connor/assistant-skills
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

remove OCR, use today's date and ask user for merchant

Browse source
This commit is contained in:
Connor Rhodes 2026-04-29 02:02:15 +00:00
parent 6d6baa79fa
commit f18d6b25ad
2 changed files with 5 additions and 74 deletions
Download patch file Download diff file Expand all files Collapse all files

19
log-work-expense/SKILL.md
View file

@ -16,23 +16,15 @@ Log receipt images and expense details into the `wip.work_expenses` collection i
## Steps
1. **Extract receipt info** — If the user sent an image, run the OCR script to read the merchant and amount:
1. **Upload the receipt image to S2** — If the user provided an image, upload it to S2 and get the public URL. If they only provided a file or no image, skip this step.
```bash
uv run --with requests python3 scripts/ocr_receipt.py /path/to/image.jpg
```
The script is located at `~/notes/skills/log-work-expense/scripts/ocr_receipt.py`. It returns JSON with `merchant` and `amount` fields. If they only provided text, use that.
2. **Upload the receipt image to S2** — If the user provided an image, upload it to S2 and get the public URL. If they only provided a file or no image, skip this step.
3. **Insert into MongoDB** — Insert a document into `wip.work_expenses` with this structure:
2. **Insert into MongoDB** — Insert a document into `wip.work_expenses` with this structure:
```json
{
"file": "https://s2.connorrhodes.com/agent/{sha256}.{ext}",
"date": "YYYY-MM-DD",
"merchant": "Name of the merchant from the receipt (e.g. Starbucks, 7 Eleven)",
"merchant": "Name of the merchant",
"description": "Context the user provided about the expense",
"status": "todo"
}
@ -40,14 +32,13 @@ The script is located at `~/notes/skills/log-work-expense/scripts/ocr_receipt.py
- **file**: The S2 URL of the uploaded receipt image. Omit if no image was provided.
- **date**: Always use today's date (the date you receive the message), formatted as YYYY-MM-DD.
- **merchant**: Extracted from the OCR result.
- **merchant**: Ask the user if not stated.
- **description**: What the user told you about the expense (e.g. "travel meal during LTISD onsite"). If they didn't provide context, ask.
- **status**: Always set to `"todo"` when inserting.
4. **Confirm** — Reply with a brief confirmation showing what was logged (date, merchant, and file link if applicable).
3. **Confirm** — Reply with a brief confirmation showing what was logged (date, merchant, and file link if applicable).
## Notes
- Use `uv run --with pymongo` for MongoDB scripts.
- Use the S2 upload endpoint from TOOLS.md for file uploads.
- If the user sends a receipt without context, log what you can read from the image and note that context is pending.

60
log-work-expense/scripts/ocr_receipt.py
View file

@ -1,60 +0,0 @@
#!/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}))