pembot 0.1.2__py2.py3-none-any.whl → 0.1.3__py2.py3-none-any.whl

pembot/.git/COMMIT_EDITMSG

@@ -1 +1 @@
-minor oopsie
+cyto/fixed the excel to markdown conversion

pembot/.git/logs/HEAD

@@ -13,3 +13,5 @@ af80ddb5890f062e364ea8ade2d602df4e12de8c 0d28f73897db0c9a9351ee9e64d2a0fe27db270
 a898d2c3947d30d8be64bd2bbcef68f956d5456b 784aa28d912b66e07748483efe0326c70d7541a5 cyto <silverstone965@gmail.com> 1752236415 +0530	commit: added prompt prefixing option to prime the llm with some more data; added the option for no-filter global search in a collection in search_within_document(s)
 784aa28d912b66e07748483efe0326c70d7541a5 f214d4d56726e2928479c5948bd88e038cf70b2e cyto <silverstone965@gmail.com> 1752858244 +0530	commit: added smolagent functionality with tool extension capability to query.py and added a caveat in search_within_documents by which you can just return no context if you set limit= 0, effectively doing a Non-contextual prompt
 f214d4d56726e2928479c5948bd88e038cf70b2e 8fc00bf69f4ad3e50c13acc4a0988b6c0fe72b5a cyto <silverstone965@gmail.com> 1752859643 +0530	commit: minor oopsie
+8fc00bf69f4ad3e50c13acc4a0988b6c0fe72b5a 203b390ad0aeb3bc5a8540840b004e6a42e5ce7a cyto <silverstone965@gmail.com> 1752865439 +0530	commit: added requirements
+203b390ad0aeb3bc5a8540840b004e6a42e5ce7a c3cc0da3d955ecec0f865c46c030a0c073697495 cyto <silverstone965@gmail.com> 1758877816 +0530	commit: cyto/fixed the excel to markdown conversion

pembot/.git/logs/refs/heads/main

@@ -13,3 +13,5 @@ af80ddb5890f062e364ea8ade2d602df4e12de8c 0d28f73897db0c9a9351ee9e64d2a0fe27db270
 a898d2c3947d30d8be64bd2bbcef68f956d5456b 784aa28d912b66e07748483efe0326c70d7541a5 cyto <silverstone965@gmail.com> 1752236415 +0530	commit: added prompt prefixing option to prime the llm with some more data; added the option for no-filter global search in a collection in search_within_document(s)
 784aa28d912b66e07748483efe0326c70d7541a5 f214d4d56726e2928479c5948bd88e038cf70b2e cyto <silverstone965@gmail.com> 1752858244 +0530	commit: added smolagent functionality with tool extension capability to query.py and added a caveat in search_within_documents by which you can just return no context if you set limit= 0, effectively doing a Non-contextual prompt
 f214d4d56726e2928479c5948bd88e038cf70b2e 8fc00bf69f4ad3e50c13acc4a0988b6c0fe72b5a cyto <silverstone965@gmail.com> 1752859643 +0530	commit: minor oopsie
+8fc00bf69f4ad3e50c13acc4a0988b6c0fe72b5a 203b390ad0aeb3bc5a8540840b004e6a42e5ce7a cyto <silverstone965@gmail.com> 1752865439 +0530	commit: added requirements
+203b390ad0aeb3bc5a8540840b004e6a42e5ce7a c3cc0da3d955ecec0f865c46c030a0c073697495 cyto <silverstone965@gmail.com> 1758877816 +0530	commit: cyto/fixed the excel to markdown conversion

pembot/.git/logs/refs/remotes/origin/main

@@ -12,3 +12,5 @@ af80ddb5890f062e364ea8ade2d602df4e12de8c 0d28f73897db0c9a9351ee9e64d2a0fe27db270
 a898d2c3947d30d8be64bd2bbcef68f956d5456b 784aa28d912b66e07748483efe0326c70d7541a5 cyto <silverstone965@gmail.com> 1752236436 +0530	update by push
 784aa28d912b66e07748483efe0326c70d7541a5 f214d4d56726e2928479c5948bd88e038cf70b2e cyto <silverstone965@gmail.com> 1752858280 +0530	update by push
 f214d4d56726e2928479c5948bd88e038cf70b2e 8fc00bf69f4ad3e50c13acc4a0988b6c0fe72b5a cyto <silverstone965@gmail.com> 1752859659 +0530	update by push
+8fc00bf69f4ad3e50c13acc4a0988b6c0fe72b5a 203b390ad0aeb3bc5a8540840b004e6a42e5ce7a cyto <silverstone965@gmail.com> 1752865472 +0530	update by push
+203b390ad0aeb3bc5a8540840b004e6a42e5ce7a c3cc0da3d955ecec0f865c46c030a0c073697495 cyto <silverstone965@gmail.com> 1758877832 +0530	update by push

pembot/.git/refs/heads/main

@@ -1 +1 @@
-8fc00bf69f4ad3e50c13acc4a0988b6c0fe72b5a
+c3cc0da3d955ecec0f865c46c030a0c073697495

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

@@ -1 +1 @@
-8fc00bf69f4ad3e50c13acc4a0988b6c0fe72b5a
+c3cc0da3d955ecec0f865c46c030a0c073697495

pembot/.gitignore

@@ -1,4 +1,3 @@
-*.txt
 TextEmbedder/__pycache__/
 pdf2markdown/
 __pycache__/

pembot/AnyToText/convertor.py

@@ -3,11 +3,11 @@ import mimetypes
 from pathlib import Path
 from pembot.pdf2markdown.extract import MarkdownPDFExtractor
 import os
-import json
 import pandas as pd
-from typing import Literal, Union, Dict, Any, List
+from typing import Literal, Union
 import tempfile
 from datetime import datetime, date
+from tabulate import tabulate
 
