pembot 0.0.6__py2.py3-none-any.whl → 0.0.8__py2.py3-none-any.whl

pembot/.git/COMMIT_EDITMSG

@@ -1 +1 @@
-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);
+added model name to convertor

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/.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/.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/.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/.git/refs/heads/main

@@ -1 +1 @@
-9528bbccd167e3f4ad583a1ae9fac98a52620e27
+af80ddb5890f062e364ea8ade2d602df4e12de8c

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

@@ -1 +1 @@
-9528bbccd167e3f4ad583a1ae9fac98a52620e27
+af80ddb5890f062e364ea8ade2d602df4e12de8c

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/TextEmbedder/mongodb_embedder.py

@@ -29,6 +29,7 @@ def search_within_document(
     limit: int = 5,
     index_name: str = "test_search",
     embeddings_collection_name: str= "doc_chunks",
+    document_belongs_to_a_type = "",
 ):
     """
     Performs a vector similarity search within the chunks of a specific document
@@ -42,6 +43,7 @@ def search_within_document(
         index_name: The name of your MongoDB Atlas Vector Search index.
                     You MUST have a vector search index created on the 'embedding' field
                     of the 'embeddings_collection' collection for this to work efficiently.
+        document_belongs_to_a_type: When search spaces intersect for different docIds, such that docId is an array field,
 
     Returns:
         A list of dictionaries, where each dictionary represents a matching chunk
@@ -50,10 +52,23 @@ def search_within_document(
     embeddings_collection = db_client[embeddings_collection_name]
 
     print(f"Searching within document (docId: {document_name_id})...")
+    # print(f" filter (slug: {document_belongs_to_a_type})...")
 
     # MongoDB Atlas Vector Search aggregation pipeline
     # The 'path' should point to the field containing the embeddings.
     # The 'filter' stage is crucial for searching within a specific document.
+    #
+    project_dict= {
+        '_id': 0,
+        'docId': 1,
+        'chunk_number': 1,
+        'chunk_text': 1,
+        'score': { '$meta': 'vectorSearchScore' } # Get the similarity score
+    }
+
+    if document_belongs_to_a_type:
+        project_dict['type']= 1
+
     pipeline = [
         {
             '$vectorSearch': {
@@ -66,25 +81,21 @@ def search_within_document(
                 'index': index_name,
 
                 #filter to search only within the specified document
-                'filter': {
-                    'docId': document_name_id
-                }
+                'filter':
+                    { "type": {"$in": [document_belongs_to_a_type ]} } if document_belongs_to_a_type else
+                    { 'docId': document_name_id }
             }
         },
 
         # to exclude the MongoDB internal _id
         {
-            '$project': {
-                '_id': 0,
-                'docId': 1,
-                'chunk_number': 1,
-                'chunk_text': 1,
-                'score': { '$meta': 'vectorSearchScore' } # Get the similarity score
-            }
+            '$project': project_dict
         }
     ]
 
+    # print("sesraching now:")
     results = list(embeddings_collection.aggregate(pipeline))
+    # print("search results: ", results)
 
     if not results:
         print(f"No relevant chunks found for document '{document_name_id}' with the given query.")
@@ -100,15 +111,18 @@ def search_within_document(
 
 
 
-def process_document_and_embed(db_client,
+def process_document_and_embed(
+    db_client,
     llm_client,
     inference_client,
     file_path: Path,
     chunk_size: int,
-    embedding_model: str = 'nomic-embed-text:v1.5',
+    embedding_model: str = 'BAAI/bge-en-icl',
     embeddings_collection_name= "doc_chunks",
     use_custom_id: str | None = None,
-    use_custom_input: str | None = None
+    use_custom_input: str | None = None,
+    document_belongs_to_a_type= "",
+    type_info= []
 ) -> list[dict]:
     """
     Processes an input document by chunking its text, generating embeddings using
@@ -228,13 +242,30 @@ def process_document_and_embed(db_client,
                 'chunk_text': chunk,
                 'embedding': embedding,
                 'chunk_id_global': chunk_id_global,
-                'chunk_id_doc_specific': chunk_id_doc_specific
+                'chunk_id_doc_specific': chunk_id_doc_specific,
             }
-            embeddings_collection.update_one(
-                {'docId': document_name_id, 'chunk_number': i + 1},
-                {'$set': doc_set},
-                upsert=True
-            )
+
+
+            # TBD: this is NOT pushing array, this is creating a "$push" field with type: "" object
+
+            if len(type_info) > 0:
+                embeddings_collection.update_one(
+                    {'docId': document_name_id, 'chunk_number': i + 1},
+                    {
+                        '$set': doc_set,
+                        '$push': {
+                            "type": type_info
+                        }
+                    },
+                    upsert=True
+                )
+            else:
+
+                embeddings_collection.update_one(
+                    {'docId': document_name_id, 'chunk_number': i + 1},
+                    {'$set': doc_set},
+                    upsert=True
+                )
             print(f"Successfully stored chunk {i+1} for '{file_path.name}' in MongoDB.")
             res.append({**doc_set, "docId": document_name_id, "chunk_number": i + 1})
 

pembot/TextEmbedder/mongodb_index_creator.py

@@ -4,7 +4,7 @@ from pymongo.operations import SearchIndexModel
 import time
 import os
 
