mainfile cgpt 7

app.py

@@ -1,14 +1,15 @@
 import streamlit as st
 import os
 import asyncio
-from langchain.vectorstores import Chroma
-from langchain.embeddings import HuggingFaceBgeEmbeddings
+from langchain_community.vectorstores import Chroma
+from langchain_community.embeddings import HuggingFaceBgeEmbeddings
 from langchain_together import Together
 from langchain import hub
 from operator import itemgetter
 from langchain.schema import format_document
 from langchain.prompts import ChatPromptTemplate, PromptTemplate
-from langchain.memory import StreamlitChatMessageHistory, ConversationBufferMemory
+from langchain_community.chat_message_histories import StreamlitChatMessageHistory
+from langchain.memory import ConversationBufferMemory
 from langchain_core.runnables import RunnableLambda, RunnableParallel, RunnablePassthrough
 
 # Load the embedding function
@@ -68,13 +69,13 @@ def store_chat_history(role: str, content: str):
 def create_conversational_qa_chain(retriever, condense_llm, answer_llm):
     condense_question_chain = RunnableLambda(
         lambda x: {"chat_history": chistory, "question": x['question']}
-    ) | CONDENSE_QUESTION_PROMPT | RunnableLambda(lambda x: {"standalone_question": x})
+    ) | CONDENSE_QUESTION_PROMPT | RunnableLambda(lambda x: {"standalone_question": x['standalone_question']})
 
     retrieval_chain = RunnableLambda(
-        lambda x: x['standalone_question']
+        lambda x: {"standalone_question": x['standalone_question']}
     ) | retriever | _combine_documents
 
-    answer_chain = ANSWER_PROMPT | answer_llm
+    answer_chain = ANSWER_PROMPT | RunnableLambda(lambda x: {"context": x, "question": x['standalone_question']}) | answer_llm
 
     return RunnableParallel(
         condense_question=condense_question_chain,