pembot 0.0.6__tar.gz → 0.0.7__tar.gz

{pembot-0.0.6 → pembot-0.0.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pembot
-Version: 0.0.6
+Version: 0.0.7
 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-0.0.7/pembot/.git/COMMIT_EDITMSG

@@ -0,0 +1 @@
+added model name to convertor

{pembot-0.0.6 → pembot-0.0.7}/pembot/.git/logs/HEAD

@@ -6,3 +6,5 @@ e91172752e9a421ae463112d2b0506b37498c98d 0c8d9b2690545bf1906b05cd9f18b783b3eb74f
 0c8d9b2690545bf1906b05cd9f18b783b3eb74f1 eb75e1c49f1e5b79dca17ccdbec8067756523238 cyto <silverstone965@gmail.com> 1750856653 +0530	commit: made arrangements for the cases when custom file bytes are to be processed to text output; handled a ollama running / crashing error
 eb75e1c49f1e5b79dca17ccdbec8067756523238 0bdb4169fc0f312b8698f1df17a258fff163aeaa cyto <silverstone965@gmail.com> 1750937276 +0530	commit: fixed the output_dir bug; fixed the excel to json function; ran some tests on convertor; incremented the version on the package; removed dependency on schema / structure, and shifted required fields to a pickle file path in the cli args;
 0bdb4169fc0f312b8698f1df17a258fff163aeaa 9528bbccd167e3f4ad583a1ae9fac98a52620e27 cyto <silverstone965@gmail.com> 1750947488 +0530	commit: handled local llm nonexistent error properly for choice of just passing None as llm_client;
+9528bbccd167e3f4ad583a1ae9fac98a52620e27 ef0503a60244391590b16042019032e91d7cc30d cyto <silverstone965@gmail.com> 1751872559 +0530	commit: added a model_name_parameter to change models quicky
+ef0503a60244391590b16042019032e91d7cc30d af80ddb5890f062e364ea8ade2d602df4e12de8c cyto <silverstone965@gmail.com> 1751896700 +0530	commit: added model name to convertor

{pembot-0.0.6 → pembot-0.0.7}/pembot/.git/logs/refs/heads/main

@@ -6,3 +6,5 @@ e91172752e9a421ae463112d2b0506b37498c98d 0c8d9b2690545bf1906b05cd9f18b783b3eb74f
 0c8d9b2690545bf1906b05cd9f18b783b3eb74f1 eb75e1c49f1e5b79dca17ccdbec8067756523238 cyto <silverstone965@gmail.com> 1750856653 +0530	commit: made arrangements for the cases when custom file bytes are to be processed to text output; handled a ollama running / crashing error
 eb75e1c49f1e5b79dca17ccdbec8067756523238 0bdb4169fc0f312b8698f1df17a258fff163aeaa cyto <silverstone965@gmail.com> 1750937276 +0530	commit: fixed the output_dir bug; fixed the excel to json function; ran some tests on convertor; incremented the version on the package; removed dependency on schema / structure, and shifted required fields to a pickle file path in the cli args;
 0bdb4169fc0f312b8698f1df17a258fff163aeaa 9528bbccd167e3f4ad583a1ae9fac98a52620e27 cyto <silverstone965@gmail.com> 1750947488 +0530	commit: handled local llm nonexistent error properly for choice of just passing None as llm_client;
+9528bbccd167e3f4ad583a1ae9fac98a52620e27 ef0503a60244391590b16042019032e91d7cc30d cyto <silverstone965@gmail.com> 1751872559 +0530	commit: added a model_name_parameter to change models quicky
+ef0503a60244391590b16042019032e91d7cc30d af80ddb5890f062e364ea8ade2d602df4e12de8c cyto <silverstone965@gmail.com> 1751896700 +0530	commit: added model name to convertor

