Update app.py

app.py

@@ -1,7 +1,7 @@
 import os
 import streamlit as st
 from langchain.embeddings.openai import OpenAIEmbeddings
-from langchain.vectorstores import Chroma
+from langchain.vectorstores import FAISS  # Changed to FAISS for in-memory storage
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.chat_models import ChatOpenAI
 from langchain.chains import ConversationalRetrievalChain
@@ -13,8 +13,6 @@ if "messages" not in st.session_state:
     st.session_state.messages = []
 if "chain" not in st.session_state:
     st.session_state.chain = None
-if "vectorstore" not in st.session_state:  # Added vectorstore to session state
-    st.session_state.vectorstore = None
 
 def create_sidebar():
     with st.sidebar:
@@ -25,7 +23,7 @@ def create_sidebar():
         ### Tools Used
         - OpenAI
         - LangChain
-        - ChromaDB
+        - FAISS
         
         ### Steps
         1. Add API key
@@ -66,23 +64,20 @@ def process_pdfs(papers, api_key):
                 # Cleanup
                 os.remove(file_path)
             
-            # Create new vectorstore
-            st.session_state.vectorstore = Chroma.from_documents(
-                documents=all_texts,
-                embedding=embeddings,
-            )
+            # Create vectorstore
+            vectorstore = FAISS.from_documents(all_texts, embeddings)
             
             # Create chain
             st.session_state.chain = ConversationalRetrievalChain.from_llm(
                 llm=ChatOpenAI(temperature=0, model_name="gpt-3.5-turbo", openai_api_key=api_key),
-                retriever=st.session_state.vectorstore.as_retriever(
-                    search_kwargs={"k": 3}  # Retrieve top 3 most relevant chunks
+                retriever=vectorstore.as_retriever(
+                    search_kwargs={"k": 3}
                 ),
                 memory=ConversationBufferMemory(
                     memory_key="chat_history",
                     return_messages=True,
                 ),
-                return_source_documents=True,  # Include source documents in response
+                return_source_documents=True,
             )
             
             st.success(f"Processed {len(papers)} PDF(s) successfully!")