 
 PandasReadEngineType = Literal['xlrd', 'openpyxl', 'odf', 'pyxlsb', 'calamine', None]
@@ -53,10 +53,7 @@ class Convertor():
                             self.output= output_file.read()
                     elif file_type == 'excel':
                         self.input_filepath= myfile
-                        self.json_filepath = output_dir / (myfile.stem + ".json")
-                        self.convert_file_to_json()
-                        with open(output_dir / (myfile.stem + '.json')) as output_file:
-                            self.output= output_file.read()
+                        self.output= self.convert_excel_to_markdown()
 
         elif output_dir is not None and myfile is not None:
             print("got output path for conversion: ", output_dir)
@@ -64,8 +61,6 @@ class Convertor():
 
             self.output_dir= output_dir
             self.input_filepath= myfile
-            base_name, _ = os.path.splitext(myfile.name)
-            self.json_filepath = output_dir / 'json' / (base_name + ".json")
 
             if mt == 'application/json':
                 print("the file was json")
@@ -73,242 +68,80 @@ class Convertor():
                 print("the file was pdf, outputting in: ", output_dir)
                 extractor= MarkdownPDFExtractor(str(myfile), output_path= str(self.output_dir), page_delimiter= "-- NEXT PAGE --", model_name= model_name)
                 extractor.extract()
+                with open(self.output_dir / (myfile.stem + '.md')) as output_file:
+                    self.output= output_file.read()
 
             elif mt in EXCEL_FILE_TYPES:
-                self.convert_file_to_json()
+                self.output = self.convert_excel_to_markdown()
 
             else:
                 print(mt)
 
-    def convert_file_to_json(
-        self,
-        sheet_to_convert: Union[str, int, None] = None,  # Relevant for Excel/ODS
-        orient: Literal['dict', 'list', 'series', 'split', 'records', 'index'] = 'records', # Corrected type hint
-        date_format: Union[str, None] = 'iso',  # 'iso', 'epoch', or None
-        csv_encoding: str = 'utf-8', # For reading CSV files
-        excel_ods_engine: PandasReadEngineType = None # For Excel/ODS, e.g., 'openpyxl', 'xlrd', 'odf'
-        ) -> bool:
+    def convert_excel_to_markdown(self, excel_ods_engine: PandasReadEngineType = None) -> str:
         """
-        Converts an Excel, ODS, or CSV file (or a specific Excel/ODS sheet)
-        into an equivalent JSON format.
+        Converts all sheets from an Excel or ODS file into a single Markdown string.
+        Each sheet is converted to a Markdown table, prefixed with the sheet's name.
 
         Args:
-            sheet_to_convert (str | int | None, optional):
-                - For Excel/ODS:
-                    - If None (default): Converts all sheets. The JSON output will be a
-                      dictionary where keys are sheet names and values are the JSON
-                      representation of each sheet.
-                    - If str: Name of the specific sheet to convert.
-                    - If int: Index of the specific sheet to convert (0-based).
-                    If a specific sheet is requested, the JSON output will directly be
-                    the representation of that sheet.
-                - For CSV: This parameter is ignored. The entire CSV is processed.
-            orient (str, optional): Pandas DataFrame.to_dict() orientation for each sheet/CSV.
-                Default: 'records'. See pandas.DataFrame.to_dict() documentation.
-            date_format (str | None, optional): Format for datetime objects.
-                - 'iso' (default): ISO8601 format (e.g., '2023-10-27T10:30:00').
-                - 'epoch': Milliseconds since epoch.
-                - None: Pandas default (often Timestamps). 'iso' is generally safer for JSON.
-            csv_encoding (str, optional): Encoding for reading CSV files. Default is 'utf-8'.
             excel_ods_engine (str | None, optional): Pandas engine for reading Excel or ODS files.
                 - For Excel: 'openpyxl' (for .xlsx), 'xlrd' (for .xls).
                 - For ODS: 'odf' (requires 'odfpy' library).
                 If None, pandas auto-detects based on file extension and installed libraries.
 
         Returns:
-            bool: True if conversion was successful, False otherwise.
+            str: A string containing the Markdown tables for all sheets, or an error message.
         """
-
         input_filepath = self.input_filepath
-        json_filepath = self.json_filepath
+        markdown_output = []
 
+        file_suffix= ''
         try:
-
             if not input_filepath.exists():
-                print(f"Error: Input file not found at {input_filepath}")
-                return False
-
-            # Ensure output directory exists
-            json_filepath.parent.mkdir(parents=True, exist_ok=True)
+                return f"Error: Input file not found at {input_filepath}"
 
             file_suffix = input_filepath.suffix.lower()
-            output_data_final: Union[Dict[str, Any], List[Dict[str, Any]]] = {}
-
-            dataframes_to_process: list[tuple[pd.DataFrame, str | None]] = []
-
             current_engine: PandasReadEngineType = excel_ods_engine
 
