edf39bcf28a631233f,sha256=7jIYfDS2dTNKkTxZKOBmgsSZeoaE6e48JEPzIhI1ySQ,91
117
122
  pembot/.git/objects/8b/5be2af9b16f290549193859c214cd9072212e8,sha256=DhGeGisCdFZ0TcRKp5angRpaseI87TQDt5FtGZInstk,117
123
+ pembot/.git/objects/8c/122efcd19ed7f20b8e7ce8eaecdff8e67ca8fa,sha256=pqfy-pvE55ZbugbU4Z_rcOiX3-gi-ZL2Oq90FYdOWdc,169
118
124
  pembot/.git/objects/8d/58ec13be39949ecfe7211b42c56acd2a83dc72,sha256=sJLULXCzo0CAnARNynNiXwWposMLEdmT2ICZnxRWJZQ,189
119
125
  pembot/.git/objects/8d/adc1d7891c79de24ba2c7c38b4c830bf61870a,sha256=QJaAleJXlBhybaUcSeKB7nC9OJg9gjP_xc071Wyq8BM,115
120
126
  pembot/.git/objects/8f/c00bf69f4ad3e50c13acc4a0988b6c0fe72b5a,sha256=uJVaujaQWN_NwzK9P0SM7cYp3I6GQFXdlYBPrnqVhcg,159
121
127
  pembot/.git/objects/90/f067b86364ab243a7e3bc75f936319ba9eac88,sha256=FLAmmgvYuEAx1-ZBU30rvDzP0ppXWRSVrzPWVnArIb0,203
122
128
  pembot/.git/objects/92/2448ecc557be58195468561e475b904bd1b349,sha256=mT1KGAHx7MalAkkpE7nAu6HlwXIB1Cts3MjZDLItErk,56
129
+ pembot/.git/objects/92/94065a10a11fe0ba233baeb658f605bacd1625,sha256=kgwBuHc_aE2M4qjS9-QDqoNEYFbJ__ujvqw0IfxbY4Y,90
123
130
  pembot/.git/objects/93/652290aac46c69b1b4dd83062b6cfe648dd643,sha256=WPgmr5bXli5s8rNdiUQM4IB4o_xyJe6nuI3TG4e5aYs,487
124
131
  pembot/.git/objects/93/8f29d9b4b1ae86e39dddf9e3d115a82ddfc9b6,sha256=xf8oZ5IBMTxfkH7MFfukV7ZIu0Apd-78eJTdlI7GBv0,90
125
132
  pembot/.git/objects/95/28bbccd167e3f4ad583a1ae9fac98a52620e27,sha256=jwJdRviwjGJIyMpE_BM6mr7B9ofGEsI5ZToJo5nmlao,263
133
+ pembot/.git/objects/95/5e4b9fb51a8891b972a85719a25b521bdaf97e,sha256=8KstJeKUc2xg_KxBSOKsIoue83RQ2_W8tn9aeHZ26TE,527
126
134
  pembot/.git/objects/97/b7aaa5c8b45f5471c9d39893cd4c893da6f444,sha256=PZW83V2jXf8-zDoTJqG1jNsCMURU8NUK8ljBD458MK0,3949
127
135
  pembot/.git/objects/99/89463f57f1f2931e5973bd543c80f18b0204bc,sha256=RoShFyJfmRnXYXP_y2c_e9KE_Otawr_T1mC22BqDNDI,6472
128
136
  pembot/.git/objects/9b/123713e30fc9e225f9ac8ff5b02f8f8cf86456,sha256=xIETiieOoilleucGg7vXOgjZ-v5PI0t34fDJjDD665A,4204
129
137
  pembot/.git/objects/9f/bc171dae3f6b60eaf86ed522b0adf6b123ec85,sha256=fBUMj01e9itIGlHZQcL4W3zTEmE6WgT-THQIKtC4-FA,56
138
+ pembot/.git/objects/a2/8dc2ae0dec8333e8a24d1d195067acf2bc03fc,sha256=4ycZpUoA5PSnw96rQFWQjAl9-h7w1T_QuSVQOQnY_YM,905
130
139
