app.py

import streamlit as st
import pandas as pd
from transformers import T5ForConditionalGeneration, T5Tokenizer
from docx import Document

# Load the generator model (FLAN-T5)
generator_tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-large")
generator_model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-large")

# Function to read DOCS files
def read_docs(file):
    doc = Document(file)
    text = "\n".join([paragraph.text for paragraph in doc.paragraphs])
    return text

# Function to process user input and generate financial statements
def generate_financial_statements(file, file_type):
    # Read the file based on its type
    if file_type == "csv":
        df = pd.read_csv(file)
        context = df.to_string()
    elif file_type == "xlsx":
        df = pd.read_excel(file)
        context = df.to_string()
    elif file_type == "docx":
        context = read_docs(file)
    else:
        st.error("Unsupported file type. Please upload a CSV, Excel, or DOCS file.")
        return None

    # Define financial statement queries
    queries = [
        "Generate a journal from the following financial data:",
        "Generate a general ledger from the following financial data:",
        "Generate an income statement from the following financial data:",
        "Generate a balance sheet from the following financial data:",
        "Generate a cash flow statement from the following financial data:"
    ]

    # Generate financial statements using the generator model
    financial_statements = {}
    for query in queries:
        # Combine query and context
        input_text = f"{query}\n{context}"

        # Generate response using the generator model
        input_ids = generator_tokenizer(input_text, return_tensors="pt", max_length=512, truncation=True).input_ids
        output = generator_model.generate(input_ids, max_length=512)
        response = generator_tokenizer.decode(output[0], skip_special_tokens=True)

        # Store the result
        financial_statements[query] = response

    return financial_statements

# Streamlit UI
st.title("Financial Statement Generator")
st.write("Upload your financial data (CSV, Excel, or DOCS) to generate journal, general ledger, income statement, balance sheet, and cash flow statement.")

# File upload
uploaded_file = st.file_uploader("Upload your file", type=["csv", "xlsx", "docx"])
if uploaded_file is not None:
    file_type = uploaded_file.name.split(".")[-1].lower()  # Ensure lowercase file type
    financial_statements = generate_financial_statements(uploaded_file, file_type)

    # Display results if financial_statements is not None
    if financial_statements is not None:
        for statement_type, statement in financial_statements.items():
            st.subheader(statement_type)
            st.write(statement)
    else:
        st.error("Failed to generate financial statements. Please check the file type and content.")