Files
glimpse2/code/main.py
2026-05-27 09:30:18 -07:00

102 lines
4.3 KiB
Python
Executable File

#!/usr/bin/env python3
import base64
import json
import os
import re
import urllib.request
from dotenv import load_dotenv
_env_path = os.path.join(os.path.dirname(__file__), '.env')
if os.path.exists(_env_path):
load_dotenv(_env_path)
import openai
client = openai.OpenAI(
api_key=os.environ["OPENROUTER_API_KEY"],
base_url="https://openrouter.ai/api/v1",
)
def slurp_file(filename):
with open(filename, 'r') as file:
return file.read()
BASE_PROMPT="""You are an invoice extraction assistant. Your job is to read PDF documents and extract all invoice and credit note details into structured JSON.
DOCUMENT TYPES YOU MAY ENCOUNTER:
1. **Single Invoice** — one invoice with line items, totals, dates, etc.
2. **Credit Note** — similar to an invoice but represents a credit/refund. Extract it the same way; the total will be positive (the credit amount).
3. **Statement / Summary** — a document listing multiple invoices or credits in a table or list format. Each row or entry represents a separate invoice/credit. Extract EACH one as a separate object in the output array.
4. **Mixed** — a document containing both invoices and credits.
EXTRACTION RULES:
- Extract EVERY invoice or credit you can find. If the document is a statement listing 10 invoices, return all 10.
- **customer_identifier**: The name of the customer/buyer. Look for "Bill To", "Customer", "Sold To", or the company name at the top.
- **vendor_identifier**: The name of the vendor/seller. Look for "From", "Vendor", "Supplier", letterhead, or the company issuing the document.
- **date**: The invoice date in ISO 8601 format (YYYY-MM-DD). If multiple dates exist, use the invoice date, not the due date or statement period.
- **invoice_number**: The unique invoice or credit note number. Look for labels like "Invoice #", "Inv No", "Credit Note #", "Reference", "Doc #".
- **account_number**: The customer's account number if present. Not required — omit if not found.
- **total**: The total amount as a decimal string (e.g., "1234.56"). Use the grand total or amount due. For credits, use the credit amount as a positive number. Numbers in parentheses indicate credits — extract them as positive values.
- **explanation**: Only use this when you cannot find any valid invoices. Provide a detailed reason (e.g., "document is blank", "PDF contains only images with no extractable text", "document is a cover letter with no invoice data").
IMPORTANT:
- Do NOT skip entries because some fields are missing. Extract what you can.
- For statements/summaries, each row in an invoice table is a separate invoice entry.
- If OCR fails completely and no text can be extracted at all, return an array with one object containing only the explanation field.
- Your FINAL response must be ONLY a JSON array. Do NOT wrap it in markdown code blocks. Do NOT add any prose before or after the JSON."""
def analyze_pdf(pdf_path):
with open(pdf_path, 'rb') as f:
pdf_data = f.read()
base64_string = base64.b64encode(pdf_data).decode("utf-8")
response = client.chat.completions.create(
model="openai/gpt-4o",
messages=[
{
"role": "system",
"content": BASE_PROMPT,
},
{
"role": "user",
"content": [
{
"type": "file",
"file": {
"filename": os.path.basename(pdf_path),
"file_data": f"data:application/pdf;base64,{base64_string}",
},
},
{
"type": "text",
"text": "extract the invoice(s) and/or credit(s) details from this document.",
},
],
},
],
)
text = response.choices[0].message.content
match = re.search(r'```(?:json)?\s*\n(.*?)\n```', text, re.DOTALL)
if match:
text = match.group(1)
return text
def analyze_url(url):
with urllib.request.urlopen(url) as response:
data = response.read()
with open("/tmp/test.pdf", "wb") as f:
f.write(data)
return analyze_pdf("/tmp/test.pdf")
def handler(event, context):
print(event)
url = event['url']
print("URL IS", url)
return analyze_url(url)