-def create_vector_index(collection: Collection, index_name: str, num_dimensions: int = 768):
+def create_vector_index(collection: Collection, index_name: str, num_dimensions: int = 768, document_belongs_to_a_type= ""):
     """
     Creates a MongoDB Atlas Vector Search index if it does not already exist.
 
@@ -13,14 +13,14 @@ def create_vector_index(collection: Collection, index_name: str, num_dimensions:
         index_name: The desired name for the vector search index.
         num_dimensions: The number of dimensions for the embedding vectors.
     """
-    
+
     # 1. Check if the index already exists
     existing_indexes = list(collection.list_search_indexes())
-    
+
     for index in existing_indexes:
         if index.get('name') == index_name:
             print(f"Search index '{index_name}' already exists. Skipping creation.")
-            
+
             # Optional: You can also check if the existing index is "READY"
             if index.get('status') == 'READY':
                 print(f"Index '{index_name}' is already ready for querying.")
@@ -33,20 +33,27 @@ def create_vector_index(collection: Collection, index_name: str, num_dimensions:
     # 2. If the index does not exist, proceed to create it
     print(f"Search index '{index_name}' does not exist. Creating it now...")
 
+    fields_arr= [
+        {
+            "type": "vector",
+            "path": "embedding",
+            "similarity": "dotProduct", # Or "cosine", "euclidean"
+            "numDimensions": num_dimensions,
+            "quantization": "scalar" # Or "none"
+        },
+        {
+            "type": "filter",
+            "path": "docId"
+        }
+    ]
+
+    if document_belongs_to_a_type:
+        fields_arr.append({
+            "type": "filter",
+            "path": "type"
+        })
     search_index_model = SearchIndexModel(definition={
-            "fields": [
-                {
-                    "type": "vector",
-                    "path": "embedding",
-                    "similarity": "dotProduct", # Or "cosine", "euclidean"
-                    "numDimensions": num_dimensions,
-                    "quantization": "scalar" # Or "none"
-                },
-                {
-                    "type": "filter",
-                    "path": "docId"
-                }
-            ]
+            "fields": fields_arr
         },
         name=index_name,
         type="vectorSearch"
@@ -70,7 +77,7 @@ def _wait_for_index_ready(collection: Collection, index_name: str):
     Helper function to poll the index status until it's ready.
     """
     print("Polling to check if the index is ready. This may take some time (up to a few minutes for large indexes).")
-    
+
     start_time = time.time()
     timeout = 300 # 5 minutes timeout, adjust as needed
 
@@ -89,7 +96,7 @@ def _wait_for_index_ready(collection: Collection, index_name: str):
                 print(f"Index '{index_name}' status: {current_status}. Waiting...")
         except Exception as e:
             print(f"Error while polling index status: {e}. Retrying...")
-        
+
         if time.time() - start_time > timeout:
             status= indices[0].get('status') if indices else 'N/A'
             print(f"Timeout: Index '{index_name}' did not become ready within {timeout} seconds. Current status: {status}")
@@ -99,9 +106,9 @@ def _wait_for_index_ready(collection: Collection, index_name: str):
 
 # --- Example Usage ---
 if __name__ == "__main__":
-    
+
     # Replace with your database and collection names
-    DATABASE_NAME = "pembot" 
+    DATABASE_NAME = "pembot"
     COLLECTION_NAME = "doc_chunks"
     VECTOR_INDEX_NAME = "test_search"
 
@@ -119,7 +126,7 @@ if __name__ == "__main__":
 
         # Call the function to create the index, with existence check
         create_vector_index(collection, VECTOR_INDEX_NAME, num_dimensions=EMBEDDING_DIMENSIONS)
-        
+
         # Test calling it again to see the "already exists" message
         create_vector_index(collection, VECTOR_INDEX_NAME, num_dimensions=EMBEDDING_DIMENSIONS)
 
@@ -129,5 +136,3 @@ if __name__ == "__main__":
         if 'mongo_client' in locals() and mongo_client:
             mongo_client.close()
             print("MongoDB connection closed.")
-
-

