Update app.py

app.py

@@ -147,15 +147,10 @@ def create_vector_db(final_items):
     import torch
     from llama_cpp import Llama
 
-    llm = Llama(
-        model_path = hf_hub_download(
-            repo_id = os.environ.get("REPO_ID", "xzlinuxmodels/ollama3.1"),
-            filename = os.environ.get("MODEL_FILE", "unsloth.BF16.gguf"),
-        ),
-        n_ctx = 2048,
-        n_gpu_layers = 10,
-    ) 
-    
+    llm = Llama.from_pretrained(
+            repo_id = "xzlinuxmodels/ollama3.1",
+            filename = "unsloth.BF16.gguf",
+        )
     for item in final_items:
         prompt = f"""
         Summarize the following segment of Antimony in a clear and concise manner: