> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/guardrails/v0.22.0/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/guardrails/_mcp/server.

# NVIDIA NeMo Guardrails Library

> Add programmable guardrails to LLM applications with an open-source Python library.

The NeMo Guardrails library is an open-source Python package for adding programmable guardrails to LLM-based applications. It intercepts inputs and outputs, applies configurable safety checks, and blocks or modifies content based on defined policies.

## About the NeMo Guardrails Library

Learn about the library and its capabilities in the following sections.

#### [Overview](/about-nemo-guardrails-library/overview)

Add programmable guardrails to LLM applications with this open-source Python library.

Concept

#### [Guardrail Types](/about-nemo-guardrails-library/rail-types)

Apply input, retrieval, dialog, execution, and output rails to protect LLM applications.

Concept

#### [How It Works](/about-nemo-guardrails-library/how-it-works)

High level explanation of how Guardrails works.

Concept

#### [Supported LLMs](/about-nemo-guardrails-library/supported-llms)

Connect to NVIDIA NIM, OpenAI, Azure, Anthropic, HuggingFace, and LangChain providers.

Reference

## Get Started

Use the following guides to get started with the NeMo Guardrails library and browse the catalog of pre-built guardrails.

#### [Installation](/get-started/installation-guide)

Install NeMo Guardrails with pip, configure your environment, and verify the installation.

Get Started

#### [Tutorials](/get-started/tutorials)

Follow hands-on tutorials to deploy Nemotron Content Safety, Nemotron Topic Control, and Nemotron Jailbreak Detect

Tutorial

#### [Guardrail Catalog](/configure-guardrails/guardrail-catalog)

Reference for pre-built guardrails including content safety, jailbreak detection, topic control, PII handling, agentic security, and third party APIs.

Reference

## Next Steps

Once you've completed the get-started tutorials, explore the following areas to deepen your understanding.

#### [About Configuring Guardrails](/configure-guardrails/configure-rails)

Configure YAML files, Colang flows, custom actions, and other components to control LLM behavior.

Concept

#### [About Running Guardrailed Inference](/run-guardrailed-inference/run-rails)

Run guardrailed inference using the Python API or Guardrails API server.

Get Started

#### [Evaluate](/evaluation/evaluate-guardrails)

Measure accuracy and performance of dialog, fact-checking, moderation, and hallucination rails.

How To

#### [Logging](/observability/logging)

Debug guardrails with verbose mode, explain method, and generation log options.

How To

#### [Observability](/observability/observability)

Use OpenTelemetry to trace requests, forward Python logs, and emit metrics for end-to-end visibility into guardrails.

How To

#### [Deployment Options](/more-deployment-options/deployment)

Deploy guardrails using the local API server, Docker containers, or production microservices.

How To

#### [LangChain Frameworks](/integration-with-third-party-libraries/langchain)

Integrate NeMo Guardrails with LangChain chains, runnables, and LangGraph workflows.

How To

> Add programmable guardrails to LLM applications with an open-source Python library.

