pembot 0.0.7__py2.py3-none-any.whl → 0.0.9__py2.py3-none-any.whl

pembot/.git/COMMIT_EDITMSG

@@ -1 +1 @@
-added model name to convertor
+fixed the type_info array pushing bug

pembot/.git/logs/HEAD

@@ -8,3 +8,5 @@ eb75e1c49f1e5b79dca17ccdbec8067756523238 0bdb4169fc0f312b8698f1df17a258fff163aea
 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
+af80ddb5890f062e364ea8ade2d602df4e12de8c 0d28f73897db0c9a9351ee9e64d2a0fe27db2705 cyto <silverstone965@gmail.com> 1752081786 +0530	commit: upgraded to 0.0.8; added ability to classify the document chunks into one more filterable parameter 'type'; other query related improvements..
+0d28f73897db0c9a9351ee9e64d2a0fe27db2705 a898d2c3947d30d8be64bd2bbcef68f956d5456b cyto <silverstone965@gmail.com> 1752136060 +0530	commit: fixed the type_info array pushing bug

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

@@ -8,3 +8,5 @@ eb75e1c49f1e5b79dca17ccdbec8067756523238 0bdb4169fc0f312b8698f1df17a258fff163aea
 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
+af80ddb5890f062e364ea8ade2d602df4e12de8c 0d28f73897db0c9a9351ee9e64d2a0fe27db2705 cyto <silverstone965@gmail.com> 1752081786 +0530	commit: upgraded to 0.0.8; added ability to classify the document chunks into one more filterable parameter 'type'; other query related improvements..
+0d28f73897db0c9a9351ee9e64d2a0fe27db2705 a898d2c3947d30d8be64bd2bbcef68f956d5456b cyto <silverstone965@gmail.com> 1752136060 +0530	commit: fixed the type_info array pushing bug

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

@@ -7,3 +7,5 @@ eb75e1c49f1e5b79dca17ccdbec8067756523238 0bdb4169fc0f312b8698f1df17a258fff163aea
 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
+af80ddb5890f062e364ea8ade2d602df4e12de8c 0d28f73897db0c9a9351ee9e64d2a0fe27db2705 cyto <silverstone965@gmail.com> 1752081801 +0530	update by push
+0d28f73897db0c9a9351ee9e64d2a0fe27db2705 a898d2c3947d30d8be64bd2bbcef68f956d5456b cyto <silverstone965@gmail.com> 1752136119 +0530	update by push

pembot/.git/objects/0d/28f73897db0c9a9351ee9e64d2a0fe27db2705

@@ -0,0 +1,3 @@
+x
��An� E��)��E�B`���z�	*�!#��%W�����߷�)�
+J��Z��K%�����HZMl���4"�� cz�mXx���
+�Y�IxaVfd�H<����@l]�G]r
w�_{�o.{�+OF�<�ػ��A�� ��[�B+�5�
V��jwl��P���Eo�t�8��y�.��ꅁ�;��-���CX�D���K�M������c��Vύo�m����rBስل���������jv�

pembot/.git/objects/a8/98d2c3947d30d8be64bd2bbcef68f956d5456b

@@ -0,0 +1 @@
+x
��݊� @�^�s�P������2�MfR���<��~pश,�A�;�HC*:�h]��8T���	)��,ņ�V��X���Q���XE�

pembot/.git/refs/heads/main

@@ -1 +1 @@
-af80ddb5890f062e364ea8ade2d602df4e12de8c
+a898d2c3947d30d8be64bd2bbcef68f956d5456b

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

@@ -1 +1 @@
-af80ddb5890f062e364ea8ade2d602df4e12de8c
+a898d2c3947d30d8be64bd2bbcef68f956d5456b

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},
+                    {
+                        '$set': doc_set,
+                        '$addToSet': {
+                            "type": { '$each': type_info }
+                        }
+                    },
+                    upsert=True
+                )
+            else:
+
+                embeddings_collection.update_one(
+                    {'docId': document_name_id, 'chunk_number': i + 1},
+                    {'$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__ = '0.0.7'
+__version__ = '0.0.9'
 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: 0.0.7
+  version: 0.0.9