  pembot/.git/objects/a8/98d2c3947d30d8be64bd2bbcef68f956d5456b,sha256=lh2LurucwRdL6WP8ChgmjXrK2lR7HASIXzt4iHFrTf4,178
131
140
  pembot/.git/objects/a9/d5e349fa091647742b09eb3d05bac8f58fe547,sha256=kaU3Z4k6ptIwO8ktcjs2-kshb0bzM4y8Uur-a27_jnk,56
132
141
  pembot/.git/objects/ab/139d2cd4798dd8e2c565b80440b1a44b376126,sha256=v1UO-WINmigZNYD74kyIv310Kq5k4SNL-gQ2DYlw9xk,6258
@@ -141,8 +150,10 @@ pembot/.git/objects/b1/ddf2869bc7d213b35dabd6fa5bfae44cd6b7a7,sha256=zC9EjJo4qRx
141
150
  pembot/.git/objects/b2/4e79ab07fe9e68781961a25ff9f1dbb1546fbb,sha256=zfd9KnP9YtBMwzci1BMWFHAQR4BWJ3XQsyr-rFqdw0Q,135
142
151
  pembot/.git/objects/b8/884c6145221ac66f84bf88919754c2cb05c12d,sha256=6EJskrHAkqVAC5ExxIZDQT_2kZWhfLPPAPbX61tmwgw,170
143
152
  pembot/.git/objects/b8/eea52176ffa4d88c5a9976bee26092421565d3,sha256=xCom1B6wyws8ZNTJoIL4JtVIXNv1yPCwsXfNsVCAGQA,4410
153
+ pembot/.git/objects/b9/633511cf991d84b40c4606b9d124c9beb22df1,sha256=2VFTCjr2bUjPfIFkS53fyi_9aD-wbJsnJAt973shuxk,56
144
154
  pembot/.git/objects/bb/a495d8e72b78fefcc534259b8edae9a3172d15,sha256=Kr92INW6aFVOO0iZm0J2y2Yld9N1Dg-fP6zP1_cqe0g,525
145
155
  pembot/.git/objects/bd/8fd1cb166996e74a8631f3a6f764a53af75297,sha256=JOkICUEv6tdVp7mYDUKtXnsWq3IIZSmm8iUP7OqQwc4,56
156
+ pembot/.git/objects/bd/e1d2d032cd63206ec22230ff3e3ba6dbee804f,sha256=Xx73UiF5eiQYZs68_cbs6zwrPTo4ZJGvtEsG9egBnFo,169
146
157
  pembot/.git/objects/bf/068a0714e2145de83a5c004f4213b091439d0e,sha256=MpiiCqAk6GQ5iGzeThU0rsabrgA5tCAgdIWudAM0IrA,420
147
158
  pembot/.git/objects/bf/32a7e6872e5dc4025ee3df3c921ec7ade0855f,sha256=lwL9ickzIFtMJgNKaPp6nTGDlMhPs6fkZTWevQWK_Lc,56
148
159
  pembot/.git/objects/bf/518686b06069d2a8abd3689908b7e1a6e16b05,sha256=w-HgdJdX2_ZdiIptJv8BcWdeDEyhl42WEk8P72X8YKU,421
@@ -161,12 +172,16 @@ pembot/.git/objects/ce/a4ffc1cf5eab61a2a0abd8f6dc941b580b69fd,sha256=yKUe_ZHD0Uy
161
172
  pembot/.git/objects/d0/937f7d832266337289d5ec09459f931a46fcf7,sha256=_RZ7Z2EZp1OOF_XZhY6e1tzWwhI8Fa5R9aaF_W8APBA,56
162
173
  pembot/.git/objects/d3/508f1537e9bd48bc784da569e14c342bc9c05e,sha256=0VpYRyf_U_go58Y-wncv2bgDw3o9gXBzBBuhft1eBQQ,55
163
174
  pembot/.git/objects/d4/40b20aae1265dabbd3ddaafb24c35e40e3ab3c,sha256=gHVL-l-koZnke8dJEK06U6Vz9HjqoP762qB4QUU9wE0,220
175