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__ = '0.0.8'
 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: 0.0.6
+  version: 0.0.8

pembot/pdf2markdown/.git/COMMIT_EDITMSG

@@ -1 +1 @@
-cyto/argument-list-bug-fix;authentication-used-in-gradio-client
+handled the gpu errors non-gracefully so that it stops

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/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/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/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/pdf2markdown/.git/refs/heads/main

@@ -1 +1 @@
-b48d697aa9fd97151eb2a84a1af5d408b7630232
+f3b2d76c75bbd50e04fc4c2ad17fc94ca6daed32

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

@@ -1 +1 @@
-b48d697aa9fd97151eb2a84a1af5d408b7630232
+f3b2d76c75bbd50e04fc4c2ad17fc94ca6daed32

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/query.py

@@ -68,7 +68,8 @@ def multi_embedding_average(llm_client, inference_client, descriptions, model= "
         except Exception as e:
             print(f"Error generating embedding for description '{desc}': {e}")
             # Decide how to handle errors: skip, raise, or use a placeholder
-            continue
+            # continue
+            raise e
         time.sleep(1)
 
     if not description_embeddings:
@@ -81,7 +82,7 @@ def multi_embedding_average(llm_client, inference_client, descriptions, model= "
 
 
 
-def rag_query_llm(db_client, llm_client, inference_client, user_query: str, document_id: str, required_fields_descriptions: list[str], model_name: str = "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B", ollama_base_url: str = "http://localhost:11434", no_of_fields= 4, embedding_model= "BAAI/bge-en-icl", llm_provider_name: PROVIDER_T= "novita", index_name: str= "test_search", embeddings_collection= "doc_chunks"):
+def rag_query_llm(db_client, llm_client, inference_client, user_query: str, document_id: str, required_fields_descriptions: list[str], model_name: str = "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B", ollama_base_url: str = "http://localhost:11434", no_of_fields= 4, embedding_model= "BAAI/bge-en-icl", llm_provider_name: PROVIDER_T= "novita", index_name: str= "test_search", embeddings_collection= "doc_chunks", document_belongs_to_a_type= ""):
     """
     Performs a RAG (Retrieval Augmented Generation) query using a Hugging Face
     embedding model, ChromaDB for retrieval, and a local Ollama model for generation.
@@ -119,10 +120,10 @@ def rag_query_llm(db_client, llm_client, inference_client, user_query: str, docu
     aggregate_query_embedding= multi_embedding_average(llm_client, inference_client, required_fields_descriptions, model= embedding_model, embed_locally= embed_locally)
     print("Aggregate query embedding generated. length: ", len(aggregate_query_embedding))
 
-    create_vector_index(db_client[embeddings_collection], index_name, num_dimensions= len(aggregate_query_embedding))
+    create_vector_index(db_client[embeddings_collection], index_name, num_dimensions= len(aggregate_query_embedding), document_belongs_to_a_type= document_belongs_to_a_type)
 
     # check the order of args
-    relevant_chunks= search_within_document(db_client, aggregate_query_embedding, document_id, limit= no_of_fields, index_name= index_name, embeddings_collection_name= embeddings_collection)
+    relevant_chunks= search_within_document(db_client, aggregate_query_embedding, document_id, limit= no_of_fields, index_name= index_name, embeddings_collection_name= embeddings_collection, document_belongs_to_a_type= document_belongs_to_a_type)
     relevant_chunks= list(map(lambda x: x['chunk_text'], relevant_chunks))
 
     if not relevant_chunks:

{pembot-0.0.6.dist-info → pembot-0.0.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pembot
-Version: 0.0.6
+Version: 0.0.8
 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-0.0.6.dist-info → pembot-0.0.8.dist-info}/RECORD

