Update app.py

app.py

@@ -32,6 +32,7 @@ from llama_index.core.node_parser import SentenceSplitter
 from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline, BitsAndBytesConfig
 from huggingface_hub import login
 import qdrant_client
+from llama_index.core.query_engine import RetrieverQueryEngine
 
 # Configure logging
 logging.basicConfig(
@@ -165,9 +166,9 @@ reranker = SentenceTransformerRerank(
     device="cuda" if torch.cuda.is_available() else "cpu"
 )
 
-query_engine = index.as_query_engine(
+query_engine = RetrieverQueryEngine(
     retriever=hybrid_retriever,
-    node_postprocessors=[reranker],
+    node_postprocessors=[reranker]
 )
 
 # --- CELL 6: Load & Quantize LLaMA Model ---