{pembot-0.0.6 → pembot-0.0.7}/pembot/.git/logs/refs/remotes/origin/main

@@ -5,3 +5,5 @@ e91172752e9a421ae463112d2b0506b37498c98d 0c8d9b2690545bf1906b05cd9f18b783b3eb74f
 0c8d9b2690545bf1906b05cd9f18b783b3eb74f1 eb75e1c49f1e5b79dca17ccdbec8067756523238 cyto <silverstone965@gmail.com> 1750856672 +0530	update by push
 eb75e1c49f1e5b79dca17ccdbec8067756523238 0bdb4169fc0f312b8698f1df17a258fff163aeaa cyto <silverstone965@gmail.com> 1750937389 +0530	update by push
 0bdb4169fc0f312b8698f1df17a258fff163aeaa 9528bbccd167e3f4ad583a1ae9fac98a52620e27 cyto <silverstone965@gmail.com> 1750947502 +0530	update by push
+9528bbccd167e3f4ad583a1ae9fac98a52620e27 ef0503a60244391590b16042019032e91d7cc30d cyto <silverstone965@gmail.com> 1751872581 +0530	update by push
+ef0503a60244391590b16042019032e91d7cc30d af80ddb5890f062e364ea8ade2d602df4e12de8c cyto <silverstone965@gmail.com> 1751896713 +0530	update by push

pembot-0.0.7/pembot/.git/objects/ef/0503a60244391590b16042019032e91d7cc30d

@@ -0,0 +1,3 @@
+x
��Kj1D��)z� ��ĴZ-{�h���
�>2�AVU��Qom��9��j�5�d��,��#��tQF&T�J|��ۀ�t̙�(�T��E�
+9U��i�%� �>�}z�Dz��~��q����pYߩ�OP���s	ޤ3R�v
+�*�.��z���a��Ԟ�t��¯����B���k�U�

pembot-0.0.7/pembot/.git/refs/heads/main

@@ -0,0 +1 @@
+af80ddb5890f062e364ea8ade2d602df4e12de8c

pembot-0.0.7/pembot/.git/refs/remotes/origin/main

@@ -0,0 +1 @@
+af80ddb5890f062e364ea8ade2d602df4e12de8c

{pembot-0.0.6 → pembot-0.0.7}/pembot/AnyToText/convertor.py

@@ -31,12 +31,14 @@ EXCEL_FILE_TYPES= [
 class Convertor():
 
 
-    def __init__(self, myfile: Path | None= None, output_dir: Path | None= None, file_bytes: bytes | None= None, suffix: str | None= None, file_type: str | None= None):
+    def __init__(self, myfile: Path | None= None, output_dir: Path | None= None, file_bytes: bytes | None= None, suffix: str | None= None, file_type: str | None= None, model_name: str | None = None):
 
         self.output= ""
 
-        # model_name=  "gemini-2.5-flash"
-        model_name= None
+        if model_name is None:
+            # model_name=  "gemini-2.5-flash"
+            model_name=  "Nanonets-OCR-s"
+
         # file_type can be pdf, excel, etc.
         if output_dir is None and myfile is None and file_bytes is not None and suffix is not None:
             with tempfile.TemporaryDirectory() as dp:

{pembot-0.0.6 → pembot-0.0.7}/pembot/__init__.py

@@ -1,6 +1,6 @@
 """
 A Python Package to convert PEM blog content to usseful information by leveraging LLMs
 """
-__version__ = '0.0.6'
+__version__ = '0.0.7'
 from .main import save_to_json_file, make_query
 __all__ = ["save_to_json_file", "make_query"]

{pembot-0.0.6 → pembot-0.0.7}/pembot/config/config.yaml

@@ -2,4 +2,4 @@ OUTPUT_DIR: /home/cyto/dev/pembotdir
 PAGE_DELIMITER: ___________________________ NEXT PAGE ___________________________
 app:
   name: pembot
-  version: 0.0.6
+  version: 0.0.7