@@ -1,17 +1,17 @@
 pembot/.gitignore,sha256=_7FTsZokJ_pzEyyPjOsGw5x5Xx3gUBFaafs7UlPsv9E,98
 pembot/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-pembot/__init__.py,sha256=s4fd-1t1D43kkQi_78FmX_7hi-NsBfqtc2BHwNrMHtw,211
+pembot/__init__.py,sha256=XAG3pbUQGlrUZZgAKAxq96MjvCGaEPkpGTSKIwzNvGY,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/query.py,sha256=D1RPRoImDWCafbshT2NpO4ymVj2RySm8j5FJ5bRzYWw,8476
+pembot/query.py,sha256=d6K2PyDDGoIOqwn7A_KIBr83w0zjMAHjhmx1S9VlVgg,8642
 pembot/requirements.txt,sha256=6OV_n5JVco2lLA8Wq38tJX1bYgo_UU0R9RKgs4d2wfc,1360
-pembot/.git/COMMIT_EDITMSG,sha256=HR106qWTNcQKmC8LAIwmZ9A9YBTENaUYQy3UtJmK0XY,238
+pembot/.git/COMMIT_EDITMSG,sha256=H9feTx6U3VWbFycy9cq077mD4oxuv2gz4G3EUOdQmV4,30
 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=9R33jd4OjVHXzQElukY8zpNSB7v6vW4j4GMcpNBT5bo,1814
+pembot/.git/index,sha256=EEe4lVsgYW5zuGbFVZ8a4t7AqjDlPTqU1JGDynBe2Sc,1814
 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
@@ -28,13 +28,14 @@ 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=crGP01FLAqdksSr1razn4_Aa5devc2MaSbfStzWV4Os,2160
-pembot/.git/logs/refs/heads/main,sha256=crGP01FLAqdksSr1razn4_Aa5devc2MaSbfStzWV4Os,2160
+pembot/.git/logs/HEAD,sha256=zUB4DZpCGTMM1FnKY1jQ98WAMwY8twSD8qaFz3Q-K-4,2521
+pembot/.git/logs/refs/heads/main,sha256=zUB4DZpCGTMM1FnKY1jQ98WAMwY8twSD8qaFz3Q-K-4,2521
 pembot/.git/logs/refs/remotes/origin/HEAD,sha256=OrkNquczPPh6fEGtutFKva_-_JhAdwnvXpCCPC4N6jk,194
-pembot/.git/logs/refs/remotes/origin/main,sha256=5cKDe0WKpvOSobN6UHTaj0is1mUWZMz0xjzyBSz1l2s,1022
+pembot/.git/logs/refs/remotes/origin/main,sha256=t9RDc56CIhCL27FolwvJyBJ6LK8uGVFkzXTZmWqHukw,1314
 pembot/.git/objects/0a/fb3a98cdc55b1434b44534ec2bf22c56cfa26c,sha256=Xxw20vI57zuhERWopDAZpQw6rAOhFtUr05lzpGyCTTE,120
 pembot/.git/objects/0b/db4169fc0f312b8698f1df17a258fff163aeaa,sha256=hsOHhX0Yajg27Y7B9lo-WjDXzW1KNMg2CBr93G116EY,387
 pembot/.git/objects/0c/8d9b2690545bf1906b05cd9f18b783b3eb74f1,sha256=GKt_CAJNOQXwGnoFLuiNpkd0s_hP_UDLKd59VRknYy0,330
+pembot/.git/objects/0c/ab66ffbaf50ef60dd41f3498595ebd2526b33c,sha256=Uk1dStvEBica-t38qHsZZ_4mxvi6b6VA9PaKE4KSunQ,90
 pembot/.git/objects/18/28e18ab80aa64d334b26428708140e280cbc63,sha256=PTF8WLVhzxBDTZhwU_PBHrkQBbijHbKvttSr0XVTOcU,3936
 pembot/.git/objects/19/f61df7dbd562d04f561288677bbf2f18f5dff7,sha256=zg8IdUSnMYpJ6HsfY2LQbXQTMwlT1IPWRSEiY2uDwyE,392
 pembot/.git/objects/1f/83a471c8119f7794d98c049170a5d7d07a4b71,sha256=XnMaYQUA8iT1fiOIvlBav331Ry7pNBOBqI3wB3Y1VM0,90
@@ -45,8 +46,10 @@ pembot/.git/objects/3e/23850624fcf5f111d6ea88ddd64adf924cf82f,sha256=ygVUpaLo7cx
 pembot/.git/objects/3e/cf23eb95123287531d708a21d4ba88d92ccabb,sha256=Jlg3XIzIjk3N5ZKolXbz_betMybJ2t2TVuOARg2ruQU,4943
