Update app.py

app.py

@@ -26,7 +26,6 @@ with st.sidebar:
 
 # Main app logic
 if "OPENAI_API_KEY" in os.environ:
-    # with st.sidebar:
     st.header('Multiple File Upload')
     uploaded_files = st.file_uploader('Upload your files', accept_multiple_files=True, type=['txt', 'pdf', 'csv', 'ppt', 'doc', 'xls', 'pptx', 'xlsx'])
 
@@ -58,72 +57,80 @@ if "OPENAI_API_KEY" in os.environ:
 
     # Process uploaded files
     if uploaded_files:
-        all_documents = []
-        for file in uploaded_files:
-            all_documents.extend(load_file(file))
+        if st.button("Process Documents"):
+            with st.spinner("Processing documents..."):
+                all_documents = []
+                for file in uploaded_files:
+                    all_documents.extend(load_file(file))
 
-        text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
-        all_splits = text_splitter.split_documents(all_documents)
+                text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+                all_splits = text_splitter.split_documents(all_documents)
 
-        # Initialize components
-        @st.cache_resource
-        def initialize_components(_all_splits):
-            dotenv.load_dotenv()
-            chat = ChatOpenAI(model="gpt-3.5-turbo-1106", temperature=0.2)
-            embeddings = OpenAIEmbeddings(model="text-embedding-ada-002")
-            vectorstore = Chroma.from_documents(documents=_all_splits, embedding=embeddings)
-            retriever = vectorstore.as_retriever(k=4)
+                # Store processed documents in session state
+                st.session_state.processed_documents = all_splits
+            st.success("Documents processed successfully!")
 
-            SYSTEM_TEMPLATE = """
-            You are an advanced AI assistant designed for document search and chatbot functionality. Your primary functions are:
+    # Initialize components
+    @st.cache_resource
+    def initialize_components():
+        dotenv.load_dotenv()
+        chat = ChatOpenAI(model="gpt-3.5-turbo-1106", temperature=0.2)
+        embeddings = OpenAIEmbeddings(model="text-embedding-ada-002")
+        return chat, embeddings
 
-            1. Process and structure multiple documents in various formats, including:
-                .txt, .pdf, .csv, .ppt, .doc, .xls, .pptx, and .xlsx
+    # Load components
+    with st.spinner("Initializing Assistant..."):
+        chat, embeddings = initialize_components()
 
-            2. Extract and organize information from these unstructured documents into a coherent, searchable format.
+    # Create vectorstore and retriever only if documents are processed
+    if 'processed_documents' in st.session_state:
+        vectorstore = Chroma.from_documents(documents=st.session_state.processed_documents, embedding=embeddings)
+        retriever = vectorstore.as_retriever(k=4)
 
-            3. Retrieve relevant information from the processed documents based on user queries.
+        SYSTEM_TEMPLATE = """
+        You are an advanced AI assistant designed for document search and chatbot functionality. Your primary functions are:
 
-            4. Act as a chatbot, engaging in conversations about the content of the documents.
+        1. Process and structure multiple documents in various formats, including:
+            .txt, .pdf, .csv, .ppt, .doc, .xls, .pptx, and .xlsx
 
-            5. Provide accurate and contextual responses to user questions, drawing solely from the information contained within the processed documents.
+        2. Extract and organize information from these unstructured documents into a coherent, searchable format.
 
-            6. If a user's question is not related to the content of the provided documents, politely inform them that you can only answer questions based on the information in the given documents.
+        3. Retrieve relevant information from the processed documents based on user queries.
 
-            7. When answering, cite the specific document or section where the information was found, if possible.
+        4. Act as a chatbot, engaging in conversations about the content of the documents.
 
-            8. If there's ambiguity in a query, ask for clarification to ensure you provide the most relevant information.
+        5. Provide accurate and contextual responses to user questions, drawing solely from the information contained within the processed documents.
 
-            9. Maintain confidentiality and do not share or discuss information from one user's documents with other users.
+        6. If a user's question is not related to the content of the provided documents, politely inform them that you can only answer questions based on the information in the given documents.
 
-            Remember, your knowledge is limited to the content of the documents you've been given to process. Do not provide information or answer questions that are outside the scope of these documents. Always strive for accuracy and relevance in your responses.
+        7. When answering, cite the specific document or section where the information was found, if possible.
 
-            <context>
-            {context}
-            </context>
+        8. If there's ambiguity in a query, ask for clarification to ensure you provide the most relevant information.
 
-            Chat History:
-            {chat_history}
-            """
+        9. Maintain confidentiality and do not share or discuss information from one user's documents with other users.
 
-            question_answering_prompt = ChatPromptTemplate.from_messages(
-                [
-                    (
-                        "system",
-                        SYSTEM_TEMPLATE,
-                    ),
-                    MessagesPlaceholder(variable_name="chat_history"),
-                    MessagesPlaceholder(variable_name="messages"),
-                ]
-            )
+        Remember, your knowledge is limited to the content of the documents you've been given to process. Do not provide information or answer questions that are outside the scope of these documents. Always strive for accuracy and relevance in your responses.
 
-            document_chain = create_stuff_documents_chain(chat, question_answering_prompt)
+        <context>
+        {context}
+        </context>
 
-            return retriever, document_chain
+        Chat History:
+        {chat_history}
+        """
 
-        # Load components
-        with st.spinner("Initializing Assistant..."):
-            retriever, document_chain = initialize_components(all_splits)
+        question_answering_prompt = ChatPromptTemplate.from_messages(
+            [
+                (
+                    "system",
+                    SYSTEM_TEMPLATE,
+                ),
+                MessagesPlaceholder(variable_name="chat_history"),
+                MessagesPlaceholder(variable_name="messages"),
+            ]
+        )
+
+        document_chain = create_stuff_documents_chain(chat, question_answering_prompt)
 
         # Initialize memory for each session
         if "memory" not in st.session_state:
@@ -176,7 +183,7 @@ if "OPENAI_API_KEY" in os.environ:
             st.session_state.memory.save_context({"input": prompt}, {"output": full_response})
 
     else:
-        st.warning("Please upload files to continue.")
+        st.warning("Please upload and process documents to start chatting.")
 
 else:
     st.warning("Please enter your OpenAI API Key in the sidebar to start the chatbot.")