Update auditqa/process_chunks.py

auditqa/process_chunks.py

@@ -50,7 +50,7 @@ def load_chunks():
     #  which will be used later for filtering database
     config = getconfig("./model_params.cfg")
   
-    doc_processed = open_file(path_to_data + "new_chunks.json" ) 
+    doc_processed = open_file(path_to_data + "docling_chunks.json" ) 
     chunks_list = []
 
     for doc in doc_processed:
@@ -62,7 +62,7 @@ def load_chunks():
     embeddings = HuggingFaceEmbeddings(
         model_kwargs = {'device': device},
         show_progress= True,
-        encode_kwargs = {'normalize_embeddings': bool(int(config.get('retriever','NORMALIZE')))},
+        encode_kwargs = {'normalize_embeddings': bool(int(config.get('retriever','NORMALIZE'))),},
         model_name=config.get('retriever','MODEL')
     )
     # placeholder for collection
@@ -79,11 +79,11 @@ def load_chunks():
     #        collection_name='reportsFeb2025',
     #   )
         
-    qdrant_collections['reportsFeb2025'] = Qdrant.from_documents(
+    qdrant_collections['docling'] = Qdrant.from_documents(
                 chunks_list,
                 embeddings,
                 path="/data/local_qdrant",
-                collection_name='reportsFeb2025',
+                collection_name='docling',
             )
     print(qdrant_collections)
     print("vector embeddings done")