mainchange cgpt 1

app.py

@@ -2,12 +2,12 @@ import streamlit as st
 import os
 from langchain.vectorstores import Chroma
 from langchain.embeddings import HuggingFaceBgeEmbeddings
-from langchain_together import Together  # Updated import
+from langchain_together import Together
 from langchain import hub
 from operator import itemgetter
-from langchain.schema import RunnableParallel, format_document  # Updated import paths
+from langchain.schema import RunnableParallel, format_document
 from typing import List, Tuple
-from langchain.chains import LLMChain, RetrievalQA, ConversationalRetrievalChain
+from langchain.chains import LLMChain, ConversationalRetrievalChain
 from langchain.schema.output_parser import StrOutputParser
 from langchain.memory import StreamlitChatMessageHistory, ConversationBufferMemory, ConversationSummaryMemory
 from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder, PromptTemplate
@@ -22,10 +22,6 @@ embedding_function = HuggingFaceBgeEmbeddings(
     encode_kwargs=encode_kwargs
 )
 
-# Load the ChromaDB vector store
-# persist_directory="./mrcpchromadb/"
-# vectordb = Chroma(persist_directory=persist_directory, embedding_function=embedding_function, collection_name="mrcppassmednotes")
-
 # Load the LLM
 llm = Together(
     model="mistralai/Mixtral-8x22B-Instruct-v0.1",
@@ -122,7 +118,7 @@ def app():
     }
     conversational_qa_chain = _inputs | _context | ANSWER_PROMPT | llm
 
-    st.header("Hello Doctor, How can I help?")
+    st.header("Ask Away!")
     for message in st.session_state.messages:
         with st.chat_message(message["role"]):
             st.write(message["content"])