Update app.py

app.py

@@ -5,6 +5,7 @@ from dotenv import load_dotenv
 from llama_index.embeddings.huggingface import HuggingFaceEmbedding
 from llama_index.core import Settings
 import os
+from transformers import AutoTokenizer, AutoModelForCausalLM
 import base64
 
 # Load environment variables
@@ -12,8 +13,8 @@ load_dotenv()
 
 # Configure the Llama index settings
 Settings.llm = HuggingFaceInferenceAPI(
-    model_name="google/gemma-1.1-7b-it",
-    tokenizer_name="google/gemma-1.1-7b-it",
+    model_name= AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
+    tokenizer_name = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
     context_window=3900,
     token=os.getenv("HF_TOKEN"),
     max_new_tokens=1000,