- Project number
- Project / 009
- Year
- 2025
- Category
- Data Engineering
- Status
- Completed
Aircraft Journey Summary Extractor
Turns photos of aircraft journey summary forms, including handwriting, into structured JSON using Gemini’s vision model.
- Stack
- Python · Gemini 2.0 Flash · Prompt engineering · JSON
- Tags
- Document AI · Vision · Extraction
01 /Overview
Journey summary forms are partly handwritten and full of aviation abbreviations, which traditional OCR reads poorly.
02 /What I built
- Gemini 2.0 Flash vision chosen over OCR plus NLP, AWS Textract and GPT-4 Vision, with the trade-offs documented
- Prompt with aviation expertise and abbreviations (FWD, GND, A/C, DD, MEL)
- JSON validation: required fields, integer types, clean-up of model output
- Graceful batch processing: one bad form does not block the rest
- Estimated cost of about $0.001 per form
03 /Outcome
A single-step extractor that returns validated JSON (aircraft, registration, route, crew, fuel, load, defect message) in about two to three seconds per form.
04 /What I learned
Domain context in the prompt was the biggest lever: telling the model it is a maintenance technician and listing abbreviations lifted handwriting accuracy from about 60% to about 95%.
