app.py

import streamlit as st
import subprocess
import camelot

# Function to install dependencies
def install_dependencies():
    try:
        import plotly
    except ImportError:
        st.write("Installing plotly...")
        subprocess.check_call(["pip", "install", "plotly", "camelot-py[cv]"])
        st.write("plotly installed successfully.")

    # Install other dependencies if needed
    required_libraries = ["torch", "transformers", "pdfplumber", "camelot-py[cv]", "pandas"]
    for library in required_libraries:
        try:
            __import__(library)
        except ImportError:
            st.write(f"Installing {library}...")
            subprocess.check_call(["pip", "install", library])
            st.write(f"{library} installed successfully.")

# Install dependencies
install_dependencies()

# Title and Description
st.title("Automated Datasheet Summarizer with Table Parsing")
st.write("Upload a datasheet PDF or enter a component name to get simplified summaries, key specs, and visual insights.")

# Input Options
input_type = st.radio("Select Input Type:", ["Upload PDF", "Enter Component Name"])

if input_type == "Upload PDF":
    uploaded_file = st.file_uploader("Upload a Datasheet PDF", type=["pdf"])
    if uploaded_file is not None:
        try:
            # Parse tables using Camelot
            tables = camelot.read_pdf(uploaded_file, pages="all")
            if len(tables) > 0:
                for i, table in enumerate(tables):
                    st.write(f"Table {i+1}")
                    st.dataframe(table.df)
            else:
                st.warning("No tables found in the PDF.")
        except Exception as e:
            st.error(f"Error parsing tables with Camelot: {e}")

elif input_type == "Enter Component Name":
    component_name = st.text_input("Enter Component Name")
    if component_name and st.button("Search and Summarize"):
        st.error("Component search functionality is under development.")

# Footer
st.markdown("---")
st.markdown("**Note:** This tool is in beta. Accuracy of the generated summaries and parsed tables depends on the quality of the datasheet.")