Change model to Mistral

rag.py

@@ -23,7 +23,7 @@ vector_index = os.getenv("VECTOR_INDEX")
 
 chat_llm = HuggingFaceEndpoint(
     # repo_id="HuggingFaceH4/zephyr-7b-beta",
-    repo_id="meta-llama/Meta-Llama-3-8B-Instruct",
+    repo_id="mistralai/Mistral-7B-Instruct-v0.3",
     task="text-generation",
     max_new_tokens=4096,
     do_sample=False,