+ pembot/.git/objects/d6/3c63232c606d61eaaa7acce7a7a07d134d04da,sha256=PKZzHS3Io6dfNXj-ZnGU5wMG9rb4jZ6ibrmaG9M4wHc,3063
164
176
  pembot/.git/objects/d9/ec420cb55a82e7efbc8564e30ec7f4c0f6021e,sha256=NfSA8eUrylFWTcpPSd2FoA8_TcifJ_pk3jBYmbfkNKQ,90
165
177
  pembot/.git/objects/dd/82bd16a51b9bad8241d9fb46619b1c6755cafe,sha256=36R9xSCSTvnCmK5IhuTacIC8FLQYWkVYh2QwxXJ2e7s,56
178
+ pembot/.git/objects/dd/d2e5c09eea11798956f2de7df33a9b1eee7e62,sha256=TjHYQNshm67MDta-V3vAxqZvoEH8xy3wI0KSDGsqk_g,192
166
179
  pembot/.git/objects/e0/9162dbd64d85bb5ed740aa99faefa73f293d78,sha256=I5fpz3BQ2maFPTSu43T1uvYMuLiep1C3K6CsX8UMNPI,196
167
180
  pembot/.git/objects/e0/da740b542afc451c45b9b4be6c0c7a3c79b06c,sha256=oAb2b2VwhPXykdK_ZV8MEFwfy-ZPd2Nja2gAv20U7hc,115
181
+ pembot/.git/objects/e2/dc7f666268cf207253a15d55a7fc73093c6d3b,sha256=1Bbu_8zk7EMnd2bbE1UMBGVGqMa-aab7XxCfJ89F8XQ,166
168
182
  pembot/.git/objects/e3/c62c141fc65ef2be0095c49b23e06263f0b734,sha256=aasWH_Wns5FItvtPMiBayVAD-4Z6jKHcV8nElgi0olU,164
169
183
  pembot/.git/objects/e3/da98f3722c2d0c937db0872836fc4491e4487a,sha256=DNdNDoMdjDexgwLErwUZDQCpvq4-QkFHtbVRXW_jKTk,168
184
+ pembot/.git/objects/e5/0cd305278d92afa13f3876027fd52639368788,sha256=a7XcDeIDSzawYw4MZnEIOS1BaT9us3ZZRk5RPwIA0D4,116
170
185
  pembot/.git/objects/e5/3070f2b07f45d031444b09b1b38658f3caf29e,sha256=irJ-z8kPZmg85B0f4TQz73yJoCMWMWsIR3Pi5wx1Dlk,4034
171
186
  pembot/.git/objects/e6/adbc3c373070269f97ef82d4f63027d7878f67,sha256=e2NqH8wvYLSYgpHFoGTpurJ4gKU_PHSULZmjJETD3FQ,204
172
187
  pembot/.git/objects/e7/911a702079a6144997ea4e70f59abbe59ec2bc,sha256=r4zY-__F4gSfjE7onRTrcxvv8umXKuPuFzd95AiQ0cs,392
@@ -180,6 +195,7 @@ pembot/.git/objects/ef/141ba9482c729796968be2e562b1488a1e5552,sha256=p6CoPdq20oI
180
195
  pembot/.git/objects/ef/3488a3c636d73d82ad138e70a92453249b7f37,sha256=09VHFwSnSxOExWa3sKBzWAfSMyx5INI9KK2mstW8-xs,203
181
196
  pembot/.git/objects/ef/c899c7f910cfa7a383692eee851cf5af36da8c,sha256=9o2hAtTleVJrHkDxERUrwEaze8hzc-E2n1Jq2t_Oo68,2853
182
197
  pembot/.git/objects/f1/2d2ef8948cbe4b24279bee282f934cf5a1b834,sha256=HvfHm5CnbujMp-uu0aucVzpaWCy2aKBzaXknvlYCnjg,3937
198
+ pembot/.git/objects/f1/2d47700be1ed59a6f0be8d84c3ec9b4404ec00,sha256=NsDaUEqZfqPUpgmPZbcnqoWC4wsoSrnxwT0cyntRmC4,905
183
199
