Update app.py

app.py

@@ -2,7 +2,7 @@ import os
 import streamlit as st
 from langchain.embeddings.openai import OpenAIEmbeddings
 from langchain.vectorstores import Chroma
-from langchain.text_splitter import RecursiveCharacterTextSplitter  # Changed to RecursiveCharacterTextSplitter
+from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.chat_models import ChatOpenAI
 from langchain.chains import ConversationalRetrievalChain, ConversationChain
 from langchain.memory import ConversationBufferMemory
@@ -44,15 +44,12 @@ def load_texts_from_papers(papers):
             file_path = save_uploaded_file(paper)
             loader = PyPDFLoader(file_path)
             documents = loader.load()
-            
-            # Using RecursiveCharacterTextSplitter with proper encoding handling
             text_splitter = RecursiveCharacterTextSplitter(
                 chunk_size=1000,
                 chunk_overlap=200,
                 length_function=len,
                 is_separator_regex=False,
             )
-            
             texts = text_splitter.split_documents(documents)
             all_texts.extend(texts)
             os.remove(file_path)
@@ -61,8 +58,8 @@ def load_texts_from_papers(papers):
     return all_texts
 
 @st.cache_resource
-def initialize_vectorstore():
-    embedding = OpenAIEmbeddings(openai_api_key=st.session_state.api_key)
+def initialize_vectorstore(api_key):  # Added api_key parameter
+    embedding = OpenAIEmbeddings(openai_api_key=api_key)
     vectorstore = Chroma(embedding_function=embedding, persist_directory="db")
     return vectorstore
 
@@ -71,9 +68,6 @@ def main():
 
     # Get API key from sidebar
     api_key = create_sidebar()
-    
-    if api_key:
-        st.session_state.api_key = api_key
 
     st.title("Chat with PDF")
     papers = st.file_uploader("Upload PDFs", type=["pdf"], accept_multiple_files=True)
@@ -86,13 +80,13 @@ def main():
         return
 
     try:
-        vectorstore = initialize_vectorstore()
+        vectorstore = initialize_vectorstore(api_key)
         texts = load_texts_from_papers(papers) if papers else []
         
         if texts:
             vectorstore.add_documents(texts)
             qa_chain = ConversationalRetrievalChain.from_llm(
-                ChatOpenAI(temperature=0, model_name="gpt-3.5-turbo"),
+                ChatOpenAI(temperature=0, model_name="gpt-3.5-turbo", openai_api_key=api_key),  # Added api_key here
                 vectorstore.as_retriever(),
                 memory=ConversationBufferMemory(
                     memory_key="chat_history",
@@ -103,7 +97,7 @@ def main():
         else:
             memory = ConversationBufferMemory(memory_key="chat_history")
             qa_chain = ConversationChain(
-                llm=ChatOpenAI(temperature=0, model_name="gpt-3.5-turbo"),
+                llm=ChatOpenAI(temperature=0, model_name="gpt-3.5-turbo", openai_api_key=api_key),  # Added api_key here
                 memory=memory
             )