Commit Graph

3 Commits

Author SHA1 Message Date
Alejandro Gutiérrez
2206ddeff2 Initial commit - WhyRating Engine (Google Reviews Scraper) 2026-02-02 18:19:00 +00:00
Alejandro Gutiérrez
0543a08242 docs: Add Classification System & Primitives Taxonomy documentation
Comprehensive documentation covering:
- Actual production primitives (37 primitives across 5 domains)
  - O: TASTE, CRAFT, FRESHNESS, TEMPERATURE, EFFECTIVENESS, ACCURACY, CONDITION, CONSISTENCY
  - P: MANNER, COMPETENCE, ATTENTIVENESS, COMMUNICATION
  - J: SPEED, FRICTION, RELIABILITY, AVAILABILITY
  - E: CLEANLINESS, COMFORT, SAFETY, AMBIANCE, ACCESSIBILITY, DIGITAL_UX
  - V: PRICE_LEVEL, PRICE_FAIRNESS, PRICE_TRANSPARENCY, VALUE_FOR_MONEY
  - meta: HONESTY, ETHICS, PROMISES, etc. + UNMAPPED, NON_INFORMATIVE
- Classification pipeline with config resolution
- Non-informative detection (skip LLM for junk content)
- Language detection and per-language UNMAPPED tracking
- Database schema for detected_spans_v2
- Evaluation tooling and quality metrics

Note: A larger taxonomy (~150 primitives) exists in gbp_primitive_prompts.py
for future expansion. The production system uses the subset above.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-01 00:35:46 +00:00
Alejandro Gutiérrez
ee596c7969 docs(reputation-report): Add comprehensive pipeline documentation
Documents:
- Data flow and architecture
- CLI options and usage
- Output schema with examples
- Scoring formulas
- Production guardrails
- Thresholds and domain mapping
- Testing instructions

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-31 23:24:57 +00:00