-            if file_suffix == '.csv':
-                if sheet_to_convert is not None:
-                    print(f"Info: 'sheet_to_convert' parameter ('{sheet_to_convert}') is ignored for CSV file '{input_filepath.name}'. Processing entire CSV.")
-                try:
-                    df = pd.read_csv(input_filepath, encoding=csv_encoding)
-                    dataframes_to_process.append((df, None))
-                except Exception as e:
-                    print(f"Error reading CSV file '{input_filepath.name}': {e}")
-                    return False
-
-            elif file_suffix in ['.xls', '.xlsx', '.ods']:
-                try:
-                    if file_suffix == '.ods':
-                        if current_engine is None:
-                            current_engine = 'odf'
-                        elif current_engine != 'odf':
-                            print(f"Warning: Specified engine '{current_engine}' may not be optimal for ODS. Forcing 'odf'.")
-                            current_engine = 'odf'
-
-                    if sheet_to_convert is not None:
-                        df = pd.read_excel(input_filepath, sheet_name=sheet_to_convert, engine=current_engine)
-                        dataframes_to_process.append((df, None))
-
-                    else:
-                        excel_file = pd.ExcelFile(input_filepath, engine=current_engine)
-                        if not excel_file.sheet_names:
-                            print(f"Warning: File '{input_filepath.name}' contains no sheets.")
-                        for sheet_name in excel_file.sheet_names:
-                            df = excel_file.parse(sheet_name) # engine is inherited
-                            dataframes_to_process.append((df, sheet_name))
-                except ImportError as ie:
-                    if 'odfpy' in str(ie).lower() and file_suffix == '.ods':
-                        print(f"Error reading ODS file '{input_filepath.name}': The 'odfpy' library is required. Please install it using 'pip install odfpy'.")
-                    elif 'xlrd' in str(ie).lower() and file_suffix == '.xls':
-                        print(f"Error reading .xls file '{input_filepath.name}': The 'xlrd' library might be required. Please install it using 'pip install xlrd'.")
-                    elif 'openpyxl' in str(ie).lower() and file_suffix == '.xlsx':
-                        print(f"Error reading .xlsx file '{input_filepath.name}': The 'openpyxl' library might be required. Please install it using 'pip install openpyxl'.")
-                    else:
-                        print(f"ImportError reading file '{input_filepath.name}': {ie}")
-                    return False
-                except Exception as e:
-                    print(f"Error reading Excel/ODS file '{input_filepath.name}': {e}")
-                    return False
-            else:
-                print(f"Error: Unsupported file type: '{file_suffix}'. Please provide a CSV, XLS, XLSX, or ODS file.")
-                return False
-
-            if not dataframes_to_process and file_suffix in ['.xls', '.xlsx', '.ods'] and sheet_to_convert is None:
-                 print(f"Info: No dataframes were loaded from '{input_filepath.name}'. Output JSON will be empty if processing all sheets from an empty file.")
-            elif not dataframes_to_process and not (file_suffix in ['.xls', '.xlsx', '.ods'] and sheet_to_convert is None):
-                 pass
-
-            is_direct_output = len(dataframes_to_process) == 1 and dataframes_to_process[0][1] is None
-            temp_processed_data: Dict[str, Any] = {}
-
-            for df_original, name_key in dataframes_to_process:
-                df = df_original.copy()
-
-                # Handle datetime columns with improved detection and conversion
-                if date_format:
-                    # Check for datetime columns using multiple approaches
-                    datetime_columns = []
-
-                    # Method 1: Use pandas dtype detection
-                    datetime_columns.extend(df.select_dtypes(include=['datetime64[ns]', 'datetime', 'datetimetz']).columns.tolist())
-
-                    # Method 2: Check for datetime objects in each column
-                    for col in df.columns:
-                        if col not in datetime_columns:
-                            # Sample a few non-null values to check type
-                            sample_values = df[col].dropna().head(10)
-                            if len(sample_values) > 0:
-                                for val in sample_values:
-                                    if isinstance(val, (datetime, date, pd.Timestamp)):
-                                        datetime_columns.append(col)
-                                        break
-
-                    # Convert datetime columns
-                    for col_name in datetime_columns:
-                        try:
-                            if date_format == 'iso':
-                                df[col_name] = df[col_name].apply(lambda x: self._convert_to_iso(x))
-                            elif date_format == 'epoch':
-                                df[col_name] = df[col_name].apply(lambda x: self._convert_to_epoch(x))
-                        except Exception as e_date:
-                            print(f"Warning: Could not fully convert date column '{col_name}' in '{name_key or input_filepath.name}' using format '{date_format}'. Error: {e_date}")
-
-                # Replace NaN values with None for JSON compatibility
-                df = df.astype(object).where(pd.notnull(df), None)
-
-                # Final safety check: convert any remaining datetime objects
-                for col in df.columns:
-                    df[col] = df[col].apply(lambda x: self._safe_datetime_convert(x, date_format))
-
-                current_json_segment = df.to_dict(orient=orient)
-
-                if is_direct_output:
-                    output_data_final = current_json_segment
-                    break
-                else:
-                    if name_key is not None:
-                        temp_processed_data[name_key] = current_json_segment
-
-            if not is_direct_output:
-                output_data_final = temp_processed_data
-
-            with open(json_filepath, 'w', encoding='utf-8') as f:
-                json.dump(output_data_final, f, indent=4, ensure_ascii=False)
-
-            print(f"Successfully converted '{input_filepath.name}' to '{json_filepath.name}'")
-            return True
-
-        except FileNotFoundError:
-            print(f"Error: Input file not found at {input_filepath.name}")
-            return False
-        except ValueError as ve:
-            print(f"ValueError during conversion of '{input_filepath.name}': {ve}")
-            return False
-        except Exception as e:
-            print(f"An unexpected error occurred during conversion of '{input_filepath.name}': {e}")
-            return False
+            if file_suffix in ['.xls', '.xlsx', '.ods']:
+                if file_suffix == '.ods':
+                    if current_engine is None:
+                        current_engine = 'odf'
+                    elif current_engine != 'odf':
+                        print(f"Warning: Specified engine '{current_engine}' may not be optimal for ODS. Forcing 'odf'.")
+                        current_engine = 'odf'
 
-    def _convert_to_iso(self, value):
-        """Convert datetime-like objects to ISO format string."""
-        if pd.isnull(value) or value is None:
-            return None
+                excel_file = pd.ExcelFile(input_filepath, engine=current_engine)
+                if not excel_file.sheet_names:
+                    return f"Warning: File '{input_filepath.name}' contains no sheets."
 
-        try:
-            if isinstance(value, str):
-                return value  # Already a string
-            elif hasattr(value, 'isoformat'):
-                return value.isoformat()
-            elif isinstance(value, pd.Timestamp):
-                return value.isoformat()
-            else:
-                return str(value)
-        except:
-            return str(value) if value is not None else None
+                for sheet_name in excel_file.sheet_names:
+                    df = excel_file.parse(sheet_name)
+                    markdown_output.append(f"## {sheet_name}\n")
+                    markdown_table = tabulate(df, headers='keys', tablefmt='pipe')
+                    markdown_output.append(markdown_table)
+                    markdown_output.append("\n")
 
-    def _convert_to_epoch(self, value):
-        """Convert datetime-like objects to epoch milliseconds."""
-        if pd.isnull(value) or value is None:
-            return None
+                return "\n".join(markdown_output)
+
+            elif file_suffix == '.csv':
+                df = pd.read_csv(input_filepath)
+                markdown_table = tabulate(df, headers='keys', tablefmt='pipe')
+                return markdown_table
 
