pages/data_loading.py

import streamlit as st

def main():
    st.title("Data Loading")

    # Introduction or instruction
    st.write("Select directories and file types to process from the configured data source.")

    # Assume we have a function `list_repo_directories(repo_url)` that returns a list of directories in the repo
    # This is a placeholder list to demonstrate UI elements
    directories = ["src", "docs", "examples", "tests"]  # Example directory names

    # Directory selection
    selected_directories = st.multiselect("Select Directories", options=directories, default=directories)
    if selected_directories:
        # Save the selected directories for later processing
        st.session_state['selected_directories'] = selected_directories
        st.success(f"Selected directories: {', '.join(selected_directories)}")
    else:
        st.error("Please select at least one directory.")

    # File type filtering
    file_types = ["pdf", "txt", "md"]  # Example file types
    selected_file_types = st.multiselect("Select File Types to Include", options=file_types, default=file_types)
    if selected_file_types:
        # Save the selected file types for later processing
        st.session_state['selected_file_types'] = selected_file_types
        st.success(f"Selected file types: {', '.join(selected_file_types)}")
    else:
        st.error("Please select at least one file type.")

    # Optional: Navigation or action buttons
    # Example: Button to proceed to the next step if this page's task is completed
    if st.button("Proceed to Model Selection and Configuration"):
        # Change the page in the session state, assuming you have set up session-based navigation in app.py
        st.session_state.page = 'model_selection'

if __name__ == "__main__":
    main()