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/requirements.txt

@@ -40,7 +40,7 @@ pandas==2.3.0
 pathlib==1.0.1
 pdfminer.six==20250506
 pdfplumber==0.11.7
-pembot==0.0.6
+pembot==0.0.8
 pillow==11.3.0
 pyasn1==0.6.1
 pyasn1_modules==0.4.2

{pembot-0.0.7.dist-info → pembot-0.0.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pembot
-Version: 0.0.7
+Version: 0.0.9
 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.dist-info → pembot-0.0.9.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=AQsB73MqtY0M4iaYZzGve48zpUhohq6R9DjdFwsbbKo,211
+pembot/__init__.py,sha256=1DmlCS-ZGr0pEr9CQ6lxoYtHSpRMghjac-_MbV29DhU,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/requirements.txt,sha256=6OV_n5JVco2lLA8Wq38tJX1bYgo_UU0R9RKgs4d2wfc,1360
-pembot/.git/COMMIT_EDITMSG,sha256=H9feTx6U3VWbFycy9cq077mD4oxuv2gz4G3EUOdQmV4,30
+pembot/query.py,sha256=d6K2PyDDGoIOqwn7A_KIBr83w0zjMAHjhmx1S9VlVgg,8642
+pembot/requirements.txt,sha256=vnjZ3uO4Dd8qPFDq1F2qGromJ5jrEBfBeiDwz7rKijk,1360
+pembot/.git/COMMIT_EDITMSG,sha256=iRLy0abINakd4FBRWJuD-QQ_WWbXZusnr_9e3wo4d90,38
 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=EEe4lVsgYW5zuGbFVZ8a4t7AqjDlPTqU1JGDynBe2Sc,1814
+pembot/.git/index,sha256=CdDhKv_jjjaFu1MNjZTrZZ4GF_av7KNYh750IqRkGWg,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
@@ -28,26 +28,34 @@ 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=zUB4DZpCGTMM1FnKY1jQ98WAMwY8twSD8qaFz3Q-K-4,2521
-pembot/.git/logs/refs/heads/main,sha256=zUB4DZpCGTMM1FnKY1jQ98WAMwY8twSD8qaFz3Q-K-4,2521
+pembot/.git/logs/HEAD,sha256=TTHA6MsudjF1a9H4QECSP3XPvB-k2AOsA8mTVCEis_o,2980
+pembot/.git/logs/refs/heads/main,sha256=TTHA6MsudjF1a9H4QECSP3XPvB-k2AOsA8mTVCEis_o,2980
 pembot/.git/logs/refs/remotes/origin/HEAD,sha256=OrkNquczPPh6fEGtutFKva_-_JhAdwnvXpCCPC4N6jk,194
-pembot/.git/logs/refs/remotes/origin/main,sha256=t9RDc56CIhCL27FolwvJyBJ6LK8uGVFkzXTZmWqHukw,1314
+pembot/.git/logs/refs/remotes/origin/main,sha256=uxD0NKkje26omv-w0V09LJA81e-ccHAA-FY148tg93g,1606
+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
 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/0d/28f73897db0c9a9351ee9e64d2a0fe27db2705,sha256=hqMFSXWo_05QL0Do-raB4AtK5QjvKLFBNc0RZqNga9o,244
+pembot/.git/objects/10/9d1ca0463ea42bbbc435bcb43a90711211cf49,sha256=vR33_Raw-LpnaXGQc1MhSk_ZgEROO2Xa9n97YmA3gtQ,56
+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/83a471c8119f7794d98c049170a5d7d07a4b71,sha256=XnMaYQUA8iT1fiOIvlBav331Ry7pNBOBqI3wB3Y1VM0,90
 pembot/.git/objects/28/db0ab48059acccd7d257aa02e52e9b6b83a4a5,sha256=S6PrWSQlkifYxKIgFdU0PZD0uLebS6uAP2LAUwp5yOI,91
 pembot/.git/objects/35/97e518a8658280be9f377f78edf1dfa1f23814,sha256=gfc5bFLVZpwNQb1Ox2VosDYAjw0Lc5ZLjmvNA8gWcmg,2546
 pembot/.git/objects/3d/07d3b29ff53d95de3898fb786d61732f210515,sha256=A9MNZO3QZ6ghGd1MyfmJ6H3dBTpF4HZcRosVxWytx8E,4077
+pembot/.git/objects/3d/e536f9c1fd05a23c2dec66423ed610afb0cf5f,sha256=omF4gmE9IQFZR8t6ybAKfnW02tdn9ZaVWKRhv_o1V4c,2083
 pembot/.git/objects/3e/23850624fcf5f111d6ea88ddd64adf924cf82f,sha256=ygVUpaLo7cxUdIgjFlaBh2BkllV6BIYYkzLIxsPKjWE,4111
 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/42/f03e1b66aa56bbb36a1c3a8dea9e1e727faffa,sha256=n4W2gcagesjI1rStKNxQ98q5UOHlfwFJGUADFeYldoE,418
+pembot/.git/objects/44/86da0f89c566c3bae8abf435d37aeca87f1632,sha256=S2hY860Ep-0c7gQcbgrH6ioG7-Hw9a3BwYHcCkwy1Hg,3884
 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
@@ -62,11 +70,15 @@ pembot/.git/objects/7e/0907822f7d316ebe0be07e1f6918bef412c80b,sha256=lFc55Bu-vEX
 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
+pembot/.git/objects/90/f067b86364ab243a7e3bc75f936319ba9eac88,sha256=FLAmmgvYuEAx1-ZBU30rvDzP0ppXWRSVrzPWVnArIb0,203
 pembot/.git/objects/93/8f29d9b4b1ae86e39dddf9e3d115a82ddfc9b6,sha256=xf8oZ5IBMTxfkH7MFfukV7ZIu0Apd-78eJTdlI7GBv0,90
 pembot/.git/objects/95/28bbccd167e3f4ad583a1ae9fac98a52620e27,sha256=jwJdRviwjGJIyMpE_BM6mr7B9ofGEsI5ZToJo5nmlao,263
 pembot/.git/objects/9b/123713e30fc9e225f9ac8ff5b02f8f8cf86456,sha256=xIETiieOoilleucGg7vXOgjZ-v5PI0t34fDJjDD665A,4204
+pembot/.git/objects/a8/98d2c3947d30d8be64bd2bbcef68f956d5456b,sha256=lh2LurucwRdL6WP8ChgmjXrK2lR7HASIXzt4iHFrTf4,178
+pembot/.git/objects/a9/d5e349fa091647742b09eb3d05bac8f58fe547,sha256=kaU3Z4k6ptIwO8ktcjs2-kshb0bzM4y8Uur-a27_jnk,56
 pembot/.git/objects/ab/139d2cd4798dd8e2c565b80440b1a44b376126,sha256=v1UO-WINmigZNYD74kyIv310Kq5k4SNL-gQ2DYlw9xk,6258
 pembot/.git/objects/ab/c6b15265171457b41e2cfdaf3b8c3994a59eb7,sha256=ivRCkHzUZHXB16wn2ojARknUrwBkoUsV_18QT3Jbs-k,205
+pembot/.git/objects/ab/f77db148e3fb3b26913af14ae43130396f3269,sha256=rJJenBYvGWdXvwNgHWqIJCF3q2oxeA3eT19eRxlNmJA,3346
 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
@@ -79,8 +91,10 @@ pembot/.git/objects/bf/32a7e6872e5dc4025ee3df3c921ec7ade0855f,sha256=lwL9ickzIFt
 pembot/.git/objects/bf/518686b06069d2a8abd3689908b7e1a6e16b05,sha256=w-HgdJdX2_ZdiIptJv8BcWdeDEyhl42WEk8P72X8YKU,421
 pembot/.git/objects/c0/793458db6e1bee7f79f1a504fb8ff4963f8ed3,sha256=b8lo_OrMeGgirc9yY_OFjv5xVpG6FBpZnBf7jbtlmyw,421
 pembot/.git/objects/c2/443060c07101948487cfa93cc39e082e9e0f5f,sha256=d9rjB8sgBOUQ-HQ8yu5I-c5Dqr_q2z0OOCXSufjDAak,3998
+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
+pembot/.git/objects/e0/da740b542afc451c45b9b4be6c0c7a3c79b06c,sha256=oAb2b2VwhPXykdK_ZV8MEFwfy-ZPd2Nja2gAv20U7hc,115