pembot-0.0.7/pembot/pdf2markdown/.git/COMMIT_EDITMSG

@@ -0,0 +1 @@
+handled the gpu errors non-gracefully so that it stops

{pembot-0.0.6 → pembot-0.0.7}/pembot/pdf2markdown/.git/logs/HEAD

@@ -2,3 +2,4 @@
 ffb759ee4605b232366a9ee58134532913c3f9e0 b8702320e56074e9680181d8b7897d6a0a552e2d cyto <silverstone965@gmail.com> 1750947962 +0530	commit: handled config loading errors gracefully; added gemini support, as an option; added huggingface nanonets transformers support (as an option); redesigned the extract markdown for captioning and image ocr (block image and full-page image);
 b8702320e56074e9680181d8b7897d6a0a552e2d 14251b198e0bac39a3dc3b42f9e57b20c01465fb cyto <silverstone965@gmail.com> 1751604763 +0530	commit: removed deps on torch and transformers; used gradio client for ocr through public spaces;
 14251b198e0bac39a3dc3b42f9e57b20c01465fb b48d697aa9fd97151eb2a84a1af5d408b7630232 cyto <silverstone965@gmail.com> 1751871887 +0530	commit: cyto/argument-list-bug-fix;authentication-used-in-gradio-client
+b48d697aa9fd97151eb2a84a1af5d408b7630232 f3b2d76c75bbd50e04fc4c2ad17fc94ca6daed32 cyto <silverstone965@gmail.com> 1751896628 +0530	commit: handled the gpu errors non-gracefully so that it stops

{pembot-0.0.6 → pembot-0.0.7}/pembot/pdf2markdown/.git/logs/refs/heads/main

@@ -2,3 +2,4 @@
 ffb759ee4605b232366a9ee58134532913c3f9e0 b8702320e56074e9680181d8b7897d6a0a552e2d cyto <silverstone965@gmail.com> 1750947962 +0530	commit: handled config loading errors gracefully; added gemini support, as an option; added huggingface nanonets transformers support (as an option); redesigned the extract markdown for captioning and image ocr (block image and full-page image);
 b8702320e56074e9680181d8b7897d6a0a552e2d 14251b198e0bac39a3dc3b42f9e57b20c01465fb cyto <silverstone965@gmail.com> 1751604763 +0530	commit: removed deps on torch and transformers; used gradio client for ocr through public spaces;
 14251b198e0bac39a3dc3b42f9e57b20c01465fb b48d697aa9fd97151eb2a84a1af5d408b7630232 cyto <silverstone965@gmail.com> 1751871887 +0530	commit: cyto/argument-list-bug-fix;authentication-used-in-gradio-client
+b48d697aa9fd97151eb2a84a1af5d408b7630232 f3b2d76c75bbd50e04fc4c2ad17fc94ca6daed32 cyto <silverstone965@gmail.com> 1751896628 +0530	commit: handled the gpu errors non-gracefully so that it stops

{pembot-0.0.6 → pembot-0.0.7}/pembot/pdf2markdown/.git/logs/refs/remotes/myorigin/main

@@ -1,3 +1,4 @@
 0000000000000000000000000000000000000000 b8702320e56074e9680181d8b7897d6a0a552e2d cyto <silverstone965@gmail.com> 1750948073 +0530	update by push
 b8702320e56074e9680181d8b7897d6a0a552e2d 14251b198e0bac39a3dc3b42f9e57b20c01465fb cyto <silverstone965@gmail.com> 1751604904 +0530	update by push
 14251b198e0bac39a3dc3b42f9e57b20c01465fb b48d697aa9fd97151eb2a84a1af5d408b7630232 cyto <silverstone965@gmail.com> 1751872077 +0530	update by push
+b48d697aa9fd97151eb2a84a1af5d408b7630232 f3b2d76c75bbd50e04fc4c2ad17fc94ca6daed32 cyto <silverstone965@gmail.com> 1751896663 +0530	update by push

pembot-0.0.7/pembot/pdf2markdown/.git/objects/f3/b2d76c75bbd50e04fc4c2ad17fc94ca6daed32

@@ -0,0 +1 @@
+x
��Kj!3vw� �l媷?`k�v��>�!�C'��:'Hk�f't:�lȺ�6g�u2j�߈G�TV��ةN��gb�rp���F��ɚ���RI��<Z���

pembot-0.0.7/pembot/pdf2markdown/.git/refs/heads/main

@@ -0,0 +1 @@
+f3b2d76c75bbd50e04fc4c2ad17fc94ca6daed32

pembot-0.0.7/pembot/pdf2markdown/.git/refs/remotes/myorigin/main

@@ -0,0 +1 @@
+f3b2d76c75bbd50e04fc4c2ad17fc94ca6daed32

{pembot-0.0.6 → pembot-0.0.7}/pembot/pdf2markdown/extract.py

@@ -115,6 +115,10 @@ class MarkdownPDFExtractor(PDFExtractor):
         except Exception as e:
             self.logger.error(f"Error processing PDF: {e}")
             self.logger.exception(traceback.format_exc())
+
+            error_message= str(e).lower()
+            if "GPU" in error_message and "quota" in error_message:
+                return "GPU quota error", []
             return "", []
 
