cclohmar/NextExpense
1
0
Fork 0
Code Issues Pull requests Projects Releases 1 Packages Wiki Activity Actions
NextExpense/internal
History
cclohmar fecf4af8a2 fix: AI receipt extraction now uses OCR (Tesseract) + LLM (DeepSeek) pipeline 
- Problem: deepseek-v4-flash is text-only, cannot process base64 images - hallucinated fake data
- Solution: Two-step pipeline that actually extracts real data:
  1. Tesseract OCR extracts raw text from the receipt image
  2. DeepSeek v4 parses the OCR text into structured JSON
- Benefits: works with any image format, fast, accurate, no hallucinated data
- Properly handles HEIC/HEIF via heif-convert before OCR
2026-05-30 12:00:40 +00:00
..
ai fix: AI receipt extraction now uses OCR (Tesseract) + LLM (DeepSeek) pipeline 2026-05-30 12:00:40 +00:00
auth chore: initial commit — ExpenseFlow AI-Powered Expense Tracker 2026-05-29 19:43:30 +00:00
database chore: initial commit — ExpenseFlow AI-Powered Expense Tracker 2026-05-29 19:43:30 +00:00
email chore: initial commit — ExpenseFlow AI-Powered Expense Tracker 2026-05-29 19:43:30 +00:00
handlers fix: support HEIC/HEIF photos from iPhone + broaden accepted image formats 2026-05-30 11:54:31 +00:00
utils chore: initial commit — ExpenseFlow AI-Powered Expense Tracker 2026-05-29 19:43:30 +00:00