 pembot/.git/objects/3f/78215d7e17da726fb352fd92b3c117db9b63ba,sha256=J8r5hqTEgAwlH5sDjr9tp1ipqpvs4BAVQY5rkiKqDCw,4080
 pembot/.git/objects/3f/e072cf3cb6a9f30c3e9936e3ddf622e80270d0,sha256=Z-UoKi2MYe0qGTtBxAr5cnIOHKkhoEXMgalevFUz9lA,2992
+pembot/.git/objects/41/ae8fa8f8baa2daee5ec0aa21ae17922ae051a0,sha256=TLuVmtSH9K33qB-WHMxKDUihHCrwdTtCKtjBs-rAnJ4,56
 pembot/.git/objects/41/cbeb6bcb4c6fa9ef9be571082d95ecb4ea0ee3,sha256=waMrzjG_o5D4JgHkjjqcDQCwuS17w60JRkVr25ZFlcI,117
 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/61/46a371b9c1bd9f51af273f11f986cfd1bedeba,sha256=KZvfnjxuriY54uWZQOM-GLovAvHs1k8_KwhpjNA5lW4,128
 pembot/.git/objects/63/1700a51c8fa97b543991f5f61bfcd1e7e1327d,sha256=sYkhBkrSPQ8klX2gPrXJUZVt2a0iaF7KC7NFGBuxgeY,4360
@@ -54,6 +57,8 @@ pembot/.git/objects/64/00040794955d17c9a1fe1aaaea59f2c4822177,sha256=-tFnLFQvYrt
 pembot/.git/objects/6d/7a865a23b1cb4182f67907820104ced48b11c9,sha256=dJRTCmT9rLygONcQ7MPETl9AImF3Iy5tB_KUeCvKyKY,2651
 pembot/.git/objects/72/f047cda92abcd1ddc857f6461de605f8668331,sha256=PFb9LUDMnUCnuJcXUa5W1ea__fdP17kNyWrnqvnOpjs,240
 pembot/.git/objects/73/2e98f08bc806c331b06847fc8c743f545499e5,sha256=kbKUb6fwwhRO73B4EZmol55JBvckqE3GNZ9PqHRB2ag,3995
+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/8b/5be2af9b16f290549193859c214cd9072212e8,sha256=DhGeGisCdFZ0TcRKp5angRpaseI87TQDt5FtGZInstk,117
@@ -63,8 +68,10 @@ pembot/.git/objects/9b/123713e30fc9e225f9ac8ff5b02f8f8cf86456,sha256=xIETiieOoil
 pembot/.git/objects/ab/139d2cd4798dd8e2c565b80440b1a44b376126,sha256=v1UO-WINmigZNYD74kyIv310Kq5k4SNL-gQ2DYlw9xk,6258
 pembot/.git/objects/ab/c6b15265171457b41e2cfdaf3b8c3994a59eb7,sha256=ivRCkHzUZHXB16wn2ojARknUrwBkoUsV_18QT3Jbs-k,205
 pembot/.git/objects/ac/9c9018c62fa30dc142665c1b5a375f4e056880,sha256=P_8LPBV0v4D17Akj4f5Cr2dhgNFUsh4o7DLK78CfNPo,349
+pembot/.git/objects/af/80ddb5890f062e364ea8ade2d602df4e12de8c,sha256=QELzH3NdMCFohFEcf5oAAu_e54VFr-LhTyPbXY7GjSk,169
 pembot/.git/objects/b1/1173d9b68db117437ccb9551461152e1e8a77d,sha256=6cl8NMNQ9b5fBh97GPEQNssOVrh-EQLJfhqSBbNb_vU,205
 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/bd/8fd1cb166996e74a8631f3a6f764a53af75297,sha256=JOkICUEv6tdVp7mYDUKtXnsWq3IIZSmm8iUP7OqQwc4,56
 pembot/.git/objects/bf/068a0714e2145de83a5c004f4213b091439d0e,sha256=MpiiCqAk6GQ5iGzeThU0rsabrgA5tCAgdIWudAM0IrA,420
@@ -79,8 +86,12 @@ pembot/.git/objects/e7/911a702079a6144997ea4e70f59abbe59ec2bc,sha256=r4zY-__F4gS
 pembot/.git/objects/e9/1172752e9a421ae463112d2b0506b37498c98d,sha256=qWZpM65kQPSxlVHAtyzH5L-j3rL-b9Jw-A7YBm4NMlI,249
 pembot/.git/objects/ea/0af89e61a882c5afc2a8c281b2d96f174bfe58,sha256=lXbMvL_xl8PhWWfL5WAnvxqE3usiGO3iY83yi3GZwXc,4438
 pembot/.git/objects/eb/75e1c49f1e5b79dca17ccdbec8067756523238,sha256=ltEINFUpQP86CkE4nAT1Afegz3ytY3Nlx1P6ibTFEbo,305
