Update app.py

app.py

@@ -59,6 +59,7 @@ def main():
     text_path = st.sidebar.text_input("Text File Path", "text.txt")
     quantization = st.sidebar.checkbox("Enable Quantization (4-bit)", value=False)
     show_context = st.sidebar.checkbox("Show Retrieved Context", value=False)
+    offload_dir = st.sidebar.text_input("Offload Directory", "/tmp")  # Default to /tmp
 
     # Load the model with the above configuration
     rag_chain = load_model(
@@ -74,6 +75,7 @@ def main():
         hf_token=None,  # If you're not using HF API token, set it to None
         max_new_tokens=max_new_tokens,
         quantization=quantization,
+        offload_dir=offload_dir,  # Pass offload dir here
     )
     
     st.write("### Enter your question:")