Spaces:
Running
Running
File size: 4,727 Bytes
715c3e9 6f317bd 715c3e9 6f317bd 8fb878c 4d66af2 834b45f 12e951c 834b45f 4d66af2 8fb878c 4d66af2 8fb878c 834b45f 8fb878c d4d78d9 8fb878c d4d78d9 |
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 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 |
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")
st.sidebar.markdown("### 🔢 Max Tokens for LLM")
selected_token_limit = st.sidebar.radio(
"Choose max tokens:",
options=[512, 1024, 2048, 4096],
index=3,
key="token_selector_sidebar"
)
# Model selector
st.sidebar.markdown("### 🤖 Choose LLM Model")
selected_model = st.sidebar.radio(
"Which model to use?",
options=[
"meta-llama/llama-4-maverick-17b-128e-instruct",
"meta-llama/llama-4-scout-17b-16e-instruct",
"deepseek-r1-distill-llama-70b",
"llama-3.3-70b-versatile",
"gemma2-9b-it"
],
index=1,
key="model_selector_sidebar"
)
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,max_tokens=selected_token_limit,model=selected_model)
if st.button("🧠 Parse Table"):
try:
df = extract_markdown_table(table_md)
# ✅ Store it freshly (overwrite old one if it exists)
st.session_state["parsed_table_df"] = df
st.success("✅ Table parsed successfully. You can now edit it.")
except Exception as e:
st.error(f"❌ Parsing failed: {e}")
if "parsed_table_df" in st.session_state:
st.subheader("✏️ Editable Parsed Table")
edited_df = st.data_editor(
st.session_state["parsed_table_df"],
num_rows="dynamic",
use_container_width=True,
key="invoice_editor"
)
# Update session state only after editing
st.session_state["parsed_table_df"] = edited_df
# Export options
import io
buffer = io.BytesIO()
edited_df.to_excel(buffer, index=False)
buffer.seek(0)
st.download_button(
label="📥 Download Edited Table as Excel",
data=buffer,
file_name="edited_invoice_table.xlsx",
mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
)
if st.button("🔄 Reset Table"):
st.session_state.pop("parsed_table_df", None)
st.success("Table has been cleared. You can parse again.")
|