60 lines
1.8 KiB
Python
60 lines
1.8 KiB
Python
#!/usr/bin/env python3
|
|
"""OCR a receipt image via OpenRouter and return structured info."""
|
|
import requests, json, sys, base64
|
|
|
|
API_KEY = "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"
|
|
MODEL = "google/gemini-2.5-flash-lite"
|
|
IMAGE_PATH = sys.argv[1]
|
|
|
|
with open(IMAGE_PATH, "rb") as f:
|
|
b64 = base64.b64encode(f.read()).decode()
|
|
|
|
resp = requests.post(
|
|
"https://openrouter.ai/api/v1/chat/completions",
|
|
headers={
|
|
"Authorization": f"Bearer {API_KEY}",
|
|
"Content-Type": "application/json",
|
|
},
|
|
json={
|
|
"model": MODEL,
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": [
|
|
{
|
|
"type": "text",
|
|
"text": (
|
|
"Extract from this receipt: merchant/restaurant name and total amount. "
|
|
"Return ONLY a JSON object with keys: merchant, amount. "
|
|
"No other text."
|
|
),
|
|
},
|
|
{
|
|
"type": "image_url",
|
|
"image_url": {"url": f"data:image/jpeg;base64,{b64}"},
|
|
},
|
|
],
|
|
}
|
|
],
|
|
"max_tokens": 200,
|
|
},
|
|
)
|
|
|
|
data = resp.json()
|
|
if "error" in data:
|
|
print(json.dumps({"error": data["error"]}), file=sys.stderr)
|
|
sys.exit(1)
|
|
|
|
text = data["choices"][0]["message"]["content"].strip()
|
|
# Strip markdown code fences if present
|
|
if text.startswith("```"):
|
|
text = text.split("\n", 1)[-1]
|
|
if text.endswith("```"):
|
|
text = text[:-3]
|
|
text = text.strip()
|
|
|
|
try:
|
|
result = json.loads(text)
|
|
print(json.dumps(result))
|
|
except json.JSONDecodeError:
|
|
print(json.dumps({"raw": text}))
|