 
@@ -176,6 +180,12 @@ class MarkdownPDFExtractor(PDFExtractor):
                     print("ocr'd: ", result[:100] + "...")
             except Exception as e:
                 print("Error during nanonet inference", e)
+                error_message = str(e)
+                if "You have exceeded your Pro GPU quota" in error_message:
+                    # print("\n\n\nFALLING BACK TO TESS\n\n\n")
+                    # return pytesseract.image_to_string(pil_image)
+                    raise e
+
             
             return result
         else:
@@ -262,6 +272,9 @@ class MarkdownPDFExtractor(PDFExtractor):
                             except Exception as e:
                                 self.logger.error(f"    Error processing embedded image block for OCR: {e}")
                                 current_page_markdown_blocks.append("\n\n![Image Processing Error](error_on_page_{page_num+1}_block_{block_num+1}.png)\n\n")
+                                error_message= str(e).lower()
+                                if "GPU" in error_message and "quota" in error_message:
+                                    raise e
 
 
                     # Insert tables at their approximate positions (after blocks are processed for the page)
@@ -306,6 +319,9 @@ class MarkdownPDFExtractor(PDFExtractor):
                                 self.logger.info(f"  Full-page OCR yielded no text for page {page_num+1}.")
                         except Exception as e:
                             self.logger.error(f"  Error during full-page OCR on page {page_num+1}: {e}")
+                            error_message= str(e).lower()
+                            if "GPU" in error_message and "quota" in error_message:
+                                raise e
                     else:
                         self.logger.info(f"  Page {page_num + 1} has sufficient searchable text or embedded image OCR; skipping full-page OCR.")
 
@@ -329,7 +345,12 @@ class MarkdownPDFExtractor(PDFExtractor):
             except Exception as e:
                 self.logger.critical(f"An unexpected error occurred during markdown extraction: {e}")
                 self.logger.exception(traceback.format_exc())
-                return "", []
+
+                error_message= str(e).lower()
+                if "GPU" in error_message and "quota" in error_message:
+                    return "GPU quota error", []
+                else:
+                    return "", []
 
     def extract_tables(self):
         """Extract tables from PDF using pdfplumber."""
@@ -412,6 +433,9 @@ class MarkdownPDFExtractor(PDFExtractor):
         except Exception as e:
             self.logger.error(f"Error captioning image: {e}")
             self.logger.exception(traceback.format_exc())
+            error_message= str(e)
+            if "GPU" in error_message and "quota" in error_message:
+                raise e
             return ""
 
     def clean_text(self, text):
@@ -726,6 +750,7 @@ class MarkdownPDFExtractor(PDFExtractor):
             self.logger.exception(traceback.format_exc())
             return ""
 
+
     def get_header_level(self, font_size):
         """Determine header level based on font size."""
         if font_size > 24:

pembot-0.0.6/pembot/.git/COMMIT_EDITMSG

@@ -1 +0,0 @@
-handled config loading errors gracefully; added gemini support, as an option; added huggingface nanonets transformers support (as an option); redesigned the extract markdown for captioning and image ocr (block image and full-page image);

pembot-0.0.6/pembot/.git/refs/heads/main

@@ -1 +0,0 @@
-9528bbccd167e3f4ad583a1ae9fac98a52620e27

pembot-0.0.6/pembot/.git/refs/remotes/origin/main

@@ -1 +0,0 @@
-9528bbccd167e3f4ad583a1ae9fac98a52620e27

pembot-0.0.6/pembot/pdf2markdown/.git/COMMIT_EDITMSG

@@ -1 +0,0 @@
-cyto/argument-list-bug-fix;authentication-used-in-gradio-client

pembot-0.0.6/pembot/pdf2markdown/.git/refs/heads/main

@@ -1 +0,0 @@
-b48d697aa9fd97151eb2a84a1af5d408b7630232

pembot-0.0.6/pembot/pdf2markdown/.git/refs/remotes/myorigin/main

@@ -1 +0,0 @@
-b48d697aa9fd97151eb2a84a1af5d408b7630232