Update app.py

app.py

@@ -3,14 +3,10 @@ import gradio as gr
 import copy
 import time
 import llama_cpp
+import ingest
 from llama_cpp import Llama
 from huggingface_hub import hf_hub_download  
 
-with open("ingest.py", "r") as file:
-    code = file.read()
-    exec(code)
-
-
 llm = Llama(
     model_path=hf_hub_download(
         repo_id=os.environ.get("REPO_ID", "TheBloke/Llama-2-7b-Chat-GGUF"),
@@ -72,4 +68,7 @@ demo = gr.ChatInterface(
     clear_btn="Clear",
 )
 demo.queue(concurrency_count=1, max_size=5)
-demo.launch()
+
+demo.launch()
+
+ingest.main()