Commit graph

7 commits

Author SHA1 Message Date
cbe8c0f03e feat(benchmark): wire EmbeddingKNNAdapter into MODEL_REGISTRY; add embed_model config
- Add embed_model: nomic-embed-text to config/label_tool.yaml (local, gitignored)
- Add # embed_model: commented example to config/label_tool.yaml.example
- Add pyyaml>=6.0 to requirements.txt (explicit dep for _resolve_urls yaml.safe_load)
- Add params assertion to test_embed_knn_nomic_registry_entry
2026-05-05 14:05:45 -07:00
5df33b0f41 feat(benchmark): wire EmbeddingKNNAdapter into MODEL_REGISTRY as embed-knn-nomic 2026-05-05 12:43:48 -07:00
41584de5df fix(benchmark): guard empty exemplars, warn on malformed JSON in build_exemplars_from_jsonl 2026-05-05 12:41:46 -07:00
1d4c07e4a0 feat(benchmark): add build_exemplars_from_jsonl() for k-NN seed 2026-05-05 11:43:12 -07:00
d1a36bfd63 fix(avocet): guard discover_finetuned_models against malformed/incomplete training_info.json 2026-03-15 15:18:13 -07:00
df37a8e16d feat(avocet): auto-discover fine-tuned models in benchmark harness 2026-03-15 11:59:13 -07:00
d68754d432 feat: initial avocet repo — email classifier training tool
Scrape → Store → Process pipeline for building email classifier
benchmark data across the CircuitForge menagerie.

- app/label_tool.py — Streamlit card-stack UI, multi-account IMAP fetch,
  6-bucket labeling, undo/skip, keyboard shortcuts (1-6/S/U)
- scripts/classifier_adapters.py — ZeroShotAdapter (+ two_pass),
  GLiClassAdapter, RerankerAdapter; ABC with lazy model loading
- scripts/benchmark_classifier.py — 13-model registry, --score,
  --compare, --list-models, --export-db; uses label_tool.yaml for IMAP
- tests/ — 20 tests, all passing, zero model downloads required
- config/label_tool.yaml.example — multi-account IMAP template
- data/email_score.jsonl.example — sample labeled data for CI

Labels: interview_scheduled, offer_received, rejected,
        positive_response, survey_received, neutral
2026-02-27 14:07:38 -08:00