-        try:
-            if isinstance(value, (int, float)):
-                return int(value)  # Assume already epoch
-            elif hasattr(value, 'timestamp'):
-                return int(value.timestamp() * 1000)
-            elif isinstance(value, pd.Timestamp):
-                return int(value.timestamp() * 1000)
             else:
-                return str(value)
-        except:
-            return str(value) if value is not None else None
-
-    def _safe_datetime_convert(self, value, date_format):
-        """Final safety conversion for any remaining datetime objects."""
-        if pd.isnull(value) or value is None:
-            return None
-
-        # If it's a datetime-like object, convert it
-        if isinstance(value, (datetime, date, pd.Timestamp)):
-            if date_format == 'iso':
-                return self._convert_to_iso(value)
-            elif date_format == 'epoch':
-                return self._convert_to_epoch(value)
+                return f"Error: Unsupported file type: '{file_suffix}'. Please provide a CSV, XLS, XLSX, or ODS file."
+
+        except ImportError as ie:
+            if 'odfpy' in str(ie).lower() and file_suffix == '.ods':
+                return f"Error reading ODS file '{input_filepath.name}': The 'odfpy' library is required. Please install it using 'pip install odfpy'."
+            elif 'xlrd' in str(ie).lower() and file_suffix == '.xls':
+                return f"Error reading .xls file '{input_filepath.name}': The 'xlrd' library might be required. Please install it using 'pip install xlrd'."
+            elif 'openpyxl' in str(ie).lower() and file_suffix == '.xlsx':
+                return f"Error reading .xlsx file '{input_filepath.name}': The 'openpyxl' library might be required. Please install it using 'pip install openpyxl'."
             else:
-                return str(value)
-
-        return value
+                return f"ImportError reading file '{input_filepath.name}': {ie}"
+        except Exception as e:
+            return f"An unexpected error occurred during conversion of '{input_filepath.name}': {e}"
 
 
 def chunk_text(text, chunk_size=500, overlap_size=50):
@@ -337,29 +170,29 @@ def chunk_text(text, chunk_size=500, overlap_size=50):
 if __name__ == '__main__':
     print("Test Run Start:")
     try:
-        print("Test 1: scaned pdf page, bytes")
-        with open("/home/cyto/Documents/scanned.pdf", "rb") as imgpdf:
-            conv= Convertor(file_bytes= imgpdf.read(), suffix= ".pdf", file_type= "pdf")
-            print(conv.output)
+        # print("Test 1: scaned pdf page, bytes")
+        # with open("/home/cyto/Documents/scanned.pdf", "rb") as imgpdf:
+        #     conv= Convertor(file_bytes= imgpdf.read(), suffix= ".pdf", file_type= "pdf")
+        #     print(conv.output)
 
         # print("Test 2: JD pdf, bytes")
         # with open("/home/cyto/dev/pembotdir/jds/PM Trainee.pdf", "rb") as imgpdf:
         #     conv= Convertor(file_bytes= imgpdf.read(), suffix= ".pdf", file_type= "pdf")
         #     print(conv.output)
 
-        # print("Test 3: excel schedule, bytes")
-        # with open("/home/cyto/Downloads/Assignment schedule.xlsx", "rb") as imgpdf:
-        #     conv= Convertor(file_bytes= imgpdf.read(), suffix= ".xlsx", file_type= "excel")
-        #     print(conv.output)
+        print("Test 3: excel schedule, bytes")
+        with open("/home/cyto/Downloads/Assignment schedule.xlsx", "rb") as imgpdf:
+            conv= Convertor(file_bytes= imgpdf.read(), suffix= ".xlsx", file_type= "excel")
+            print(conv.output)
 
         # without bytes example:
         print("Test 4: scanned pdf, path")
         conv= Convertor(myfile= Path('/home/cyto/Documents/scanned.pdf'), output_dir= Path('/home/cyto/Documents'))
         print(conv.output)
 
-        # print("Test 5: schedule excel, path")
-        # conv= Convertor(myfile= Path('/home/cyto/Downloads/Assignment schedule.xlsx'), output_dir= Path('/home/cyto/Downloads'))
-        # print(conv.output)
+        print("Test 5: schedule excel, path")
+        conv= Convertor(myfile= Path('/home/cyto/Downloads/Assignment schedule.xlsx'), output_dir= Path('/home/cyto/Downloads'))
+        print(conv.output)
     except FileNotFoundError as fe:
         print("file not found, modify the driver code to get sample files to test:\n\n", fe)
     except Exception as e:

pembot/__init__.py

@@ -1,6 +1,6 @@
 """
 A Python Package to convert PEM blog content to usseful information by leveraging LLMs
 """
-__version__ = '0.1.2'
+__version__ = '0.1.3'
 from .main import save_to_json_file, make_query
 __all__ = ["save_to_json_file", "make_query"]

pembot/config/config.yaml

@@ -2,4 +2,4 @@ OUTPUT_DIR: /home/cyto/dev/pembotdir
 PAGE_DELIMITER: ___________________________ NEXT PAGE ___________________________
 app:
   name: pembot
-  version: 0.1.2
+  version: 0.1.3

pembot/requirements.txt

@@ -9,6 +9,7 @@ cffi==1.17.1
 charset-normalizer==3.4.2
 click==8.2.1
 cryptography==45.0.5
+defusedxml==0.7.1
 dnspython==2.7.0
 duckduckgo_search==8.1.1
 et_xmlfile==2.0.0
@@ -36,6 +37,7 @@ MarkupSafe==3.0.2
 mdurl==0.1.2
 msgpack==1.1.1
 numpy==2.3.1
+odfpy==1.4.1
 ollama==0.5.1
 openpyxl==3.1.5
 orjson==3.10.18
@@ -44,7 +46,7 @@ pandas==2.3.0
 pathlib==1.0.1
 pdfminer.six==20250506
 pdfplumber==0.11.7
-pembot==0.1.2
+pembot==0.1.3
 pillow==11.3.0
 primp==0.15.0
 pyasn1==0.6.1
@@ -76,6 +78,7 @@ smolagents==1.20.0
 sniffio==1.3.1
 soupsieve==2.7
 starlette==0.46.2
+tabulate==0.9.0
 tenacity==8.5.0
 tomlkit==0.13.3
 tqdm==4.67.1
@@ -86,3 +89,4 @@ tzdata==2025.2
 urllib3==2.5.0
 uvicorn==0.35.0
 websockets==15.0.1
+xlrd==2.0.2

