234 lines
8.8 KiB
Python
234 lines
8.8 KiB
Python
|
import gradio as gr
|
||
|
|
import requests
|
||
|
|
import json
|
||
|
|
import re
|
||
|
|
import os
|
||
|
|
|
||
|
|
# ── Config ─────────────────────────────────────────────────────
|
||
|
|
MODEL_ID = "ratulsur/multi-format-finance-parser"
|
||
|
|
API_URL = f"https://api-inference.huggingface.co/models/{MODEL_ID}"
|
||
|
|
HF_TOKEN = os.environ.get("HF_TOKEN", "")
|
||
|
|
|
||
|
|
SYSTEM_PROMPT = """You are a production financial document parser.
|
||
|
|
Given raw text from any financial document, output ONLY a single valid JSON object.
|
||
|
|
Schema: {document_type, vendor, client, date (YYYY-MM-DD), due_date, document_id,
|
||
|
|
currency, subtotal, tax_amount, tax_rate_pct, total_amount,
|
||
|
|
line_items:[{description,quantity,unit_price,amount}], payment_terms, notes, metadata}.
|
||
|
|
All monetary values must be floats. Unknown fields → null. No explanation."""
|
||
|
|
|
||
|
|
# ── Inference ──────────────────────────────────────────────────
|
||
|
|
def call_api(text: str) -> dict:
|
||
|
|
prompt = (
|
||
|
|
f"<|im_start|>system\n{SYSTEM_PROMPT}<|im_end|>\n"
|
||
|
|
f"<|im_start|>user\nParse this financial document:\n\n{text}<|im_end|>\n"
|
||
|
|
f"<|im_start|>assistant\n"
|
||
|
|
)
|
||
|
|
headers = {
|
||
|
|
"Authorization": f"Bearer {HF_TOKEN}",
|
||
|
|
"Content-Type": "application/json",
|
||
|
|
}
|
||
|
|
payload = {
|
||
|
|
"inputs": prompt,
|
||
|
|
"parameters": {
|
||
|
|
"max_new_tokens": 512,
|
||
|
|
"temperature": 0.05,
|
||
|
|
"return_full_text": False,
|
||
|
|
"do_sample": False,
|
||
|
|
},
|
||
|
|
}
|
||
|
|
resp = requests.post(API_URL, headers=headers, json=payload, timeout=120)
|
||
|
|
resp.raise_for_status()
|
||
|
|
raw = resp.json()[0]["generated_text"].strip()
|
||
|
|
raw = re.sub(r"```json\s*|```\s*", "", raw).strip()
|
||
|
|
|
||
|
|
# JSON repair heuristics
|
||
|
|
try:
|
||
|
|
return json.loads(raw)
|
||
|
|
except json.JSONDecodeError:
|
||
|
|
raw = (raw
|
||
|
|
.replace("'", '"')
|
||
|
|
.replace("None", "null")
|
||
|
|
.replace("True", "true")
|
||
|
|
.replace("False", "false")
|
||
|
|
.replace(",\n}", "\n}")
|
||
|
|
.replace(",\n]", "\n]"))
|
||
|
|
match = re.search(r"\{.*\}", raw, re.DOTALL)
|
||
|
|
try:
|
||
|
|
return json.loads(match.group() if match else raw)
|
||
|
|
except Exception:
|
||
|
|
return {"error": "Could not parse model output", "raw": raw}
|
||
|
|
|
||
|
|
|
||
|
|
# ── Main processing function ───────────────────────────────────
|
||
|
|
def process(text_input: str, doc_hint: str):
|
||
|
|
if not text_input.strip():
|
||
|
|
return "⚠️ Please paste some document text.", ""
|
||
|
|
|
||
|
|
try:
|
||
|
|
text = text_input.strip()
|
||
|
|
if doc_hint and doc_hint != "Auto-detect":
|
||
|
|
text = f"[Document type: {doc_hint}]\n\n{text}"
|
||
|
|
|
||
