Index of every page on this site: llms.txt
Avatar for nvidia-nemo

nvidia-nemo

9 skills2 repos 7.5k Synced

nvidia-nemo/guardrails

NeMo Guardrails is an open-source library for applying programmable safety and security controls to LLM and agentic applications.

5 skills 7.5k
npx skilld add nvidia-nemo/guardrails --all
  • Step-by-step contribution guide for adding a new rail to nemoguardrails/library/: manifest, actions returning RailOutcome, config schema, flows, HTTP rules for vendor backends, Python package requirements, unit and recorded tests, docs and examples. Use when implementing, scaffolding, or reviewing a new built-in or vendor guardrail integration. Trigger keywords - add rail, new rail, library rail, vendor integration, guardrail integration, RailManifest, RailOutcome, RailRequirements, optional_dependencies, rail.py, guardrail catalog, third-party rail.

  • Helps developers create a NeMo Guardrails configuration for an LLM application. Use when users want to build, scaffold, configure, test, or iterate on input, output, retrieval, dialog, execution, Colang, or catalog-based guardrails. Trigger keywords - create guardrails, build guardrails, scaffold config, write rails, create config.yml, add input rails, add output rails, Colang flow, guardrails config, test guardrails.

  • Routes NVIDIA NeMo Guardrails library product-usage questions to the canonical documentation. Use when users ask how to install, configure, integrate, evaluate, observe, deploy, troubleshoot, or use the NVIDIA NeMo Guardrails library. Trigger keywords - install guardrails, configure rails, guardrail catalog, Colang, Python API, LangChain, LangGraph, server, evaluate guardrails, tracing, metrics, Docker, troubleshooting.

  • Decides when a code change requires a recorded/VCR test, whether a test belongs in tests/recorded/ or the plain unit suite under tests/, and how to structure it in either place. Use when adding, reviewing, or relocating tests that involve LLM calls, streaming, cassettes, snapshots, or provider traffic, and when changing provider clients, public API output shapes, or model-calling rails. Trigger keywords - recorded test, cassette, VCR, replay, snapshot test, tests/recorded, record-cassettes, fake cassette, TestChat, FakeLLMModel.

  • Review a pull request that adds or modifies a rail in nemoguardrails/library/ (built-in or vendor guardrail integration). Runs the mechanical gates first, then judgment dimensions tests cannot check (privacy honesty, retry semantics, fail-closed behavior, dialect coverage, docs accuracy), then a security pass. Use when reviewing rail-integration PRs, vendor integration contributions, or changes under nemoguardrails/library/. Trigger keywords - review rail PR, rail integration review, vendor integration PR, library rail review, guardrail contribution.

nvidia-nemo/switchyard

Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimization.

4 skills 3.7k
npx skilld add nvidia-nemo/switchyard --all
  • Build or publish nemo-switchyard Python distributions through the repository's GitHub Actions workflow. Use when asked to build a development wheel, cut a Python release, publish to PyPI, create a release tag, or debug .github/workflows/publish.yml.

  • Edit or debug the published Switchyard MkDocs site. Use for docs pages, mkdocs.yml navigation, mkdocs_hooks.py source links, strict build failures, local previews, or .github/workflows/docs.yml.

  • Review Switchyard Rust changes for correctness and maintainability. Use for pull requests or diffs touching crates, PyO3 bindings, async runtime behavior, streaming, protocol types, translation, algorithms, or LLM clients.

  • Select or debug Switchyard validation and GitHub CI. Use when asked which tests to run, whether a change is ready, why a CI job failed, how to reproduce CI, or whether live provider tests are appropriate.

Skills published by nvidia-nemo. Checked GitHub just now