Update app.py

app.py

@@ -37,6 +37,7 @@ import spaces  # For GPU
 import transformers  # LLM Loading
 import langchain_community.vectorstores  # Vectorstore for publications
 import langchain_huggingface  # Embeddings
+import llama_cpp
 
 # The number of publications to retrieve for the prompt
 PUBLICATIONS_TO_RETRIEVE = 5