Update auditqa/doc_process.py

auditqa/doc_process.py

@@ -50,4 +50,27 @@ def process_pdf():
                     doc.metadata["year"] = file[-4:]
 
                 all_documents[category].append(doc_processed)
+
+    for key, docs_processed in all_documents.items():
+    docs_processed = [item for sublist in docs_processed for item in sublist]
+    all_documents[key] = docs_processed
+
+    embeddings = HuggingFaceEmbeddings(
+        model_kwargs = {'device': device},
+        encode_kwargs = {'normalize_embeddings': True},
+        model_name="BAAI/bge-small-en-v1.5"
+    )
+
+    qdrant_collections = {}
+
+    for file,value in all_documents.items():
+    print("emebddings for:",file)
+    qdrant_collections[file] = Qdrant.from_documents(
+        value,
+        embeddings,
+        location=":memory:", 
+        collection_name=file,
+    )
+    print("done")
+    return qdrant_collections