pembot 0.1.9__tar.gz → 0.1.10__tar.gz

{pembot-0.1.9 → pembot-0.1.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pembot
-Version: 0.1.9
+Version: 0.1.10
 Summary: A Python Package to convert PEM blog content to usseful information by leveraging LLMs
 Author-email: cyto <aryan_sidhwani@protonmail.com>
 License-Expression: MIT

pembot-0.1.10/pembot/.git/COMMIT_EDITMSG

@@ -0,0 +1 @@
+added logs; fixed typo

{pembot-0.1.9 → pembot-0.1.10}/pembot/.git/logs/HEAD

@@ -21,3 +21,4 @@ e6adbc3c373070269f97ef82d4f63027d7878f67 81d01e1c63d48b096c77aae83471d42272ca9fc
 e89cb4f5af158d26dcff5eed03dba6671a818739 e3c62c141fc65ef2be0095c49b23e06263f0b734 cyto <silverstone965@gmail.com> 1758892053 +0530	commit: silly willy mistake
 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
 d440b20aae1265dabbd3ddaafb24c35e40e3ab3c 8d58ec13be39949ecfe7211b42c56acd2a83dc72 cyto <silverstone965@gmail.com> 1761392079 +0530	commit: added DeepSeek-OCR as a model option to use spaces
+8d58ec13be39949ecfe7211b42c56acd2a83dc72 e2dc7f666268cf207253a15d55a7fc73093c6d3b cyto <silverstone965@gmail.com> 1761539934 +0530	commit: added logs; fixed typo

{pembot-0.1.9 → pembot-0.1.10}/pembot/.git/logs/refs/heads/main

@@ -21,3 +21,4 @@ e6adbc3c373070269f97ef82d4f63027d7878f67 81d01e1c63d48b096c77aae83471d42272ca9fc
 e89cb4f5af158d26dcff5eed03dba6671a818739 e3c62c141fc65ef2be0095c49b23e06263f0b734 cyto <silverstone965@gmail.com> 1758892053 +0530	commit: silly willy mistake
 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
 d440b20aae1265dabbd3ddaafb24c35e40e3ab3c 8d58ec13be39949ecfe7211b42c56acd2a83dc72 cyto <silverstone965@gmail.com> 1761392079 +0530	commit: added DeepSeek-OCR as a model option to use spaces
+8d58ec13be39949ecfe7211b42c56acd2a83dc72 e2dc7f666268cf207253a15d55a7fc73093c6d3b cyto <silverstone965@gmail.com> 1761539934 +0530	commit: added logs; fixed typo

{pembot-0.1.9 → pembot-0.1.10}/pembot/.git/logs/refs/remotes/origin/main

@@ -20,3 +20,4 @@ e6adbc3c373070269f97ef82d4f63027d7878f67 81d01e1c63d48b096c77aae83471d42272ca9fc
 e89cb4f5af158d26dcff5eed03dba6671a818739 e3c62c141fc65ef2be0095c49b23e06263f0b734 cyto <silverstone965@gmail.com> 1758892065 +0530	update by push
 e3c62c141fc65ef2be0095c49b23e06263f0b734 d440b20aae1265dabbd3ddaafb24c35e40e3ab3c cyto <silverstone965@gmail.com> 1759127680 +0530	update by push
 d440b20aae1265dabbd3ddaafb24c35e40e3ab3c 8d58ec13be39949ecfe7211b42c56acd2a83dc72 cyto <silverstone965@gmail.com> 1761392127 +0530	update by push
+8d58ec13be39949ecfe7211b42c56acd2a83dc72 e2dc7f666268cf207253a15d55a7fc73093c6d3b cyto <silverstone965@gmail.com> 1761539997 +0530	update by push

pembot-0.1.10/pembot/.git/objects/e2/dc7f666268cf207253a15d55a7fc73093c6d3b

@@ -0,0 +1,3 @@
+x
��A
+�0E]����t��x�I2���HEoo�����}^*�:W���
+L�}�1J����@Y,E�����<e�G��)hB�1��iToco

pembot-0.1.10/pembot/.git/refs/heads/main

@@ -0,0 +1 @@
+e2dc7f666268cf207253a15d55a7fc73093c6d3b

pembot-0.1.10/pembot/.git/refs/remotes/origin/main

@@ -0,0 +1 @@
+e2dc7f666268cf207253a15d55a7fc73093c6d3b

{pembot-0.1.9 → pembot-0.1.10}/pembot/AnyToText/convertor.py

@@ -53,6 +53,7 @@ class Convertor():
                 myfile.write_bytes(file_bytes)
 
                 if file_type == 'pdf':
+                    print("PDF extraction model is: ", model_name)
                     extractor = MarkdownPDFExtractor(str(myfile), output_path=str(output_dir), page_delimiter="-- NEXT PAGE --", model_name=model_name)
                     extractor.extract()
                     with open(output_dir / (myfile.stem + '.md')) as output_file:

{pembot-0.1.9 → pembot-0.1.10}/pembot/__init__.py

@@ -1,6 +1,6 @@
 """
 A Python Package to convert PEM blog content to usseful information by leveraging LLMs
 """
-__version__ = '0.1.9'
+__version__ = '0.1.10'
 from .main import save_to_json_file, make_query
 __all__ = ["save_to_json_file", "make_query"]

{pembot-0.1.9 → pembot-0.1.10}/pembot/config/config.yaml

@@ -2,4 +2,4 @@ OUTPUT_DIR: /home/cyto/dev/pembotdir
 PAGE_DELIMITER: ___________________________ NEXT PAGE ___________________________
 app:
   name: pembot
-  version: 0.1.9
+  version: 0.1.10

{pembot-0.1.9 → pembot-0.1.10}/pembot/pdf2markdown/extract.py

@@ -153,7 +153,7 @@ class MarkdownPDFExtractor(PDFExtractor):
             )
             # print("response :", response)
             return response.text
-        elif 'nanonet' in model_name or 'DeepSeek-OCR' in model_name:
+        elif 'nanonet' in model_name or 'deepseek' in model_name:
 
             result= ""
             try:

{pembot-0.1.9 → pembot-0.1.10}/pembot/requirements.txt

@@ -45,7 +45,7 @@ pandas==2.3.0
 pathlib==1.0.1
 pdfminer.six==20250506
 pdfplumber==0.11.7
-pembot==0.1.9
+pembot==0.1.10
 pillow==11.3.0
 primp==0.15.0
 pyasn1==0.6.1

pembot-0.1.9/pembot/.git/COMMIT_EDITMSG

@@ -1 +0,0 @@
-added DeepSeek-OCR as a model option to use spaces

pembot-0.1.9/pembot/.git/refs/heads/main

@@ -1 +0,0 @@
-8d58ec13be39949ecfe7211b42c56acd2a83dc72

pembot-0.1.9/pembot/.git/refs/remotes/origin/main

@@ -1 +0,0 @@
-8d58ec13be39949ecfe7211b42c56acd2a83dc72