{pembot-0.1.2.dist-info → pembot-0.1.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pembot
-Version: 0.1.2
+Version: 0.1.3
 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-0.1.2.dist-info → pembot-0.1.3.dist-info}/RECORD

@@ -1,19 +1,19 @@
-pembot/.gitignore,sha256=_7FTsZokJ_pzEyyPjOsGw5x5Xx3gUBFaafs7UlPsv9E,98
+pembot/.gitignore,sha256=yyDEUmeqZekG4AOrU9Zvu2ZQhJvEzEg_lQp2CDfBhXM,92
 pembot/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-pembot/__init__.py,sha256=JS8ONln7V9MIxi_JrRdEW9Kc9ygOmpCCRKEYC9TnTjA,211
+pembot/__init__.py,sha256=BSH5pBwk4cE-px43hTajMIU1KPohYzz7NSoELkXBd7s,211
 pembot/gartner.py,sha256=3ALknQ5mSXIimmwCa3JFDzB_EW2hHEcQO1T2odyBquk,5408
 pembot/main.py,sha256=lZLIV8XPonvNoY4LVS-5fct1y9URMXWoSGJUKMw3Yg8,9667
 pembot/output_structure_local.py,sha256=YfpHzfTNeLMSsB_CjAamha9D6Iz7E1IC-tW9xPCMWFc,3000
 pembot/pem.py,sha256=mv6iGcN1peSY7z2dtCQ_BKj31EFBNfczBhps_d-0XDo,6377
 pembot/pyrightconfig.json,sha256=j2O2tc8Z-Zu7hEnhN9neoKk6-iLkAlp4qOmAxFyHB7Y,368
 pembot/query.py,sha256=zgfIJsSMDatFPl0Fw3MhK7fO8uBB0Yj4rxEAExqGyGA,18054
-pembot/requirements.txt,sha256=BGGuhM9oXJGN6oueIu3AYmBMUXeo-BoEQFJHHyO1BCc,1508
+pembot/requirements.txt,sha256=bSXSM-tdrwGooRpz9e1VE3Yt9hXwz3inSq2PYpPw3hU,1567
 pembot/search.py,sha256=IW0F8QjE-HSYP47v5P9EqfnzKgFEf5CGxeICtHDDrkE,9137
-pembot/.git/COMMIT_EDITMSG,sha256=pTsMiZ9dt9Of1JgR5858BXwxO8jn7P0MpLw0pJE7dqc,13
+pembot/.git/COMMIT_EDITMSG,sha256=PRRNgCxdUYryr-DaiG3MSBswsgdYtfleiBnQX_2R64U,44
 pembot/.git/HEAD,sha256=KNJb-Cr0wOK3L1CVmyvrhZ4-YLljCl6MYD2tTdsrboA,21
 pembot/.git/config,sha256=ZFl9d2GyxirgRXRsv8iULIieKxwGC9P6SAjB_AmTkmQ,271
 pembot/.git/description,sha256=hatsFj1DoX6pz3eIMIvKFGbxsKjRzJLibpv2PaQGKu4,73
-pembot/.git/index,sha256=70Iy37BW4GBRzaodLY4qm1hjjcBml0r1cdcFyNX_G_I,1974
+pembot/.git/index,sha256=5oJw9H2tF6dW5jUIaChBVJVZAfTwLdB-F-cyM_oLdx0,2054
 pembot/.git/packed-refs,sha256=7DECsr7q7vJ6Gw6a2gS3dE4v-YzbxGiWYoSWM43DgsQ,112
 pembot/.git/hooks/applypatch-msg.sample,sha256=AiNJeguLAzqlijpSG4YphpOGz3qw4vEBlj0yiqYhk_c,478
 pembot/.git/hooks/commit-msg.sample,sha256=H3TV6SkpebVz69WXQdRsuT_zkazdCD00C5Q3B1PZJDc,896
@@ -30,10 +30,10 @@ pembot/.git/hooks/push-to-checkout.sample,sha256=pT0HQXmLKHxt16-mSu5HPzBeZdP0lGO
 pembot/.git/hooks/sendemail-validate.sample,sha256=ROv8kj3FRmvACWAvDs8Ge5xlRZq_6IaN3Em3jmztepI,2308
 pembot/.git/hooks/update.sample,sha256=jV8vqD4QPPCLV-qmdSHfkZT0XL28s32lKtWGCXoU0QY,3650
 pembot/.git/info/exclude,sha256=ZnH-g7egfIky7okWTR8nk7IxgFjri5jcXAbuClo7DsE,240
-pembot/.git/logs/HEAD,sha256=OrEUcE6427s9cKnTnrPMYZLrJcs4v-PSww3Zq_Tc060,3790
-pembot/.git/logs/refs/heads/main,sha256=OrEUcE6427s9cKnTnrPMYZLrJcs4v-PSww3Zq_Tc060,3790
+pembot/.git/logs/HEAD,sha256=yPZc9m6stXELdpuwEBMSjn0rVegOtxHb8YcCsBL0USA,4131
+pembot/.git/logs/refs/heads/main,sha256=yPZc9m6stXELdpuwEBMSjn0rVegOtxHb8YcCsBL0USA,4131
 pembot/.git/logs/refs/remotes/origin/HEAD,sha256=OrkNquczPPh6fEGtutFKva_-_JhAdwnvXpCCPC4N6jk,194
-pembot/.git/logs/refs/remotes/origin/main,sha256=iJ6dB86rQ2-iqzRSdgRdjkze4t1IGz0MTxou3cwLYE4,2044
+pembot/.git/logs/refs/remotes/origin/main,sha256=i4leZYJW4JljsOW0xXKwBmnDOlygP8qJN378MfpDauM,2336
 pembot/.git/objects/01/5f71967c525963c827d7fe5415ae2c040c4a64,sha256=-qlT-5utWcwFnO3ADkH2SA2LBsdcph6wE2iePxJxkHs,170
 pembot/.git/objects/09/ee34d94dffd4c286df1d6d528b2e98e2a6cce2,sha256=FSXPGn6UBhR7s1Ug-afzCYLfGy8dE3Umn8dBKaahkDM,203
