Update app.py

app.py

@@ -1,6 +1,8 @@
 import gradio as gr
 from gpt4all import GPT4All
 from huggingface_hub import hf_hub_download
+import faiss
+from langchain_community.embeddings import HuggingFaceEmbeddings
 
 title = "Mistral-7B-Instruct-GGUF Run On CPU-Basic Free Hardware"
 
@@ -30,6 +32,14 @@ model._is_chat_session_activated = False
 
 max_new_tokens = 2048
 
+model_kwargs = {'device': 'cpu'}
+encode_kwargs = {'normalize_embeddings': False}
+embeddings = HuggingFaceEmbeddings(
+    
+    model_kwargs=model_kwargs,
+    encode_kwargs=encode_kwargs
+)
+
 def generater(message, history, temperature, top_p, top_k):
     prompt = "<s>"
     for user_message, assistant_message in history: