Hugging Face's logo

Spaces:
RameshJ
/
Invoices_to_Table
Sleeping

App Files Community
Invoices_to_Table
File size: 3,181 Bytes 
715c3e9
 
6f317bd
715c3e9
 
 
 
6f317bd
8fb878c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
 
import os

# Force Streamlit to use a writable config directory
os.environ["XDG_CONFIG_HOME"] = "/tmp"
os.environ["STREAMLIT_HOME"] = "/tmp"
os.makedirs("/tmp/.streamlit", exist_ok=True)

import streamlit as st
import pandas as pd
from ocr_llm_utils import run_ocr_with_gcv, extract_table_from_text, extract_markdown_table
import tempfile
from PIL import Image
import io

# Set wide layout
st.set_page_config(page_title="Invoice Processor", layout="wide")

# Sidebar navigation
st.sidebar.title("Navigation")
page = st.sidebar.radio("Go to", ["Charges Incurred", "Invoices to Table"])

# Charges Incurred page (placeholder)
if page == "Charges Incurred":
    st.title("Charges Incurred")
    
    col1, col2 = st.columns([1, 1])  # col1 = processing, col2 = image
    with col1:
        st.subheader("1️⃣ Google Cloud Vision OCR Cost")
        st.image("assets/gcv_ocr_costs.png", caption="GCV OCR Pricing", use_container_width=True)
    with col2:
        st.subheader("2️⃣ Groq API Cost (LLaMA 4 Scout)")
        st.image("assets/groq_api_costs.png", caption="Groq LLM Pricing", use_container_width=True)

    st.subheader("3️⃣ Combined Cost Summary")
    st.image("assets/cost_summary_from_chatgpt.png", caption="Total Estimated Cost for 1000 Invoices", use_container_width=True)

# Invoices to Table
elif page == "Invoices to Table":
    st.title("Invoice Table Extractor")

    uploaded_file = st.file_uploader("📤 Upload Invoice Image", type=["jpg", "jpeg", "png"])
    col1, col2 = st.columns([1.5, 1])  # col1 = processing, col2 = image

    if uploaded_file is not None:
        # Save image temporarily
        with tempfile.NamedTemporaryFile(delete=False) as temp_file:
            temp_file.write(uploaded_file.read())
            image_path = temp_file.name

        with col2:
            st.subheader("🖼️ Invoice Preview")
            st.image(uploaded_file, use_container_width=True)

        with col1:
            with st.spinner("🔍 Running OCR..."):
                text = run_ocr_with_gcv(image_path)

            with st.expander("📝 Extracted Text"):
                st.text_area("OCR Text", text, height=300)

            with st.spinner("📊 Extracting Table..."):
                table_md = extract_table_from_text(text)

            if st.button("🧠 Parse Table"):
                try:
                    df = extract_markdown_table(table_md)
                    st.success("✅ Table parsed successfully")

                    # Preview table
                    st.subheader("📋 Table Preview")
                    st.dataframe(df)

                    # Download as Excel
                    excel_buffer = io.BytesIO()
                    df.to_excel(excel_buffer, index=False)
                    excel_buffer.seek(0)

                    st.download_button(
                        label="📥 Download Table as Excel",
                        data=excel_buffer,
                        file_name="invoice_table.xlsx",
                        mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
                    )
                except Exception as e:
                    st.error(f"❌ {e}")