upgraded to mistral 7b v0.2

app.py

@@ -18,7 +18,8 @@ pinecone.init(
 pinecone_index = pinecone.Index('ikigai-chat')
 text_vectorizer = SentenceTransformer('all-distilroberta-v1')
 chat_bots = {
-    "Mistral 7B" : "mistralai/Mistral-7B-Instruct-v0.1",
+    "Mistral 7B v0.2" : "mistralai/Mistral-7B-Instruct-v0.2",
+    "Mistral 7B v0.1" : "mistralai/Mistral-7B-Instruct-v0.1",
     "Zephyr 7B-beta": "HuggingFaceH4/zephyr-7b-beta",
     "Zephyr 7B-alpha" : "HuggingFaceH4/zephyr-7b-alpha",
 }
@@ -72,7 +73,7 @@ def gen_augmented_prompt(prompt, top_k) :
 
 data = {
     "Attribute": ["LLM", "Text Vectorizer", "Vector Database","CPU", "System RAM"],
-    "Information": ["Mistral-7B-Instruct-v0.1","all-distilroberta-v1", "Hosted Pinecone" ,"2 vCPU", "16 GB"]
+    "Information": ["Mistral-7B-Instruct-v0.2","all-distilroberta-v1", "Hosted Pinecone" ,"2 vCPU", "16 GB"]
 }
 df = pd.DataFrame(data)
 
@@ -107,7 +108,7 @@ if "rag_enabled" not in st.session_state :
     st.session_state.rag_enabled = True
 
 if "chat_bot" not in st.session_state :
-    st.session_state.chat_bot = "Mistral 7B"
+    st.session_state.chat_bot = "Mistral 7B v0.2"
 
 with st.sidebar:
     st.markdown("# Retrieval Settings")
@@ -204,7 +205,7 @@ if prompt := st.chat_input("Chat with Ikigai Docs..."):
     len_response = (len(prompt.split()) + len(full_response.split())) * 1.25
     st.session_state["tokens_used"] = len_response + st.session_state["tokens_used"]
 
-    if st.session_state["tokens_used"] > 15000 :
+    if st.session_state["tokens_used"] > 12000 :
         st.session_state.history = st.session_state.history[-3:]
 
     st.session_state.history.append([prompt, full_response])