no problems, local llm setup

src/app.py

@@ -1,8 +1,8 @@
 import os
 import gradio as gr
 from llama_index.core import Settings, ServiceContext
-from llama_index_embeddings_huggingface import HuggingFaceEmbedding
-from llama_index.llms import HuggingFaceLLM
+from llama_index.embeddings.huggingface import HuggingFaceEmbedding
+from llama_index.llms.huggingface import HuggingFaceLLM
 from ctransformers import AutoModelForCausalLM
 from parse_tabular import create_symptom_index
 import json
@@ -23,8 +23,7 @@ model = AutoModelForCausalLM.from_pretrained(
 llm = HuggingFaceLLM(
     model=model,
     context_window=2048,
-    max_new_tokens=256,
-    temperature=0.7
+    max_new_tokens=256
 )
 
 # Create service context with local LLM
@@ -34,7 +33,7 @@ service_context = ServiceContext.from_defaults(
 )
 
 # Create the index at startup with local service context
-symptom_index = create_symptom_index(service_context=service_context)
+symptom_index = create_symptom_index()
 
 # --- System prompt ---
 SYSTEM_PROMPT = """