Update auditqa/doc_process.py

auditqa/doc_process.py

@@ -6,7 +6,7 @@ from torch import cuda
 from langchain_community.document_loaders import PyMuPDFLoader
 from langchain_community.embeddings import HuggingFaceEmbeddings, HuggingFaceInferenceAPIEmbeddings
 from langchain_community.vectorstores import Qdrant
-#from qdrant_client import QdrantClient
+from qdrant_client import QdrantClient
 from auditqa.reports import files, report_list
 device = 'cuda' if cuda.is_available() else 'cpu'
 
@@ -93,15 +93,18 @@ def process_pdf():
     print("done")
     return qdrant_collections
 
-def get_local_qdrant(client, name): 
+def get_local_qdrant(): 
     print(client.get_collections())
+    qdrant_collections = {}
     embeddings = HuggingFaceEmbeddings(
         model_kwargs = {'device': device},
         encode_kwargs = {'normalize_embeddings': True},
         model_name="BAAI/bge-small-en-v1.5")
-
-    vectorstore = Qdrant(client=client, collection_name=name, embeddings=embeddings, )
-    return vectorstore
+    list_ = ['Consolidated','District','Ministry','allreports']
+    for val in list_:
+        client = QdrantClient(path="./data/{val}") 
+        qdrant_collections[val] = Qdrant(client=client, collection_name=val, embeddings=embeddings, )
+    return qdrant_collections