 pembot/.git/objects/e5/3070f2b07f45d031444b09b1b38658f3caf29e,sha256=irJ-z8kPZmg85B0f4TQz73yJoCMWMWsIR3Pi5wx1Dlk,4034
 pembot/.git/objects/e7/911a702079a6144997ea4e70f59abbe59ec2bc,sha256=r4zY-__F4gSfjE7onRTrcxvv8umXKuPuFzd95AiQ0cs,392
 pembot/.git/objects/e9/1172752e9a421ae463112d2b0506b37498c98d,sha256=qWZpM65kQPSxlVHAtyzH5L-j3rL-b9Jw-A7YBm4NMlI,249
@@ -88,6 +102,7 @@ pembot/.git/objects/ea/0af89e61a882c5afc2a8c281b2d96f174bfe58,sha256=lXbMvL_xl8P
 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/f1/3181b12cf4d539e635bf94ad6e950d68cedaf1,sha256=2cORujYAURTvGACujtNJvP1f-s7rt-UkrtPBuKfDR-g,419
 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
@@ -98,20 +113,21 @@ pembot/.git/objects/fa/9c9a62ec1203a5868b033ded428c2382c4e1b6,sha256=is9gmIhAL-Q
 pembot/.git/objects/fb/6c90c9ce5e0cdfbe074a3f060afc66f62eefde,sha256=Bmrnc27anjqoAL6akhBM4MEO9BreF5olubroBwVVUvs,56
 pembot/.git/objects/fc/988aab7e2d46396dc595ad24345e8e77dda0e4,sha256=8982HA0S9bCm0JQsrgWzIkRNIiGfaDRUUrXsnuVjE6A,196
 pembot/.git/objects/fc/e56f1e09d09a05b9babf796fb40bece176f3a2,sha256=g-IVuI_8YBn048qkyyY6Vpn8zfP8UCJxUs0F5bDD6qM,1114
+pembot/.git/objects/fd/abd48f3e947a9f420003446dd118c5295346a5,sha256=cWWr70MLaXk82O6EIPpYlGUd5P30IUEELrbrh2MrUXE,115
 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=DymD5B54ONj5DkUMd4HYO5m52NWPWMez_QV6RdNCG0g,41
+pembot/.git/refs/heads/main,sha256=UNQiShSvoG1AvbUvWeJLlN5V3ZHJSDarZ4vFLDI-Xh8,41
 pembot/.git/refs/remotes/origin/HEAD,sha256=K7aiSqD8bEhBAPXVGim7rYQc0sdV9dk_qiBOXbtOsrQ,30
-pembot/.git/refs/remotes/origin/main,sha256=DymD5B54ONj5DkUMd4HYO5m52NWPWMez_QV6RdNCG0g,41
+pembot/.git/refs/remotes/origin/main,sha256=UNQiShSvoG1AvbUvWeJLlN5V3ZHJSDarZ4vFLDI-Xh8,41
 pembot/AnyToText/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 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=n-xQwCxSCpGC9jvxHoCVWhBhtm4fVmeg_Gvcn0FDJQ4,10699
+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=xqo_Zq2dKEw98tzXDvJqOiJBluFCvT5JNhXpqkIqW0Y,156
+pembot/config/config.yaml,sha256=9Ysd58bptzE9_od_DQQj1ebzrYsyLrOrlzN52dTA3zQ,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
@@ -167,7 +183,7 @@ 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-0.0.7.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-pembot-0.0.7.dist-info/WHEEL,sha256=Dyt6SBfaasWElUrURkknVFAZDHSTwxg3PaTza7RSbkY,100
-pembot-0.0.7.dist-info/METADATA,sha256=7kfZ28VYYaCy0mWNNLTP_pP6Bi9c-PtzbEwdbyNdLzI,313
-pembot-0.0.7.dist-info/RECORD,,
+pembot-0.0.9.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+pembot-0.0.9.dist-info/WHEEL,sha256=Dyt6SBfaasWElUrURkknVFAZDHSTwxg3PaTza7RSbkY,100
+pembot-0.0.9.dist-info/METADATA,sha256=Ba3uu0dcTllzXwQqeTwRIJx3--FKl_eXCCorQAPp2pU,313
+pembot-0.0.9.dist-info/RECORD,,