added import

src/app.py

@@ -1,16 +1,15 @@
 import os
 from pathlib import Path
-from huggingface_hub import snapshot_download
+from huggingface_hub import hf_hub_download
 import gradio as gr
-from llama_index.core import Settings, ServiceContext
+from llama_index.core import Settings
 from llama_index.embeddings.huggingface import HuggingFaceEmbedding
 from llama_index.llms.llama_cpp import LlamaCPP
 from parse_tabular import create_symptom_index
 import json
-import torch
 import psutil
-import subprocess
 from typing import Tuple, Dict
+import torch
 
 # Model options mapped to their requirements
 MODEL_OPTIONS = {
@@ -109,11 +108,6 @@ def ensure_model():
 # Ensure model is downloaded
 model_path = ensure_model()
 
-# Configure embeddings globally
-Settings.embed_model = HuggingFaceEmbedding(
-    model_name="sentence-transformers/all-MiniLM-L6-v2"
-)
-
 # Configure local LLM with LlamaCPP
 llm = LlamaCPP(
     model_path=model_path,
@@ -122,13 +116,13 @@ llm = LlamaCPP(
     context_window=2048
 )
 
-# Create service context with local LLM
-service_context = ServiceContext.from_defaults(
-    llm=llm,
-    embed_model=Settings.embed_model
+# Configure global settings
+Settings.llm = llm
+Settings.embed_model = HuggingFaceEmbedding(
+    model_name="sentence-transformers/all-MiniLM-L6-v2"
 )
 
-# Create the index at startup with local service context
+# Create the index at startup
 symptom_index = create_symptom_index()
 
 # --- System prompt ---