+pembot/.git/objects/ee/a73c7f24094ed83b014f7cfce46e10f817bec8,sha256=fFYq_ODekFhF9SwBL9GP_fGDsNavXVVOuI6kmnHlkiY,5140
+pembot/.git/objects/ef/0503a60244391590b16042019032e91d7cc30d,sha256=mrF9jZHY2oJm8tkd8nQdMgUPbrZfENOFaR3mvbwi1dg,187
 pembot/.git/objects/f1/655afa1c5636c8d58969e3194bb770aefbc552,sha256=Ugf-wTcOlwZXmxmbnjEc3iOK3dDRntTVONOJsrOjl3E,205
 pembot/.git/objects/f4/e991088a63def67a30a2b8bbdb4d58514abab8,sha256=Y5WfCEpk121Cy9gaFfSY4ZkUz54qu45osRZdTy9kZ8c,393
+pembot/.git/objects/f6/b1d54483ce20fbcb252a8a93a5eff7bec88729,sha256=MrRy-fBSXZcp-yJM3e-tH3wCdUS-VFX6rW_mKTa-0_Y,419
+pembot/.git/objects/f8/6fbd490878cb0d3c35cc4443672d1309171bf1,sha256=hBVqthGLEEX2NmdD51kjiIeTd5CP5MU8it41zHlW3m0,419
 pembot/.git/objects/f8/cbb5bfd1503e66cec2c593362c60a317b6d300,sha256=p_PmV9ng8Bhxj4AJjQRxpZDWcSHcksAhYU5r77adriY,4581
 pembot/.git/objects/f9/98e1f01c2bf0a20159fc851327af05beb3ac88,sha256=uU1uWZIPyQBpUuEM4m9Ff-gnn7opvjOpIt3JoqdFwN0,205
 pembot/.git/objects/fa/9c9a62ec1203a5868b033ded428c2382c4e1b6,sha256=is9gmIhAL-QXC9oLx3DHkatfI9wWFePJlo1yGPZrPaE,196
@@ -90,28 +101,28 @@ pembot/.git/objects/fc/e56f1e09d09a05b9babf796fb40bece176f3a2,sha256=g-IVuI_8YBn
 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=Sz6HMFv8rlaBjeNHaBfSrRUorGipDPAJnfxmiUADG5I,41
+pembot/.git/refs/heads/main,sha256=DymD5B54ONj5DkUMd4HYO5m52NWPWMez_QV6RdNCG0g,41
 pembot/.git/refs/remotes/origin/HEAD,sha256=K7aiSqD8bEhBAPXVGim7rYQc0sdV9dk_qiBOXbtOsrQ,30
-pembot/.git/refs/remotes/origin/main,sha256=Sz6HMFv8rlaBjeNHaBfSrRUorGipDPAJnfxmiUADG5I,41
+pembot/.git/refs/remotes/origin/main,sha256=DymD5B54ONj5DkUMd4HYO5m52NWPWMez_QV6RdNCG0g,41
 pembot/AnyToText/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-pembot/AnyToText/convertor.py,sha256=8fDFxjyiL8H9mhZTjmxgePQj-sVZCHnEfMooYMqt6wk,17104
+pembot/AnyToText/convertor.py,sha256=gqvhwFssUsAeirfO4n0Ztwga1hn8zHbdG96sMTjYrpE,17188
 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=pD8mP-uC_o0COPdOrCTMpoC5PdF8hXlqARHvTr2T-VI,9642
-pembot/TextEmbedder/mongodb_index_creator.py,sha256=ejpsF_y1zY6Z0nux02vjODiDPnxx-YA_xy2PmT94zZ4,5306
+pembot/TextEmbedder/mongodb_embedder.py,sha256=RotNlerS3WKEUGRNeQM5MTkl5BtaWNHVaXO1gN5NicI,10682
+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=JHvRjzmkPIdKjryQY3W375B1IQgFvbumQ727AwvRW7U,156
+pembot/config/config.yaml,sha256=y-2BklPelldaXJ_hxFD9k-bFpDA6OAZkaoh5XlvASCE,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
-pembot/pdf2markdown/extract.py,sha256=ylkPfxMJiePUKmGlZ8B3fz51FtG17Q8P27KGLrz9J48,33289
+pembot/pdf2markdown/extract.py,sha256=0fnZnUqNy7shef6dijqEAMgBSf0YAiEx_mbRSU_pmQg,34418
 pembot/pdf2markdown/pyrightconfig.json,sha256=Vt_k4N2LtZhth0lQOQAOnRKDOQkYYVzmdtb-bP3gu7M,47
 pembot/pdf2markdown/requirements.txt,sha256=0vZQzkSZKLNVUttd4euoDyYEy0nc2W3CIVxhepHW5Ho,76