  pembot/.git/objects/f1/3181b12cf4d539e635bf94ad6e950d68cedaf1,sha256=2cORujYAURTvGACujtNJvP1f-s7rt-UkrtPBuKfDR-g,419
184
200
  pembot/.git/objects/f1/655afa1c5636c8d58969e3194bb770aefbc552,sha256=Ugf-wTcOlwZXmxmbnjEc3iOK3dDRntTVONOJsrOjl3E,205
185
201
  pembot/.git/objects/f2/14d4d56726e2928479c5948bd88e038cf70b2e,sha256=e-Ff8_3sWUqd5ciQJLbXohN-E2ShUWKUiYZCHMitMus,290
@@ -198,21 +214,21 @@ pembot/.git/objects/fe/cc5d8154b1e77e4c6beb23ce9cbe8fea55d34d,sha256=0it_Z3Lk5Mj
198
214
  pembot/.git/objects/pack/pack-d5469edc8c36e3bb1de5e0070e4d5b1eae935dd4.idx,sha256=CNzx_lz6v4PulPxRW2t9nz-ifvplpSFPhMA2M9WNUrA,3424
199
215
  pembot/.git/objects/pack/pack-d5469edc8c36e3bb1de5e0070e4d5b1eae935dd4.pack,sha256=dk3Sqrd0L-tNVLRy3uJdTYJNkw8v59mE1hV8zrCFNzc,41355
200
216
  pembot/.git/objects/pack/pack-d5469edc8c36e3bb1de5e0070e4d5b1eae935dd4.rev,sha256=7U3tpTWQ3dn5dwQo_KWMWxF31cKaDnCk2AzTO7Cx4Bg,388
201
- pembot/.git/refs/heads/main,sha256=uEuah700WPimZUV8DPQJkB7P2y-1mRSsAFuF4_YiQKY,41
217
+ pembot/.git/refs/heads/main,sha256=hW4GIGsdOhCHPv73PiP8LreD8UKoda1T6ast3epwAjI,41
202
218
  pembot/.git/refs/remotes/origin/HEAD,sha256=K7aiSqD8bEhBAPXVGim7rYQc0sdV9dk_qiBOXbtOsrQ,30
203
- pembot/.git/refs/remotes/origin/main,sha256=uEuah700WPimZUV8DPQJkB7P2y-1mRSsAFuF4_YiQKY,41
219
+ pembot/.git/refs/remotes/origin/main,sha256=hW4GIGsdOhCHPv73PiP8LreD8UKoda1T6ast3epwAjI,41
204
220
  pembot/AnyToText/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
205
- pembot/AnyToText/convertor.py,sha256=1wMzqcBvt6hgjvvdd2evxpFInOy-bmrr8dkOE-fUC4I,9611
221
+ pembot/AnyToText/convertor.py,sha256=DIwQdzSbi1fQgt2kB1Cv7Xbz1bScB1A1Q_vOVJ1ykmo,9678
206
222
  pembot/TextEmbedder/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
207
223
  pembot/TextEmbedder/gemini_embedder.py,sha256=P679-2mmQESlYKML1vcrwx_-CSgWJgIQk7NL4F7BLQE,677
208
224
  pembot/TextEmbedder/mongodb_embedder.py,sha256=-xIr-zrAGzCmgNeojuX6qYj2t019EVO1I6g-Hwq0FL8,10799
209
225
  pembot/TextEmbedder/mongodb_index_creator.py,sha256=kopqdVYJii_wExVrXGZjMfqWZ2dD42b3PeNWo71weHI,5354
210
226
  pembot/TextEmbedder/vector_query.py,sha256=Kh1uhx9CatB-oQlQtnW-1I2Qz7MGHI20n2h_8peAChM,1986
211
- pembot/config/config.yaml,sha256=5sjUtvZ3xDMa4qRI1hyLKuBVGdyRiufGMLKfht9OGmw,156
227
