Spaces:

vxa8502
/

Sage

Sleeping

App Files Files Community

Sage / scripts

250 kB

Ctrl+K

Ctrl+K

1 contributor

History: 44 commits

vxa8502's picture

Declutter repo root: move DATA_CARD, drop stale gitkeeps and dead scripts/lib

d37c68b 26 days ago

__init__.py

47 Bytes
Replace EDA with production Qdrant queries 6 months ago
build_esci_overlap_query_bank.py

17.2 kB
Apply ruff format across codebase about 1 month ago
build_natural_eval_dataset.py

3.41 kB
Apply ruff format across codebase about 1 month ago
calibrate_token_threshold.py

13.2 kB
Apply ruff format across codebase about 1 month ago
demo.py

5.23 kB
Replace EDA with production Qdrant queries 6 months ago
eda.py

12.6 kB
Declutter repo root: move DATA_CARD, drop stale gitkeeps and dead scripts/lib 26 days ago
eval_gate.py

1.87 kB
Add eval gate; guard load-test against broken deployments; drop orphaned scripts about 1 month ago
evaluate_boundary_behavior.py

11.3 kB
Update and add evaluation, query-bank, and pipeline scripts about 1 month ago
evaluate_evidence_gate_holdout.py

722 Bytes
Update and add evaluation, query-bank, and pipeline scripts about 1 month ago
evaluate_retrieval_configs.py

3.58 kB
Update and add evaluation, query-bank, and pipeline scripts about 1 month ago
evaluation.py

24.2 kB
Apply ruff format across codebase about 1 month ago
explanation.py

13.6 kB
Update and add evaluation, query-bank, and pipeline scripts about 1 month ago
faithfulness.py

5.36 kB
Harden RAGAS eval: 60s timeout, checkpoint/resume, haiku model, --ragas-only flag about 1 month ago
freeze_faithfulness_seed_bundles.py

23.7 kB
Update and add evaluation, query-bank, and pipeline scripts about 1 month ago
import_esci_queries.py

4.36 kB
Apply ruff format across codebase about 1 month ago
load_test.py

29.6 kB
Update and add evaluation, query-bank, and pipeline scripts about 1 month ago
materialize_faithfulness_cases.py

28 kB
Update and add evaluation, query-bank, and pipeline scripts about 1 month ago
pipeline.py

13 kB
Update and add evaluation, query-bank, and pipeline scripts about 1 month ago
sanity_checks.py

18.7 kB
Update and add evaluation, query-bank, and pipeline scripts about 1 month ago
summary.py

20.5 kB
Apply ruff format across codebase about 1 month ago