 pembot/.git/objects/0a/fb3a98cdc55b1434b44534ec2bf22c56cfa26c,sha256=Xxw20vI57zuhERWopDAZpQw6rAOhFtUr05lzpGyCTTE,120
@@ -44,10 +44,14 @@ pembot/.git/objects/0d/28f73897db0c9a9351ee9e64d2a0fe27db2705,sha256=hqMFSXWo_05
 pembot/.git/objects/0e/120123bfadfd594220963f3bbca54056bab6ee,sha256=fj4c6vIKYMYSj5DEdXd6fcYGcanqaPGRD_9haJy35ns,56
 pembot/.git/objects/0f/ccea3d0db4864a854f8b2c13b9f76b3601d200,sha256=Fq6qF_9lqg1bYsF2tWArhzkldnfgLFELLK2CH_2XNcU,203
 pembot/.git/objects/10/9d1ca0463ea42bbbc435bcb43a90711211cf49,sha256=vR33_Raw-LpnaXGQc1MhSk_ZgEROO2Xa9n97YmA3gtQ,56
+pembot/.git/objects/10/d1fb81ceede7365dbe132a770a49026e86e9a5,sha256=OhI6pEx_G6KbujS7idkp5MxJd1Aw92Wn3Sl-JBgU2VU,115
 pembot/.git/objects/14/22c2d0cf79fd928ff7e2d77f96ad5b40cc2a31,sha256=2INSnjkW4KTAcfO2aLYVzjnpT89NXxx8TBJj4iU9e3Y,170
 pembot/.git/objects/18/28e18ab80aa64d334b26428708140e280cbc63,sha256=PTF8WLVhzxBDTZhwU_PBHrkQBbijHbKvttSr0XVTOcU,3936
 pembot/.git/objects/19/f61df7dbd562d04f561288677bbf2f18f5dff7,sha256=zg8IdUSnMYpJ6HsfY2LQbXQTMwlT1IPWRSEiY2uDwyE,392
+pembot/.git/objects/1f/791d08c432b4244a670517c87ada2181159101,sha256=Zpth_iVM6H5W4u5jLVEKdRz0i3ydBLm5XJql4ieuj8U,169
 pembot/.git/objects/1f/83a471c8119f7794d98c049170a5d7d07a4b71,sha256=XnMaYQUA8iT1fiOIvlBav331Ry7pNBOBqI3wB3Y1VM0,90
+pembot/.git/objects/20/3b390ad0aeb3bc5a8540840b004e6a42e5ce7a,sha256=tNzFPYJ0Y6YpaNw4w2hRH_0iTa5fNlC2nzARkKFbIec,162
+pembot/.git/objects/27/02d55c4513a6d23e577aa2f104982c8b9436b2,sha256=SQ84I7DnyPaaxoWCBoh20Iw1VZm8wgSaPaL5uDR-R8I,90
 pembot/.git/objects/28/db0ab48059acccd7d257aa02e52e9b6b83a4a5,sha256=S6PrWSQlkifYxKIgFdU0PZD0uLebS6uAP2LAUwp5yOI,91
 pembot/.git/objects/35/97e518a8658280be9f377f78edf1dfa1f23814,sha256=gfc5bFLVZpwNQb1Ox2VosDYAjw0Lc5ZLjmvNA8gWcmg,2546
 pembot/.git/objects/37/175696b3ca7a5d17379f03fb61a1023d50aeba,sha256=XaF3EsJ1wSIWtgBtgKsZkwiMK0NM8acFy9nnqE9_d0s,3085
@@ -62,11 +66,13 @@ pembot/.git/objects/41/cbeb6bcb4c6fa9ef9be571082d95ecb4ea0ee3,sha256=waMrzjG_o5D
 pembot/.git/objects/42/f03e1b66aa56bbb36a1c3a8dea9e1e727faffa,sha256=n4W2gcagesjI1rStKNxQ98q5UOHlfwFJGUADFeYldoE,418
 pembot/.git/objects/44/86da0f89c566c3bae8abf435d37aeca87f1632,sha256=S2hY860Ep-0c7gQcbgrH6ioG7-Hw9a3BwYHcCkwy1Hg,3884
 pembot/.git/objects/44/9dea1ca63d6f1e47d119b36576acc94822a37c,sha256=gVL6GHxMRFhlOnyUCO1dSxnsBlMd4Jx90eNZFrv32UQ,6490
+pembot/.git/objects/48/b71bba3a3f9887828863521c13901eceb54331,sha256=Kx2Tcs17_chpF5rbY3AB34Cj1S3DGnr7Y1tZOTxvrdM,80
 pembot/.git/objects/4b/c4370a037feed828cca0915ebb0bb94b24a9d4,sha256=jt9lsSz8c3dw9PyfEEtkReCC_8YLXSKuc6ykSJCKZPM,487
 pembot/.git/objects/4d/a03134f70896f72053fbdc0cd4f4c76d4ac1d8,sha256=GBhAvxM1omIt-PN6mNXYlIJMN5nx2AUE0ZOf68El5pc,117
 pembot/.git/objects/50/39b29fda67743a044993436df6a4a1db7b8888,sha256=NYNmYtOq8IMmH32GaQSOBpTRTTm6jEJfY3vytVpzfKM,115
 pembot/.git/objects/51/9e780574933d7627a083222bd10dd74f430904,sha256=3e3Iu2-waVySghbLYXmwhDPpfhV4PF82suvjcYkSVog,3604
 pembot/.git/objects/59/69ac8b9d6b44a601385c3ed8c710a69d05216e,sha256=3IOcUn5myiozgeId1iWJZX-r7cS65xXnzQCEjrc-1ZA,168
+pembot/.git/objects/5b/efa3b2f18d2b5d332c6de503a7054f4af0569f,sha256=g84QcQu-1NZ4-MfLHRosIUOnlK0VItVBqqFW5ffGDNI,882
 pembot/.git/objects/5c/4f01d3ce9e243bbb8a693f97e5c7d13a857cb7,sha256=BnHoA5JBo5NY2ReemhwmZ-dOdx6CwXWY1TQsc-FSM5o,242
 pembot/.git/objects/61/46a371b9c1bd9f51af273f11f986cfd1bedeba,sha256=KZvfnjxuriY54uWZQOM-GLovAvHs1k8_KwhpjNA5lW4,128
 pembot/.git/objects/63/1700a51c8fa97b543991f5f61bfcd1e7e1327d,sha256=sYkhBkrSPQ8klX2gPrXJUZVt2a0iaF7KC7NFGBuxgeY,4360
@@ -75,12 +81,14 @@ pembot/.git/objects/6d/7a865a23b1cb4182f67907820104ced48b11c9,sha256=dJRTCmT9rLy
 pembot/.git/objects/71/014c7a6c8c98449a26ef966485a6cf30a1974d,sha256=ZamWua6G5BGjBYZYeG8dN3nHhwz_kqFfoYyO2wtuRV0,417
 pembot/.git/objects/72/f047cda92abcd1ddc857f6461de605f8668331,sha256=PFb9LUDMnUCnuJcXUa5W1ea__fdP17kNyWrnqvnOpjs,240
 pembot/.git/objects/73/2e98f08bc806c331b06847fc8c743f545499e5,sha256=kbKUb6fwwhRO73B4EZmol55JBvckqE3GNZ9PqHRB2ag,3995
+pembot/.git/objects/73/5b5f6d515f0816599343f1ae7ccffc1d5a487e,sha256=0aByFDI4DyyfA-TKCFoUXbQAvNabJIV7CXHSIDna5bo,2833
 pembot/.git/objects/75/321fbcd2be44a548400fbacbf5bcb71e3810fd,sha256=7AXaYVgItbw3xQiEqeRyO5qdIedIxDoI9hTDn8CBRxM,56
 pembot/.git/objects/78/4aa28d912b66e07748483efe0326c70d7541a5,sha256=6ut1I6cMnpRs6EK2CZZv50W25yNc0Ha6nC_cj9tSQjI,249
 pembot/.git/objects/7a/7d28b0313a3d9d509823faaae31949af8610ef,sha256=X59k-p9VNLBpmJlL53qIz8mntLeCSpnjw-rq9u9z_6I,90
 pembot/.git/objects/7e/0907822f7d316ebe0be07e1f6918bef412c80b,sha256=lFc55Bu-vEXF8In553gHxlEsB47Vg2qFXHiJqepWEqg,5167
 pembot/.git/objects/86/cdaec229f1fbebf43042266b03878944669f25,sha256=eTvQhUeYXP8E181oTOcBydcgmImr62IizaH_Jbcbg8g,4077
 pembot/.git/objects/87/d6df5217a4a374f8c1211a05f9bd657f72c9a7,sha256=OGq5-x1lFa94vTX7WYO6o4TGvCZwAvZ6LXm6N3dpiKM,3881
+pembot/.git/objects/88/0c3d45ac59940344dfb6c45005f7e908173138,sha256=7VMQzB6baLdC2Uj5f84w-X6XLM3GinXGBQjewhXupAc,914
 pembot/.git/objects/8b/5be2af9b16f290549193859c214cd9072212e8,sha256=DhGeGisCdFZ0TcRKp5angRpaseI87TQDt5FtGZInstk,117
 pembot/.git/objects/8d/adc1d7891c79de24ba2c7c38b4c830bf61870a,sha256=QJaAleJXlBhybaUcSeKB7nC9OJg9gjP_xc071Wyq8BM,115
 pembot/.git/objects/8f/c00bf69f4ad3e50c13acc4a0988b6c0fe72b5a,sha256=uJVaujaQWN_NwzK9P0SM7cYp3I6GQFXdlYBPrnqVhcg,159
@@ -102,13 +110,17 @@ pembot/.git/objects/b1/1173d9b68db117437ccb9551461152e1e8a77d,sha256=6cl8NMNQ9b5
 pembot/.git/objects/b2/4e79ab07fe9e68781961a25ff9f1dbb1546fbb,sha256=zfd9KnP9YtBMwzci1BMWFHAQR4BWJ3XQsyr-rFqdw0Q,135
 pembot/.git/objects/b8/884c6145221ac66f84bf88919754c2cb05c12d,sha256=6EJskrHAkqVAC5ExxIZDQT_2kZWhfLPPAPbX61tmwgw,170
 pembot/.git/objects/b8/eea52176ffa4d88c5a9976bee26092421565d3,sha256=xCom1B6wyws8ZNTJoIL4JtVIXNv1yPCwsXfNsVCAGQA,4410
+pembot/.git/objects/bb/a495d8e72b78fefcc534259b8edae9a3172d15,sha256=Kr92INW6aFVOO0iZm0J2y2Yld9N1Dg-fP6zP1_cqe0g,525
 pembot/.git/objects/bd/8fd1cb166996e74a8631f3a6f764a53af75297,sha256=JOkICUEv6tdVp7mYDUKtXnsWq3IIZSmm8iUP7OqQwc4,56
 pembot/.git/objects/bf/068a0714e2145de83a5c004f4213b091439d0e,sha256=MpiiCqAk6GQ5iGzeThU0rsabrgA5tCAgdIWudAM0IrA,420
 pembot/.git/objects/bf/32a7e6872e5dc4025ee3df3c921ec7ade0855f,sha256=lwL9ickzIFtMJgNKaPp6nTGDlMhPs6fkZTWevQWK_Lc,56
 pembot/.git/objects/bf/518686b06069d2a8abd3689908b7e1a6e16b05,sha256=w-HgdJdX2_ZdiIptJv8BcWdeDEyhl42WEk8P72X8YKU,421
 pembot/.git/objects/c0/793458db6e1bee7f79f1a504fb8ff4963f8ed3,sha256=b8lo_OrMeGgirc9yY_OFjv5xVpG6FBpZnBf7jbtlmyw,421
+pembot/.git/objects/c0/f948ab4636a125bc202368e6c9cbe80d76169a,sha256=GPQso_R_RWWLx_pF3g58MiM4HyeSnpXTeLeKDfhkyPc,526
 pembot/.git/objects/c2/443060c07101948487cfa93cc39e082e9e0f5f,sha256=d9rjB8sgBOUQ-HQ8yu5I-c5Dqr_q2z0OOCXSufjDAak,3998
+pembot/.git/objects/c2/926f040b089a52edfb8351480f63619ab7e0ab,sha256=HAXSsWokz2tuk9Y952ogIEzSBlbUC4lZ1CjvWBc22Cg,56
 pembot/.git/objects/c2/ce19d575a8cccf6886862c4fa6afefba142511,sha256=kxbbFUJ1TpEVIrqgiLzepP5Z1k_kF3FjCHvJ04yCBvs,3370
