setup for local llm

src/app.py

@@ -2,7 +2,7 @@ import os
 import gradio as gr
 from llama_index.core import Settings, ServiceContext
 from llama_index.embeddings.huggingface import HuggingFaceEmbedding
-from llama_index_llms_llama_cpp import LlamaCPP
+from llama_index.llms.llama_cpp import LlamaCPP
 from parse_tabular import create_symptom_index
 import json
 
@@ -17,10 +17,7 @@ llm = LlamaCPP(
     model_path="models/mistral-7b-instruct-v0.1.Q4_K_M.gguf",
     temperature=0.7,
     max_new_tokens=256,
-    context_window=2048,
-    # GPU configuration
-    n_gpu_layers=0,  # Increase for GPU support
-    n_threads=8      # Adjust based on your CPU
+    context_window=2048
 )
 
 # Create service context with local LLM