Update app.py

app.py

@@ -1,84 +1,56 @@
 import streamlit as st
-from langchain_community.document_loaders import PyPDFLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain_community.vectorstores import FAISS
 from langchain.chains import ConversationalRetrievalChain
 from langchain_openai import ChatOpenAI
-import tempfile
 import os
 
-# Configure page
-st.set_page_config(page_title="Document Q&A Bot")
+st.set_page_config(page_title="Chat with Text", layout="wide")
 
-# Initialize session state
 if "messages" not in st.session_state:
     st.session_state.messages = []
-if "chat_history" not in st.session_state:
-    st.session_state.chat_history = []
+if "vector_store" not in st.session_state:
+    st.session_state.vector_store = None
 
-# API key input
-api_key = st.sidebar.text_input("Enter OpenAI API Key", type="password")
-os.environ["OPENAI_API_KEY"] = api_key
-
-# File upload
-uploaded_file = st.sidebar.file_uploader("Upload your PDF", type="pdf")
-
-@st.cache_resource
-def process_document(file):
-    # Save uploaded file temporarily
-    with tempfile.NamedTemporaryFile(delete=False) as tmp_file:
-        tmp_file.write(file.getvalue())
-        tmp_path = tmp_file.name
-
-    # Load and process the document
-    loader = PyPDFLoader(tmp_path)
-    documents = loader.load()
-    
-    # Split text into chunks
+def create_vector_store(text):
     text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
-    chunks = text_splitter.split_documents(documents)
-    
-    # Create embeddings and vector store
+    chunks = text_splitter.create_documents([text])
     embeddings = HuggingFaceEmbeddings()
-    vector_store = FAISS.from_documents(chunks, embeddings)
-    
-    # Clean up temp file
-    os.unlink(tmp_path)
-    
-    return vector_store
+    return FAISS.from_documents(chunks, embeddings)
 
-def get_conversation_chain(vector_store):
+def get_qa_chain(vector_store):
     llm = ChatOpenAI(temperature=0)
-    chain = ConversationalRetrievalChain.from_llm(
+    return ConversationalRetrievalChain.from_llm(
         llm=llm,
         retriever=vector_store.as_retriever(),
         return_source_documents=True
     )
-    return chain
 
-# Main interface
-st.title("Document Q&A Bot")
+st.title("💬 Chat with Your Text")
 
-if uploaded_file and api_key:
-    # Process document
-    vector_store = process_document(uploaded_file)
-    chain = get_conversation_chain(vector_store)
+with st.sidebar:
+    api_key = st.text_input("OpenAI API Key", type="password")
+    if api_key:
+        os.environ["OPENAI_API_KEY"] = api_key
     
-    # Chat interface
-    user_question = st.chat_input("Ask a question about your document:")
-    if user_question:
-        response = chain({"question": user_question, "chat_history": st.session_state.chat_history})
-        
-        # Update chat history
-        st.session_state.chat_history.extend([(user_question, response["answer"])])
-        
-        # Display chat history
-        for question, answer in st.session_state.chat_history:
-            st.chat_message("user").write(question)
-            st.chat_message("assistant").write(answer)
+    text_input = st.text_area("Your Text Here", height=300)
+    if st.button("Process Text") and text_input and api_key:
+        with st.spinner("Processing text..."):
+            st.session_state.vector_store = create_vector_store(text_input)
+            st.success("Ready to chat!")
+
+if st.session_state.vector_store and api_key:
+    if question := st.chat_input("Ask your question about the text"):
+        chain = get_qa_chain(st.session_state.vector_store)
+        response = chain({"question": question, "chat_history": st.session_state.messages})
+        st.session_state.messages.append((question, response["answer"]))
+
+    for message in st.session_state.messages:
+        st.chat_message("user").write(message[0])
+        st.chat_message("assistant").write(message[1])
 
 elif not api_key:
-    st.warning("Please enter your OpenAI API key in the sidebar.")
-elif not uploaded_file:
-    st.warning("Please upload a PDF document in the sidebar.")
+    st.warning("⚠️ Please enter your OpenAI API key")
+elif not st.session_state.vector_store:
+    st.info("👈 Please input your text and process it first")