Update app.py

app.py

@@ -125,7 +125,7 @@ def fetch_context(db, model, model_name, query, template, use_compressor=True):
         #logger.info(f"User Query : {query}")
         compressed_docs = compression_retriever.get_relevant_documents(query)
         #logger.info(f"Retrieved Compressed Docs : {compressed_docs}")
-        print(f"Compressed context Generation Time: {time.time() - start_time}")")
+        print(f"Compressed context Generation Time: {time.time() - start_time}")
         return compressed_docs
     
     docs = db.max_marginal_relevance_search(query)
@@ -266,6 +266,7 @@ if __name__=="__main__":
     device = "cuda" if torch.cuda.is_available() else "cpu"
     model_name = "llama" if device=="cpu" else "mistral"
     logger.info(f"Running {model_name} model for inference on {device}")
+    print(f"Running {model_name} model for inference on {device}")
 
     # Loading and caching db and model
     #bar = st.progress(0, "Loading Database.  Please wait.")