| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| director_ai-1.7.0-py3-none-any.whl | 2026-03-01 | 97.9 kB | |
| director_ai-1.7.0.tar.gz | 2026-03-01 | 156.9 kB | |
| README.md | 2026-03-01 | 971 Bytes | |
| v1.7.0 -- Domain Presets, Halt Evidence, Pluggable Scorer source code.tar.gz | 2026-03-01 | 1.4 MB | |
| v1.7.0 -- Domain Presets, Halt Evidence, Pluggable Scorer source code.zip | 2026-03-01 | 1.6 MB | |
| Totals: 5 Items | 3.3 MB | 0 | |
What's New
- Domain presets:
DirectorConfig.from_profile("medical"|"finance"|"legal"|"creative"|"customer_support")with tuned thresholds, NLI/reranker flags, and logic/fact weights - Structured halt evidence:
stream_tokens(scorer=...)populatesHaltEvidencewith top-K contradicting chunks, NLI scores, and suggested action - Pluggable scorer backend:
CoherenceScorer(scorer_backend="deberta"|"onnx"|"minicheck", onnx_path=...) - Batched MiniCheck: native list API for batch NLI scoring
- False-halt rate: 0.0% on 20 good passages (heuristic mode), asserted in CI
- Competitor one-pager: summary comparison table (Director-AI vs NeMo vs Lynx vs GuardrailsAI vs SelfCheckGPT)
- Repo hygiene: dependabot, ROADMAP, updated SECURITY versions, copyright headers, all GH Actions bumped to latest
Install
:::bash
pip install director-ai==1.7.0
Full Changelog
https://github.com/anulum/director-ai/blob/main/CHANGELOG.md