Update app.py

app.py

@@ -3,18 +3,20 @@ import whisper
 import numpy as np
 from langchain_community.llms import HuggingFaceEndpoint
 from langchain_community.embeddings import HuggingFaceBgeEmbeddings
-from langchain.memory import ConversationBufferMemory
-from langchain.chains import ConversationalRetrievalChain
 from langchain_community.vectorstores import FAISS
-from langchain.prompts import PromptTemplate
+from langchain_core.prompts import PromptTemplate
+from langchain_core.memory import BaseMemory
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.runnables import RunnablePassthrough
+from langchain.chains import ConversationChain
 import os
 from dotenv import load_dotenv
 import requests
 from requests.adapters import HTTPAdapter
 from requests.packages.urllib3.util.retry import Retry
-import time  # Imported time module
+import time
 from streamlit_chat import message
-from streamlit_audiorecorder import audiorecorder  # For audio recording
+from streamlit_audiorecorder import audiorecorder
 
 # Load environment variables
 load_dotenv()
@@ -26,6 +28,8 @@ if "audio_data" not in st.session_state:
     st.session_state.audio_data = None
 if "recording" not in st.session_state:
     st.session_state.recording = False
+if "text_input" not in st.session_state:
+    st.session_state.text_input = ""
 
 # Prompt template
 PROMPT_TEMPLATE = """
@@ -72,7 +76,7 @@ llm = HuggingFaceEndpoint(
 )
 
 # Setup memory and conversation chain
-memory = ConversationBufferMemory(
+memory = ConversationChain(
     memory_key="chat_history",
     return_messages=True
 )
@@ -91,14 +95,24 @@ qa_prompt = PromptTemplate(
     input_variables=["context", "chat_history", "question"]
 )
 
-conversation_chain = ConversationalRetrievalChain.from_llm(
-    llm=llm,
-    retriever=vectorstore.as_retriever(),
-    memory=memory,
-    combine_docs_chain_kwargs={"prompt": qa_prompt},
-    return_source_documents=True,
-    output_key='answer'  # Specify output_key to fix the error
-)
+def create_chain():
+    prompt = PromptTemplate(
+        template=PROMPT_TEMPLATE,
+        input_variables=["context", "chat_history", "question"]
+    )
+    
+    retriever = vectorstore.as_retriever()
+    
+    chain = (
+        {"context": retriever, "question": RunnablePassthrough()}
+        | prompt
+        | llm
+        | StrOutputParser()
+    )
+    
+    return chain
+
+conversation_chain = create_chain()
 
 def get_ai_response(user_input: str) -> str:
     max_retries = 3