-pembot/pdf2markdown/.git/COMMIT_EDITMSG,sha256=n3-nJDAjMCjnbADDTrmOPQYgrUSZRElYCQsXxv_AS1g,64
+pembot/pdf2markdown/.git/COMMIT_EDITMSG,sha256=K6REOtE5mjRmxGSeQdpaFAr1luu1BmaZnzXkTjKINzY,55
 pembot/pdf2markdown/.git/HEAD,sha256=KNJb-Cr0wOK3L1CVmyvrhZ4-YLljCl6MYD2tTdsrboA,21
 pembot/pdf2markdown/.git/config,sha256=bxpN4Vp2IKsAw9QkRoCIXULseCngmK7OQMg_81HDmww,398
 pembot/pdf2markdown/.git/description,sha256=hatsFj1DoX6pz3eIMIvKFGbxsKjRzJLibpv2PaQGKu4,73
-pembot/pdf2markdown/.git/index,sha256=b6ZJzQ8qBONIIcgKXWOnK38rPQ1h93xQGpjMUmeVhqc,656
+pembot/pdf2markdown/.git/index,sha256=0VmTX9ESG5zK1K1FPqgzWMCzNvTfSUfnBeod1rhNHW8,656
 pembot/pdf2markdown/.git/packed-refs,sha256=kJfKR7KBh8Ao4cGF_14wFxiFMP_lBLTKdXRAB2UMQ_o,112
 pembot/pdf2markdown/.git/hooks/applypatch-msg.sample,sha256=AiNJeguLAzqlijpSG4YphpOGz3qw4vEBlj0yiqYhk_c,478
 pembot/pdf2markdown/.git/hooks/commit-msg.sample,sha256=H3TV6SkpebVz69WXQdRsuT_zkazdCD00C5Q3B1PZJDc,896
@@ -128,11 +139,12 @@ pembot/pdf2markdown/.git/hooks/push-to-checkout.sample,sha256=pT0HQXmLKHxt16-mSu
 pembot/pdf2markdown/.git/hooks/sendemail-validate.sample,sha256=ROv8kj3FRmvACWAvDs8Ge5xlRZq_6IaN3Em3jmztepI,2308
 pembot/pdf2markdown/.git/hooks/update.sample,sha256=jV8vqD4QPPCLV-qmdSHfkZT0XL28s32lKtWGCXoU0QY,3650
 pembot/pdf2markdown/.git/info/exclude,sha256=ZnH-g7egfIky7okWTR8nk7IxgFjri5jcXAbuClo7DsE,240
-pembot/pdf2markdown/.git/logs/HEAD,sha256=kgz5CoaL_AuYbbsv4KXiCvuqydnLusQUvmjDdzMtl6U,1002
-pembot/pdf2markdown/.git/logs/refs/heads/main,sha256=kgz5CoaL_AuYbbsv4KXiCvuqydnLusQUvmjDdzMtl6U,1002
-pembot/pdf2markdown/.git/logs/refs/remotes/myorigin/main,sha256=bmsvulVWtYHEVD_JpjpPFXZKCZd9dZVkA-XT3fzBauw,438
+pembot/pdf2markdown/.git/logs/HEAD,sha256=Y5czyWfueqU9tPNqxXVaF_68HbwbQmSHXFJtAgsqAZc,1196
+pembot/pdf2markdown/.git/logs/refs/heads/main,sha256=Y5czyWfueqU9tPNqxXVaF_68HbwbQmSHXFJtAgsqAZc,1196
+pembot/pdf2markdown/.git/logs/refs/remotes/myorigin/main,sha256=IRBHjv2h2ZmZW1wiNFT6J0mY2KXK9juXpTz_QgW4R24,584
 pembot/pdf2markdown/.git/logs/refs/remotes/origin/HEAD,sha256=jJscThcgJ-i1V19vA4RVs9acp0QIKsVSwY9zAmV3tjU,193
 pembot/pdf2markdown/.git/objects/14/251b198e0bac39a3dc3b42f9e57b20c01465fb,sha256=Ssx4RupGzteVz0Irtgh95-Ccnacskv8ql8zLtqUgmOE,209
+pembot/pdf2markdown/.git/objects/24/7b15a6b1e0e3d270c05af184f048736376cd4e,sha256=rD1H5Ywoiuw8gwDZyHJ1p4zxqfIh47ym6jJg0pL6KLI,10023
 pembot/pdf2markdown/.git/objects/24/8f03b5f969a7fbd396b496f40b57f0ae81c148,sha256=ScB91DWSzfIrFLnghWglGqxxxmHxzODACQiXJEHDeWA,229
 pembot/pdf2markdown/.git/objects/57/74dc9c3901d2ffb2cd7dafe2ad6612a7f9f42c,sha256=0Vkgzw7kU0cludbgJUyqCWLgK5Q3vfFnoKmeLq6c-uU,52
 pembot/pdf2markdown/.git/objects/72/2dc14f82e78ce41717348b256e0c17834933b4,sha256=062pZN8JWfsC9z4MKIEgUcLIdnjzC6hwPjjsvHDhW-M,266
