This release introduces enhancements to elevate your AI development experience. Key highlights of this release include the introduction of a Content Safety Module, which aids in the integration of different content safety models, a new Migration Tool that facilitates migration from Colang 1.0 or Colang 2-alpha to the latest version of Colang 2 by handling a significant part of the conversion, support for the NeMo Guardrails standard library in Colang 2.x, added support for Rails Exception Handling within both Colang 1.0 and 2.x, and the addition of a Debugging Tool for Colang 2.x.

This update also includes numerous bug fixes and performance improvements contributed by our community.

What's Changed

• bug fix by @saradiazdelser in https://github.com/NVIDIA/NeMo-Guardrails/pull/392
• Fixed broken links by @buvnswrn in https://github.com/NVIDIA/NeMo-Guardrails/pull/670
• Feature/colang 2/standard library updates by @schuellc-nvidia in https://github.com/NVIDIA/NeMo-Guardrails/pull/669
• Fix: hallucination-check by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/679
• Add the relevant_chunks to the gpt-3.5 general prompt template. by @drazvan in https://github.com/NVIDIA/NeMo-Guardrails/pull/678
• Feature/colang 2/flow event bugfix by @schuellc-nvidia in https://github.com/NVIDIA/NeMo-Guardrails/pull/672
• Feat/content safety by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/674
• feat(embeddings): add search threshold to BasicEmbeddingsIndex by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/620
• Doc/llm per task by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/676
• Check that flow names don't start with keywords by @schuellc-nvidia in https://github.com/NVIDIA/NeMo-Guardrails/pull/637
• Feature/colang 2/deactivate keyword by @schuellc-nvidia in https://github.com/NVIDIA/NeMo-Guardrails/pull/673
• Fix/nvidia ai endpoints streaming by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/654
• Fix/issue 183 non openai hallucination check by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/681
• feat(llmrails): Add serialization support for LLMRails by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/627
• New Evaluation Tooling by @drazvan in https://github.com/NVIDIA/NeMo-Guardrails/pull/677
• fix: streamlit import error by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/686
• Fix/ issue 589 override prompt self check facts by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/621
• Initial work on support for exceptions. by @drazvan in https://github.com/NVIDIA/NeMo-Guardrails/pull/384
• refactor(api): Update Pydantic validators by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/688
• Feat/migration tool by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/624
• Refactor/migrate standard library by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/625
• Fix/output parser deprecation warning by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/691
• Colang 2.0 - Guardrails Library by @drazvan in https://github.com/NVIDIA/NeMo-Guardrails/pull/689
• Fix/langchain_nvidia_ai_endpoints patch by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/697
• Revert back the abc bot Colang v1 and move the v2 version to separate config. by @drazvan in https://github.com/NVIDIA/NeMo-Guardrails/pull/698
• Fix/colang 2 runtime issues by @schuellc-nvidia in https://github.com/NVIDIA/NeMo-Guardrails/pull/699
• fix: change 'send event' to 'send' by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/701
• Fix a small bug in the generate_flow action for Colang 2. by @drazvan in https://github.com/NVIDIA/NeMo-Guardrails/pull/710
• Fix/output parser validation by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/704
• Feaure/colang 2/expose bot config by @schuellc-nvidia in https://github.com/NVIDIA/NeMo-Guardrails/pull/703
• Fix: pass config and kwargs to passthrough_fn runnable for issue 665 by @vpr1995 in https://github.com/NVIDIA/NeMo-Guardrails/pull/695
• [Feature] Add Cleanlab's Trustworthiness Score by @AshishSardana in https://github.com/NVIDIA/NeMo-Guardrails/pull/572
• Feature/colang 2/llm chat interface by @schuellc-nvidia in https://github.com/NVIDIA/NeMo-Guardrails/pull/709
• Feat/add relevant chunk support to colang 2 by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/708
• Fix/rails exception migration by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/705
• fix(migration): replace hyphens and apostrophes by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/725
• Fix/llm flow continuation generation by @schuellc-nvidia in https://github.com/NVIDIA/NeMo-Guardrails/pull/724
• Fix/cli server command by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/723
• Fix/cache embeddings filesystem by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/722
• feat(library): Migrate cleanlab to colang 2 and add exception handling by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/714
• Docs/community cleanlab by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/713
• Feature/colang debug library by @schuellc-nvidia in https://github.com/NVIDIA/NeMo-Guardrails/pull/560
• Feature/extend debug cli by @schuellc-nvidia in https://github.com/NVIDIA/NeMo-Guardrails/pull/717
• Feature/colang 2/interaction loop priorties by @schuellc-nvidia in https://github.com/NVIDIA/NeMo-Guardrails/pull/712
• Fix the detection of the triggering flow id by @drazvan in https://github.com/NVIDIA/NeMo-Guardrails/pull/728
• Add support for tags in the Eval UI. by @drazvan in https://github.com/NVIDIA/NeMo-Guardrails/pull/731
• feat: Add support for embeddings only with search threshold by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/733
• Fix: Process all outgoing events by @sklinglernv in https://github.com/NVIDIA/NeMo-Guardrails/pull/732
• Fix the scene form and choice flows in the Colang 2 standard library by @sklinglernv in https://github.com/NVIDIA/NeMo-Guardrails/pull/741
• Feat/embedding only support colang 2 by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/737
• docs: Add note for rails exception handling in Colang 2.x by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/744
• feat: add relevant chunks prompts by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/745
• Fix multiline LLM output syntax error for dynamic flow generation by @radinshayanfar in https://github.com/NVIDIA/NeMo-Guardrails/pull/748
• Feature/gcp moderation by @kauabh in https://github.com/NVIDIA/NeMo-Guardrails/pull/727
• Feat/migration tool sample converstaion syntax conversion by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/764
• chore: Upgrade langchain-core and jinja by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/766
• Update changelog by @Pouyanpi in https://github.com/NVIDIA/NeMo-Guardrails/pull/769

New Contributors

• @saradiazdelser made their first contribution in https://github.com/NVIDIA/NeMo-Guardrails/pull/392
• @buvnswrn made their first contribution in https://github.com/NVIDIA/NeMo-Guardrails/pull/670
• @vpr1995 made their first contribution in https://github.com/NVIDIA/NeMo-Guardrails/pull/695
• @AshishSardana made their first contribution in https://github.com/NVIDIA/NeMo-Guardrails/pull/572
• @sklinglernv made their first contribution in https://github.com/NVIDIA/NeMo-Guardrails/pull/732
• @radinshayanfar made their first contribution in https://github.com/NVIDIA/NeMo-Guardrails/pull/748
• @kauabh made their first contribution in https://github.com/NVIDIA/NeMo-Guardrails/pull/727

Full Changelog: https://github.com/NVIDIA/NeMo-Guardrails/compare/v0.9.1.1...v0.10.0