## Docs

- [Overview of the NeMo Guardrails Library](https://docs.nvidia.com/nemo/guardrails/v0.22.0/about-nemo-guardrails-library/overview.md): Add programmable guardrails to LLM applications with this open-source Python library.
- [Architecture Overview](https://docs.nvidia.com/nemo/guardrails/v0.22.0/about-nemo-guardrails-library/how-it-works.md): High level explanation of how Guardrails works.
- [Guardrail Types](https://docs.nvidia.com/nemo/guardrails/v0.22.0/about-nemo-guardrails-library/rail-types.md): Apply input, retrieval, dialog, execution, and output rails to protect LLM applications.
- [Supported LLMs](https://docs.nvidia.com/nemo/guardrails/v0.22.0/about-nemo-guardrails-library/supported-llms.md): Connect to NVIDIA NIM, OpenAI, Azure, Anthropic, Hugging Face, and LangChain providers.
- [Release Notes](https://docs.nvidia.com/nemo/guardrails/v0.22.0/about-nemo-guardrails-library/release-notes.md): Review new features, breaking changes, and fixed issues for each release.
- [Install the NeMo Guardrails Library](https://docs.nvidia.com/nemo/guardrails/v0.22.0/get-started/installation-guide.md): Install NeMo Guardrails with pip, configure your environment, and verify the installation.
- [NeMo Guardrails Tutorials](https://docs.nvidia.com/nemo/guardrails/v0.22.0/get-started/tutorials.md): Follow hands-on tutorials to deploy Nemotron Content Safety, Nemotron Topic Control, and Nemotron Jailbreak Detect NIMs.
- [Check Harmful Content with Nemotron Content Safety NIM](https://docs.nvidia.com/nemo/guardrails/v0.22.0/get-started/tutorials/nemotron-safety-guard-deployment.md): Check text inputs and outputs for harmful content using Nemotron Content Safety NIM.
- [Deploy Nemotron Content Safety Reasoning 4B](https://docs.nvidia.com/nemo/guardrails/v0.22.0/get-started/tutorials/nemotron-content-safety-reasoning-deployment.md): Deploy Nemotron-Content-Safety-Reasoning-4B for customizable content safety with reasoning traces.
- [Restrict Topics with Llama 3.1 NemoGuard 8B TopicControl NIM](https://docs.nvidia.com/nemo/guardrails/v0.22.0/get-started/tutorials/nemoguard-topiccontrol-deployment.md): Restrict conversations to allowed topics using Llama 3.1 NemoGuard 8B TopicControl NIM.
- [Detect Jailbreak Attempts with NVIDIA NemoGuard JailbreakDetect NIM](https://docs.nvidia.com/nemo/guardrails/v0.22.0/get-started/tutorials/nemoguard-jailbreakdetect-deployment.md): Detect and block adversarial prompts and jailbreak attempts using NemoGuard JailbreakDetect NIM.
- [Use Jailbreak Detection Heuristics](https://docs.nvidia.com/nemo/guardrails/v0.22.0/get-started/tutorials/jailbreak-detection-heuristics.md): Add jailbreak detection heuristics to the ABC bot configuration and test malicious and benign prompts.
- [Add Multimodal Content Safety Using a Vision Model](https://docs.nvidia.com/nemo/guardrails/v0.22.0/get-started/tutorials/multimodal.md): Add safety checks to images and text using a vision model as LLM-as-a-Judge.
- [Integrate Guardrails into Your Application](https://docs.nvidia.com/nemo/guardrails/v0.22.0/get-started/integrate-into-application.md): Add guardrails to existing applications using the Python SDK, the HTTP API, or the optional LangChain integration.
- [About Configuring Guardrails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/configure-rails.md): Configure YAML files, Colang flows, custom actions, and other components to control LLM behavior.
- [NeMo Guardrails Library Configuration Overview](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/overview.md): Learn to write config.yml, Colang flows, and custom actions for guardrails.
- [Pre-Configuration Checklist](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/before-configuration.md): Prepare LLM endpoints, NemoGuard NIMs, and knowledge base documents before configuration.
- [Configuring YAML File](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/yaml-schema.md): Define models, guardrails, prompts, and tracing settings in the config.yml file.
- [Model Configuration for NeMo Guardrails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/yaml-schema/model-configuration.md): Configure LLM engines, embedding models, and task-specific models in config.yml.
- [Guardrails Configuration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/yaml-schema/guardrails-configuration.md): Configure input, output, dialog, retrieval, and execution rails in config.yml to control LLM behavior.
- [Prompt Configuration for the NVIDIA NeMo Guardrails Library](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/yaml-schema/prompt-configuration.md): Customize prompts for self-check, fact-checking, and intent generation tasks.
- [Tracing Configuration for NeMo Guardrails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/yaml-schema/tracing-configuration.md): Configure FileSystem and OpenTelemetry tracing adapters to monitor guardrails.
- [Streaming Configuration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/yaml-schema/streaming.md): Configure streaming for LLM token generation and output rail processing in config.yml.
- [Streaming LLM Responses in Real-Time](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/yaml-schema/streaming/global-streaming.md): Enable and use streaming mode for LLM responses in real-time in the NeMo Guardrails library.
- [Output Rail Streaming Configuration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/yaml-schema/streaming/output-rail-streaming.md): Configure how output rails process streamed tokens in chunked mode.
- [Configuration YAML Schema Reference](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/configuration-reference.md): Reference for all config.yml options including models, rails, prompts, and advanced settings.
- [Guardrail Catalog](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog.md): Reference for pre-built guardrails including content safety, jailbreak detection, topic control, PII handling, agentic security, and third party APIs.
- [Content Safety](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/content-safety.md): Reference for pre-built content safety guardrails for protecting against violence, criminal activity, hate speech, sexually explicit content, and similar areas.
- [Jailbreak Protection](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/jailbreak-protection.md): Reference for jailbreak protection guardrails that help prevent adversarial attempts from bypassing safety measures.
- [Topic Control](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/topic-control.md): Reference for topic control guardrails that ensure conversations stay within predefined subject boundaries.
- [PII Detection](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/pii-detection.md): Reference for PII detection guardrails that protect user privacy by detecting and masking sensitive data.
- [Agentic Security](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/agentic-security.md): Reference for agentic security guardrails that protect LLM-based agents using tools and interacting with external systems.
- [Hallucinations & Fact-Checking](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/fact-checking.md): Reference for fact-checking and hallucination detection guardrails that ensure LLM output is grounded in evidence.
