Changed the LLM to Phi3

rag.py

@@ -8,7 +8,7 @@ from transformers import AutoTokenizer , AutoModelForCausalLM
 class RAG:
 
     def __init__(self):
-        self.model_id = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
+        self.model_id = "microsoft/Phi-3-mini-128k-instruct"
         self.device = "cuda" if torch.cuda.is_available() else "cpu"
 
         self.embedding_model_name = "all-mpnet-base-v2"