튜토리얼: 이미지, 검사와 이미지를 보는 심사 모델로 평가하기

python3 -m venv .venv
. .venv/bin/activate
pip install 'oloproof[media]'

oloproof init --example media product-thumbnails
cd product-thumbnails

product-thumbnails/
  app.py                              the thumbnailer under test (baseline)
  app_v2.py                           the candidate change
  judge_server.py                     a stand-in vision judge speaking the OpenAI API on 127.0.0.1
  rubrics/caption_names_colour.md     the judge's rubric
  oloproof.yaml                       the suite
  release.yaml                        rules for a run
  compare.yaml                        a rule for a comparison
  data/products.jsonl                 20 cases
  photos/                             the 20 product photos the cases name
  make_photos.py                      how the photos were drawn
  labels/reviewer_verdicts.csv        one person's verdicts on the baseline's captions
  fill_labels.py                      copies those verdicts into a labelling sheet

# app.py (excerpt)
@system(name="thumbnailer", version=VERSION, records=("media/v1",))
def describe(case: dict[str, Any]) -> dict[str, str]:
    photo_path = HERE / case["photo"]
    photo = Image.open(photo_path).convert("RGB")
    thumb = photo.copy()
    thumb.thumbnail((320, 320))
    out = HERE / "thumbs" / VERSION / photo_path.name
    out.parent.mkdir(parents=True, exist_ok=True)
    thumb.save(out)
    given = media_file(photo_path, role="input")
    made = media_file(out, width=thumb.width, height=thumb.height)
    current_case().media([given, made])
    centre = photo.getpixel((photo.width // 2, photo.height // 2))
    return {"caption": f"A {colour_name(centre)} product."}

{"id": "p03", "input": {"photo": "photos/p03.png"}, "expected": {"photo": "photos/p03.png", "colour": "yellow", "shape": "triangle"}}

evaluators:
  # The catalogue's limits, measured from the thumbnail's bytes: a web format, at most 256 by
  # 256 pixels, at most 50 kB.
  - type: media_check
    criterion: thumbnail_fits
    kind: image
    formats: [png, jpeg, webp]
    max_width: 256
    max_height: 256
    max_bytes: 50000
  # The thumbnail is still the product's photo: a perceptual hash within 10 of 64 bits.
  - type: image_matches_reference
    criterion: same_photo
    reference_field: photo
    max_distance: 10
  # The caption, judged by a model that sees the thumbnail.
  - type: rubric_judge
    criterion: caption_names_colour
    provider: openai_compatible
    model: stand-in-vision
    base_url: http://127.0.0.1:8798/v1
    rubric_file: rubrics/caption_names_colour.md
    media: output

python judge_server.py --port 8798

version: 1
confidence_level: 0.95
block_on: [FAIL, INSUFFICIENT_EVIDENCE, MANUAL_REVIEW]
require_validated_evaluators: true
rules:
  - id: thumbnails-fit
    metric: thumbnail_fits
    kind: observed_count
    max_failures: 0
  - id: same-photo
    metric: same_photo
    kind: observed_count
    max_failures: 0
  - id: caption-floor
    metric: caption_names_colour
    min: 0.80

oloproof run

Gate: BLOCK (exit 1)
│ thumbnails-fit │ thumbnail_fits       │ FAIL                  │ observed_failures_exceed_limit   │
│ same-photo     │ same_photo           │ PASS                  │ observed_failures_within_limit   │
│ caption-floor  │ caption_names_colour │ INSUFFICIENT_EVIDENCE │ evaluator_not_validated          │
│ thumbnail_fits       │ 0.0%     │ [0.0%, 16.9%]   │ 0 / 20 observed · 0 missing · 0 excluded  │
│ same_photo           │ 100.0%   │ [83.1%, 100.0%] │ 20 / 20 observed · 0 missing · 0 excluded │
│ caption_names_colour │ 60.0%    │ [36.0%, 80.9%]  │ 12 / 20 observed · 0 missing · 0 excluded │

oloproof inspect RUN_ID --failures

p03
  output: {"caption": "A white product."}
  thumbnail_fits: failed
    measured: p03.png: width 320 px is above 256 px
  caption_names_colour: failed
    judge text, not verified: the product is yellow; the caption says 'a white product.'

oloproof labels export RUN_ID --criterion caption_names_colour --sample 20 --local --out sample.csv
python fill_labels.py sample.csv
oloproof labels import sample.csv

oloproof evaluators list
oloproof evaluators validate EVALUATOR_ID --by alice

caption_names_colour: sha256:53605dd6... is now VALIDATED
  agreement 100.0% [83.1%, 100.0%] · 20 of 20 labelled cases agreed · 0 labelled but not judged · kappa 1.000

oloproof gate RUN_ID --policy release.yaml

thumbnails-fit: FAIL (observed_failures_exceed_limit)
same-photo: PASS (observed_failures_within_limit)
caption-floor: INSUFFICIENT_EVIDENCE (interval_overlaps_threshold)
Gate: BLOCK (exit 1)

oloproof run

Gate: ALLOW (exit 0)
│ thumbnails-fit │ thumbnail_fits       │ PASS  │ observed_failures_within_limit │
│ same-photo     │ same_photo           │ PASS  │ observed_failures_within_limit │
│ caption-floor  │ caption_names_colour │ PASS  │ lower_bound_meets_minimum      │

oloproof compare CANDIDATE_RUN_ID BASELINE_RUN_ID --policy compare.yaml

thumbnail_fits: +100.0 points [+52.9, +100.0] · 20 paired · 0 missing · 0 excluded
caption_names_colour: +40.0 points [+1.8, +72.7] · 20 paired · 0 missing · 0 excluded
  captions-better  caption_names_colour  superiority  PASS  difference_above_zero

# live_judge.yaml
type: rubric_judge
criterion: caption_names_colour
provider: openai_compatible
model: qwen2.5vl
base_url: http://localhost:11434/v1
rubric_file: rubrics/caption_names_colour.md
media: output
timeout_s: 300

oloproof evaluators try live_judge.yaml