Update app.py

app.py

@@ -74,17 +74,17 @@ if uploaded_file is not None:
     pdf_vectors = embedding.encode(texts)
     vector_count = len(documents)
     example_data_generator = map(lambda i: (f'id-{i}', pdf_vectors[i], {"text": texts[i]}), range(vector_count))
-    if 'ns' in index.describe_index_stats()['namespaces']:
-        index.delete(delete_all=True,namespace='ns')
+    if '( Default )' in index.describe_index_stats()['namespaces']:
+        index.delete(delete_all=True,namespace='( Default )')
     for ids_vectors_chunk in chunks(example_data_generator, batch_size=100):
-        index.upsert(vectors=ids_vectors_chunk,namespace='ns')
+        index.upsert(vectors=ids_vectors_chunk,namespace='( Default )')
 
 # Search query related context
 sample_query = st.text_input("Stellen Sie eine Frage zu dem PDF: (Ask a question related to the PDF:)")
 if st.button("Abschicken (Submit)"):
     if uploaded_file is not None and sample_query:
         query_vector = embedding.encode(sample_query).tolist()
-        query_search = index.query(vector=query_vector, top_k=5, include_metadata=True,namespace='ns')
+        query_search = index.query(vector=query_vector, top_k=5, include_metadata=True)
 
         matched_contents = [match["metadata"]["text"] for match in query_search["matches"]]