v0.8.2
版本发布时间: 2024-04-02 04:52:04
NVIDIA/NeMo-Guardrails最新发布版本:v0.10.1(2024-10-03 02:38:56)
This minor release adds support for integrating NeMo Guardrails with NVIDIA AI Endpoints and Vertex AI. It also introduces the research overview page, which guides the development of future guardrails. Last but not least, it adds another round of improvements for Colang 2.0 and multiple getting-started examples.
Colang 2.0 is the next version of Colang and will replace Colang 1.0 in a future release. It adds a more powerful flow engine, improved syntax, multi-modal support, parallelism for actions and flows, a standard library of flows, and more. This release still targets alpha testers and does not include the new documentation, which will be added in 0.9.0. Colang 2.0 and 1.0 will be supported side-by-side until Colang 1.0 is deprecated and removed.
What's Changed
Added
- #402 Integrate Vertex AI Models into Guardrails by @aishwaryap.
- #403 Add support for NVIDIA AI Endpoints by @patriciapampanelli
- #396 Docs/examples nv ai foundation models.
- #438 Add research roadmap documentation.
Changed
-
#389 Expose the
verbose
parameter throughRunnableRails
by @d-mariano. -
#415 Enable
print(...)
andlog(...)
. - #389 Expose verbose arg in RunnableRails by @d-mariano.
- #414 Feature/colang march release.
- #416 Refactor and improve the verbose/debug mode.
- #418 Feature/colang flow context sharing.
- #425 Feature/colang meta decorator.
- #427 Feature/colang single flow activation.
- #426 Feature/colang 2.0 tutorial.
- #428 Feature/Standard library and examples.
- #431 Feature/colang various improvements.
- #433 Feature/Colang 2.0 improvements: generate_async support, stateful API.
Fixed
- #412 Fix #411 - explain rails not working for chat models.
- #413 Typo fix: Comment in llm_flows.co by @habanoz.
- #420 Fix typo for hallucination message.
New Contributors
- @aishwaryap made their first contribution in https://github.com/NVIDIA/NeMo-Guardrails/pull/402
- @patriciapampanelli made their first contribution in https://github.com/NVIDIA/NeMo-Guardrails/pull/403
- @habanoz made their first contribution in https://github.com/NVIDIA/NeMo-Guardrails/pull/413
- @d-mariano made their first contribution in https://github.com/NVIDIA/NeMo-Guardrails/pull/389
Full Changelog: https://github.com/NVIDIA/NeMo-Guardrails/compare/v0.8.1...v0.9.0