|
|
result = call_api(text)
|
||
|
|
|
||
|
|
# Build summary
|
||
|
|
summary = []
|
||
|
|
if result.get("error"):
|
||
|
|
return f"❌ Error: {result['error']}", json.dumps(result, indent=2)
|
||
|
|
if result.get("document_type"):
|
||
|
|
summary.append(f"**Type:** {result['document_type']}")
|
||
|
|
if result.get("vendor"):
|
||
|
|
summary.append(f"**Vendor:** {result['vendor']}")
|
||
|
|
if result.get("client"):
|
||
|
|
summary.append(f"**Client:** {result['client']}")
|
||
|
|
if result.get("date"):
|
||
|
|
summary.append(f"**Date:** {result['date']}")
|
||
|
|
if result.get("due_date"):
|
||
|
|
summary.append(f"**Due date:** {result['due_date']}")
|
||
|
|
if result.get("document_id"):
|
||
|
|
summary.append(f"**Document ID:** {result['document_id']}")
|
||
|
|
if result.get("currency") and result.get("total_amount") is not None:
|
||
|
|
summary.append(f"**Total:** {result['currency']} {result['total_amount']:,.2f}")
|
||
|
|
if result.get("tax_amount") is not None:
|
||
|
|
summary.append(f"**Tax:** {result.get('currency','')} {result['tax_amount']:,.2f}")
|
||
|
|
if result.get("line_items"):
|
||
|
|
summary.append(f"**Line items:** {len(result['line_items'])}")
|
||
|
|
if result.get("payment_terms"):
|
||
|
|
summary.append(f"**Payment terms:** {result['payment_terms']}")
|
||
|
|
|
||
|
|
return "\n\n".join(summary), json.dumps(result, indent=2, ensure_ascii=False)
|
||
|
|
|
||
|
|
except requests.exceptions.Timeout:
|
||
|
|
return "⚠️ Model is loading, please wait 20 seconds and try again.", ""
|
||
|
|
except requests.exceptions.HTTPError as e:
|
||
|
|
return f"❌ API Error: {e}", ""
|
||
|
|
except Exception as e:
|
||
|
|
return f"❌ Error: {e}", ""
|
||
|
|
|
||
|
|
|
||
|
|
# ── Examples ───────────────────────────────────────────────────
|
||
|
|
EXAMPLES = [
|
||
|
|
["""INVOICE
|
||
|
|
Vendor: Tata Consultancy Services Ltd.
|
||
|
|
Invoice No: TCS-2024-8821
|
||
|
|
Date: 2024-11-15
|
||
|
|
Due Date: 2024-12-15
|
||
|
|
Bill To: Reliance Industries Ltd.
|
||
|
|
|
||
|
|
Service: Cloud Infrastructure Management (Oct 2024) INR 42,500.00
|
||
|
|
Service: SAP Integration Support INR 18,000.00
|
||
|
|
GST @ 18%: INR 10,890.00
|
||
|
|
TOTAL DUE: INR 71,390.00
|
||
|
|
Payment Terms: Net 30""", "Invoice"],
|
||
|
|
|
||
|
|
["""SAP FI - VENDOR PAYMENT REPORT
|
||
|
|
Company Code: 1000 | Fiscal Year: 2024
|
||
|
|
Run Date: 2024-09-30
|
||
|
|
|
||
|
|
|DocNo |Vendor |Amount |Curr|Status |
|
||
|
|
|----------|--------------------|--------------|----|--------|
|
||
|
|
|1900045621|Wipro Limited | 4,25,000.00 |INR |Open |
|
||
|
|
|1900045622|HCL Technologies | 2,10,500.00 |INR |Cleared |
|
||
|
|
|1900045623|Infosys BPO | 8,75,200.00 |INR |Open |
|
||
|
|
|
||
|
|
Total: 15,10,700.00 INR""", "SAP Report"],
|
||
|
|
|
||
|
|
["""INCOME STATEMENT
|
||
|
|
Reliance Industries Ltd.