+ pembot/config/config.yaml,sha256=dBG-ltv7kOM0EmyzqUxlgZapQiGgmVgcCKxcUJlN2Ok,157
212
228
  pembot/pdf2markdown/LICENSE,sha256=1JTJhQjUYDqJzFJhNtitm7mHyE71PRHgetIqRRWg6Pk,1068
213
229
  pembot/pdf2markdown/README.md,sha256=jitM1pwI69oa0N4mXv5-SY1ka9Sz3jsRNCDdpW-50kY,4545
214
230
  pembot/pdf2markdown/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
215
- pembot/pdf2markdown/extract.py,sha256=oomC2qxisdVuYOtYV4fhF92BBjsfixOViWwBv0khjKM,35038
231
+ pembot/pdf2markdown/extract.py,sha256=SiGlSoOpb4NrCMNglfpeUOLRe_R9qtqeGD0Bgl2xuPM,34987
216
232
  pembot/pdf2markdown/pyrightconfig.json,sha256=Vt_k4N2LtZhth0lQOQAOnRKDOQkYYVzmdtb-bP3gu7M,47
217
233
  pembot/pdf2markdown/requirements.txt,sha256=0vZQzkSZKLNVUttd4euoDyYEy0nc2W3CIVxhepHW5Ho,76
218
234
  pembot/pdf2markdown/.git/COMMIT_EDITMSG,sha256=K6REOtE5mjRmxGSeQdpaFAr1luu1BmaZnzXkTjKINzY,55
@@ -261,10 +277,11 @@ pembot/pdf2markdown/.git/refs/heads/main,sha256=II7qd2fp3dz8A72owuHimxMIScJpmznu
261
277
  pembot/pdf2markdown/.git/refs/remotes/myorigin/main,sha256=II7qd2fp3dz8A72owuHimxMIScJpmznueAkXM0sHxJU,41
262
278
  pembot/pdf2markdown/.git/refs/remotes/origin/HEAD,sha256=K7aiSqD8bEhBAPXVGim7rYQc0sdV9dk_qiBOXbtOsrQ,30
263
279
  pembot/pdf2markdown/config/config.yaml,sha256=w75W2Eg4-tu8rRk_23PqxWDh0010kRKLmPrh46f_Njc,66
280
+ pembot/pdf2markdown/logs/extract.log,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
264
281
  pembot/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
265
282
  pembot/utils/inference_client.py,sha256=jeURmY2P5heVlH1dCV0XSgiX3U2qYGEmrnUv0KFpdww,5380
266
283
  pembot/utils/string_tools.py,sha256=gtRa5rBR0Q7GspTu2WtCnvhJQLFjPfWLvhmyiPkyStU,1883
267
- pembot-0.1.9.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
268
- pembot-0.1.9.dist-info/WHEEL,sha256=Dyt6SBfaasWElUrURkknVFAZDHSTwxg3PaTza7RSbkY,100
269
- pembot-0.1.9.dist-info/METADATA,sha256=P4CgwerFdlz7tBVa0Aakloj6F26pkyaTIBsH01ffjak,313
270
- pembot-0.1.9.dist-info/RECORD,,
284
+ pembot-0.1.11.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
285
+ pembot-0.1.11.dist-info/WHEEL,sha256=Dyt6SBfaasWElUrURkknVFAZDHSTwxg3PaTza7RSbkY,100
286
+ pembot-0.1.11.dist-info/METADATA,sha256=P1MqBU2BvnbQ-W1JfaQl0MQSXVOW4PFkJXDf6xNffMc,314
287
+ pembot-0.1.11.dist-info/RECORD,,