+pembot/.git/objects/c3/cc0da3d955ecec0f865c46c030a0c073697495,sha256=7ZXWsXqapYhbZZJwaaeAwqGcgX8JwoS5DazqOGaRHeQ,179
 pembot/.git/objects/ce/a4ffc1cf5eab61a2a0abd8f6dc941b580b69fd,sha256=yKUe_ZHD0UynTIrDRhuVqjDjKYDfZkWplqXjeSOD_bk,3894
 pembot/.git/objects/d0/937f7d832266337289d5ec09459f931a46fcf7,sha256=_RZ7Z2EZp1OOF_XZhY6e1tzWwhI8Fa5R9aaF_W8APBA,56
 pembot/.git/objects/e0/9162dbd64d85bb5ed740aa99faefa73f293d78,sha256=I5fpz3BQ2maFPTSu43T1uvYMuLiep1C3K6CsX8UMNPI,196
@@ -140,17 +152,17 @@ pembot/.git/objects/fe/cc5d8154b1e77e4c6beb23ce9cbe8fea55d34d,sha256=0it_Z3Lk5Mj
 pembot/.git/objects/pack/pack-d5469edc8c36e3bb1de5e0070e4d5b1eae935dd4.idx,sha256=CNzx_lz6v4PulPxRW2t9nz-ifvplpSFPhMA2M9WNUrA,3424
 pembot/.git/objects/pack/pack-d5469edc8c36e3bb1de5e0070e4d5b1eae935dd4.pack,sha256=dk3Sqrd0L-tNVLRy3uJdTYJNkw8v59mE1hV8zrCFNzc,41355
 pembot/.git/objects/pack/pack-d5469edc8c36e3bb1de5e0070e4d5b1eae935dd4.rev,sha256=7U3tpTWQ3dn5dwQo_KWMWxF31cKaDnCk2AzTO7Cx4Bg,388
-pembot/.git/refs/heads/main,sha256=XQJQDbhwKcxH2eABZeHWgpv9Yedy7ytKBo0tRWo03ZM,41
+pembot/.git/refs/heads/main,sha256=a4NhMFSYteuWFt7KclttMW9wgrlLiv3bnLAY88lZVCU,41
 pembot/.git/refs/remotes/origin/HEAD,sha256=K7aiSqD8bEhBAPXVGim7rYQc0sdV9dk_qiBOXbtOsrQ,30
-pembot/.git/refs/remotes/origin/main,sha256=XQJQDbhwKcxH2eABZeHWgpv9Yedy7ytKBo0tRWo03ZM,41
+pembot/.git/refs/remotes/origin/main,sha256=a4NhMFSYteuWFt7KclttMW9wgrlLiv3bnLAY88lZVCU,41
 pembot/AnyToText/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-pembot/AnyToText/convertor.py,sha256=gqvhwFssUsAeirfO4n0Ztwga1hn8zHbdG96sMTjYrpE,17188
+pembot/AnyToText/convertor.py,sha256=L0d6AevJBtyC-5pP-vJGHR_Uaumf0iWPNYLmwGaiUHI,8772
 pembot/TextEmbedder/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pembot/TextEmbedder/gemini_embedder.py,sha256=P679-2mmQESlYKML1vcrwx_-CSgWJgIQk7NL4F7BLQE,677
 pembot/TextEmbedder/mongodb_embedder.py,sha256=-xIr-zrAGzCmgNeojuX6qYj2t019EVO1I6g-Hwq0FL8,10799
 pembot/TextEmbedder/mongodb_index_creator.py,sha256=kopqdVYJii_wExVrXGZjMfqWZ2dD42b3PeNWo71weHI,5354
 pembot/TextEmbedder/vector_query.py,sha256=Kh1uhx9CatB-oQlQtnW-1I2Qz7MGHI20n2h_8peAChM,1986
-pembot/config/config.yaml,sha256=uLE_cngQbhDN3pwqRaZC60yhXP5dSFUYIWQKZ0qkhFM,156
+pembot/config/config.yaml,sha256=DMNFp9EdsN22ZGe8Tp4DRCn-wAWSinhN5oI1muXE-_Y,156
 pembot/pdf2markdown/LICENSE,sha256=1JTJhQjUYDqJzFJhNtitm7mHyE71PRHgetIqRRWg6Pk,1068
 pembot/pdf2markdown/README.md,sha256=jitM1pwI69oa0N4mXv5-SY1ka9Sz3jsRNCDdpW-50kY,4545
 pembot/pdf2markdown/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -206,7 +218,7 @@ pembot/pdf2markdown/config/config.yaml,sha256=w75W2Eg4-tu8rRk_23PqxWDh0010kRKLmP
 pembot/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pembot/utils/inference_client.py,sha256=jeURmY2P5heVlH1dCV0XSgiX3U2qYGEmrnUv0KFpdww,5380
 pembot/utils/string_tools.py,sha256=gtRa5rBR0Q7GspTu2WtCnvhJQLFjPfWLvhmyiPkyStU,1883
-pembot-0.1.2.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-pembot-0.1.2.dist-info/WHEEL,sha256=Dyt6SBfaasWElUrURkknVFAZDHSTwxg3PaTza7RSbkY,100
-pembot-0.1.2.dist-info/METADATA,sha256=2Eaou5uE_IQB3jUmUnvxXuY_ifpKbo9ZhZpdVjj2DMk,313
-pembot-0.1.2.dist-info/RECORD,,
+pembot-0.1.3.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+pembot-0.1.3.dist-info/WHEEL,sha256=Dyt6SBfaasWElUrURkknVFAZDHSTwxg3PaTza7RSbkY,100
+pembot-0.1.3.dist-info/METADATA,sha256=vftTQKyRwrw4BFJ_hdonub57buM5DyRXDWw28sUt884,313
+pembot-0.1.3.dist-info/RECORD,,