|
||
|
|
Period ending: 2024-09-30
|
||
|
|
(in INR)
|
||
|
|
|
||
|
|
Revenue: 50,000,000.00
|
||
|
|
Cost of Revenue: (22,000,000.00)
|
||
|
|
Gross Profit: 28,000,000.00
|
||
|
|
Operating Expenses: (12,000,000.00)
|
||
|
|
EBIT: 16,000,000.00
|
||
|
|
Income Tax 25%: (4,000,000.00)
|
||
|
|
Net Income: 12,000,000.00""", "Income Statement"],
|
||
|
|
|
||
|
|
["""PURCHASE ORDER
|
||
|
|
PO Number: PO-2024-00456
|
||
|
|
Date: 2024-10-01
|
||
|
|
Vendor: Amazon Web Services India
|
||
|
|
Ship To: HDFC Bank Ltd., Mumbai
|
||
|
|
|
||
|
|
Item 1: EC2 Reserved Instances (1yr) USD 12,000.00
|
||
|
|
Item 2: S3 Storage 50TB USD 1,800.00
|
||
|
|
Item 3: RDS Multi-AZ USD 4,200.00
|
||
|
|
Subtotal: USD 18,000.00
|
||
|
|
Tax: USD 0.00
|
||
|
|
Total: USD 18,000.00
|
||
|
|
Payment Terms: Net 45""", "Purchase Order"],
|
||
|
|
]
|
||
|
|
|
||
|
|
|
||
|
|
# ── UI ─────────────────────────────────────────────────────────
|
||
|
|
with gr.Blocks(
|
||
|
|
title="Multi-Format Finance Parser",
|
||
|
|
theme=gr.themes.Soft(),
|
||
|
|
css=".json-output { font-family: monospace; font-size: 13px; }"
|
||
|
|
) as demo:
|
||
|
|
|
||
|
|
gr.Markdown("""
|
||
|
|
# 🏦 Multi-Format Finance Document Parser
|
||
|
|
**Production-grade** financial document extraction → structured JSON.
|
||
|
|
|
||
|
|
Supports: **Invoice · SAP Report · Income Statement · Bank Statement · Purchase Order · SQL results**
|
||
|
|
|
||
|
|
*Fine-tuned Qwen2.5-7B-Instruct · QLoRA 4-bit NF4 · Trained on CORD-v2 + synthetic finance data*
|
||
|
|
""")
|
||
|
|
|
||
|
|
with gr.Row():
|
||
|
|
with gr.Column(scale=1):
|
||
|
|
text_in = gr.Textbox(
|
||
|
|
label="Paste document text",
|
||
|
|
lines=16,
|
||
|
|
placeholder="Paste your invoice, SAP export, income statement, or any financial document here...",
|
||
|
|
)
|
||
|
|
hint_in = gr.Dropdown(
|
||
|
|
choices=[
|
||
|
|
"Auto-detect",
|
||
|
|
"Invoice",
|
||
|
|
"SAP Report",
|
||
|
|
"Balance Sheet",
|
||
|
|
"Income Statement",
|
||
|
|
"Bank Statement",
|
||
|
|
"Purchase Order",
|
||
|
|
"SQL Result",
|
||
|
|
],
|
||
|
|
value="Auto-detect",
|
||
|
|
label="Document type hint (optional)",
|
||
|
|
)
|
||
|
|
parse_btn = gr.Button("Parse Document", variant="primary", size="lg")
|
||
|
|
|
||
|
|
with gr.Column(scale=1):
|
||
|
|
summary_out = gr.Markdown(label="Summary")
|
||
|
|
json_out = gr.Code(
|
||
|
|
label="Structured JSON output",
|
||
|
|
language="json",
|
||
|
|
lines=18,
|
||
|
|
)
|
||
|
|
|
||
|
|
gr.Markdown("### Try an example")
|
||
|
|
gr.Examples(
|
||
|
|
examples=EXAMPLES,
|
||
|
|
inputs=[text_in, hint_in],
|
||
|
|
label="Click any example to load it",
|
||
|
|
)
|
||
|
|
|
||
|
|
gr.Markdown("""
|
||
|
|
---
|
||
|
|
**Model:** [ratulsur/multi-format-finance-parser](https://huggingface.co/ratulsur/multi-format-finance-parser)
|
||
|
|
**Training:** QLoRA (4-bit NF4 double quantization) on Qwen2.5-7B-Instruct
|
||
|
|
**Dataset:** CORD-v2 receipts + synthetic invoices, SAP reports, income statements
|
||
|
|
""")
|
||
|
|
|
||
|
|
parse_btn.click(
|
||
|
|
fn=process,
|
||
|
|
inputs=[text_in, hint_in],
|
||
|
|
outputs=[summary_out, json_out],
|
||
|
|
)
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
demo.launch()
|