@@ -140,20 +152,22 @@ pembot/pdf2markdown/.git/objects/79/eb7b93ced70e399bd561093c45de7641414dbd,sha25
 pembot/pdf2markdown/.git/objects/8d/9ce1fd9733a78c592b34af9c94b98960c601ed,sha256=eJMRf2BFDCxSgPuVPPLd6zZu3NmwMeYVYwyxW9QkW6M,9772
 pembot/pdf2markdown/.git/objects/95/745843bb4377d6042180daeda818c0b16fd493,sha256=ddMj81nqLqqtVtrJ6TV7eOEjrzq38AbIjgWAPj0MaT8,12391
 pembot/pdf2markdown/.git/objects/a5/c6dfb577782c259990dcf977e355298e923428,sha256=c6vkmaxLJ8-6V2DykAhGnGUFJc1EH_-TuDeijrrHRWg,265
+pembot/pdf2markdown/.git/objects/a7/4bcd5e67cb1066dd504b92b42390fe0b2c3d38,sha256=Tg_Co5uUFebLteNs9dqzI-P4FGwktB-K1PZN4drr9Rk,266
 pembot/pdf2markdown/.git/objects/b4/8d697aa9fd97151eb2a84a1af5d408b7630232,sha256=nSKTkx4mVrz7uaJkacuDJH7KO-vR1-OrvBV-e2HQvm0,194
 pembot/pdf2markdown/.git/objects/b8/702320e56074e9680181d8b7897d6a0a552e2d,sha256=-XJJ4C0svu4LaZ9Zi3pAWVvy18w2CJ2lg16Zr2Hnu-U,372
 pembot/pdf2markdown/.git/objects/e6/9de29bb2d1d6434b8b29ae775ad8c2e48c5391,sha256=FkxfqAZ_rPGkPwnOPQ416_U6f1cj7L8VqGZ8_FPCb2w,15
+pembot/pdf2markdown/.git/objects/f3/b2d76c75bbd50e04fc4c2ad17fc94ca6daed32,sha256=CohsUCG2jiRVFKvC6ouCuy1pE0RS8C_dHMfOpSoCTM8,187
 pembot/pdf2markdown/.git/objects/pack/pack-d3051affdd6c31306dc53489168fc870872085d1.idx,sha256=nZ0BJQYRC49OtqnyhZR_teR85PqslUG6j16UAKoX8m4,3452
 pembot/pdf2markdown/.git/objects/pack/pack-d3051affdd6c31306dc53489168fc870872085d1.pack,sha256=_KzHMGgrVzHGn2ZiKyHlvqc-BwTEeq3PqDPPJ9DYI5E,32222
 pembot/pdf2markdown/.git/objects/pack/pack-d3051affdd6c31306dc53489168fc870872085d1.rev,sha256=1jASJFjt2r2Sxd2G87oSTfrQnowK2ThvjVlWTIF-47E,392
-pembot/pdf2markdown/.git/refs/heads/main,sha256=oRkN5qBSGT5N23aQ_E4DIUGMZLPez-Cij_1QgK-k3jI,41
-pembot/pdf2markdown/.git/refs/remotes/myorigin/main,sha256=oRkN5qBSGT5N23aQ_E4DIUGMZLPez-Cij_1QgK-k3jI,41
+pembot/pdf2markdown/.git/refs/heads/main,sha256=II7qd2fp3dz8A72owuHimxMIScJpmznueAkXM0sHxJU,41
+pembot/pdf2markdown/.git/refs/remotes/myorigin/main,sha256=II7qd2fp3dz8A72owuHimxMIScJpmznueAkXM0sHxJU,41
 pembot/pdf2markdown/.git/refs/remotes/origin/HEAD,sha256=K7aiSqD8bEhBAPXVGim7rYQc0sdV9dk_qiBOXbtOsrQ,30
 pembot/pdf2markdown/config/config.yaml,sha256=w75W2Eg4-tu8rRk_23PqxWDh0010kRKLmPrh46f_Njc,66
 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-0.0.6.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-pembot-0.0.6.dist-info/WHEEL,sha256=Dyt6SBfaasWElUrURkknVFAZDHSTwxg3PaTza7RSbkY,100
-pembot-0.0.6.dist-info/METADATA,sha256=jcibBPdDsmAbgWICvgecVgEEk_9wPQ4xDBkHpdhjKPw,313
-pembot-0.0.6.dist-info/RECORD,,
+pembot-0.0.8.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+pembot-0.0.8.dist-info/WHEEL,sha256=Dyt6SBfaasWElUrURkknVFAZDHSTwxg3PaTza7RSbkY,100
+pembot-0.0.8.dist-info/METADATA,sha256=kfa20bL5qROy6a8bsALEzDRlmF-JnTgmR7Qc8rz6PNQ,313
+pembot-0.0.8.dist-info/RECORD,,