- [LLM Self-Check](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/self-check.md): Reference for LLM self-checking guardrails that prompt the LLM to perform input checking, output checking, or fact-checking.
- [Third-Party APIs](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/third-party.md): Reference for third-party API integrations that connect with managed services for guardrail use cases.
- [ActiveFence Integration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/third-party/active-fence.md)
- [AlignScore Integration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/third-party/alignscore.md)
- [AutoAlign Integration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/third-party/auto-align.md)
- [Cisco AI Defense Integration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/third-party/ai-defense.md)
- [Clavata Integration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/third-party/clavata.md)
- [Cleanlab Integration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/third-party/cleanlab.md)
- [CrowdStrike AIDR integration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/third-party/crowdstrike-aidr.md)
- [Fiddler Guardrails Integration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/third-party/fiddler.md)
- [GCP Text Moderation Integration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/third-party/gcp-text-moderations.md)
- [GLiNER Integration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/third-party/gliner.md)
- [GuardrailsAI Integration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/third-party/guardrails-ai.md)
- [Llama-Guard Integration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/third-party/llama-guard.md)
- [Pangea AI Guard integration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/third-party/pangea.md)
- [Patronus Evaluate API Integration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/third-party/patronus-evaluate-api.md)
- [Patronus Lynx Integration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/third-party/patronus-lynx.md)
- [PolicyAI Integration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/third-party/policyai.md)
- [Presidio Integration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/third-party/presidio.md)
- [Private AI Integration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/third-party/privateai.md)
- [Prompt Security Integration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/third-party/prompt-security.md)
- [Regular Expression Detection Integration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/third-party/regex.md)
- [Trend Micro Vision One AI Application Security](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/guardrail-catalog/third-party/trend-micro.md)
- [Configuring Custom Actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/actions.md): Create Python actions to extend guardrails with external APIs and validation logic.
- [Creating Custom Actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/actions/creating-actions.md): Create custom actions using the @action decorator to integrate Python logic.
- [Built-in Actions Reference](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/actions/built-in-actions.md): Reference for default actions included in the NeMo Guardrails library.
- [Action Parameters Reference](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/actions/action-parameters.md): Reference for special parameters like context, llm, and config provided to actions.
- [Registering Custom Actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/actions/registering-actions.md): Register custom actions via actions.py, LLMRails.register_action(), or config.py.
- [Configuring Custom Initialization](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/custom-initialization.md): Use config.py to register custom LLM providers, embedding providers, and shared resources at startup.
- [The Init Function for NeMo Guardrails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/custom-initialization/init-function.md): Define the init() function to initialize resources and register action parameters at startup.
- [Custom LLM Providers for NeMo Guardrails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/custom-initialization/custom-llm-providers.md): Register LangChain BaseLLM and BaseChatModel providers under the LangChain framework path (requires NEMOGUARDRAILS_LLM_FRAMEWORK=langchain).
- [Custom LLM Models for the NVIDIA NeMo Guardrails library](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/custom-initialization/custom-llm-model.md): Implement the LLMModel protocol to connect a non-OpenAI-compatible backend to the NVIDIA NeMo Guardrails library without depending on LangChain.
- [Testing Your Guardrails Configuration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/custom-initialization/testing-your-config.md): Write fast, deterministic tests for your NeMo Guardrails configuration using the public testing surface.
- [Custom LLM Frameworks for the NVIDIA NeMo Guardrails library](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/custom-initialization/custom-llm-framework.md): Replace the LLM framework layer to connect LiteLLM, an in-house orchestrator, or any non-default LLM stack to the NVIDIA NeMo Guardrails library.
- [Custom Embedding Providers for NeMo Guardrails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/custom-initialization/custom-embedding-providers.md): Register custom embedding providers for vector similarity search in NeMo Guardrails.
- [Custom Configuration Data for NeMo Guardrails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/custom-initialization/custom-data.md): Pass and access custom data from config.yml in your initialization code and actions.
- [Colang Guide](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang.md): Learn Colang, the event-driven language for defining guardrails flows and bot behavior.
- [Colang 2.0 Guide](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2.md): Learn Colang 2.0 syntax, concepts, migration guidance, tutorials, and language reference topics.
- [What's Changed](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/whats-changed.md): This guide provides a non-comprehensive overview of the most important changes in Colang 2.0.
- [Migrating from Colang 1 to Colang 2](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/migration-guide.md): Convert Colang 1.0 configurations to Colang 2.x using the nemoguardrails convert tool.
- [Getting Started with Colang 2.0](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/getting-started.md): Build Colang 2.0 guardrails step by step, from Hello World to LLM and multimodal flows.
- [Hello World](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/getting-started/hello-world.md): This section introduces a "Hello World" Colang example.
- [Interaction Loop](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/getting-started/interaction-loop.md): This section explains how to create an interaction loop in Colang 2.0.
- [Input Rails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/getting-started/input-rails.md): This section explains how to create *input rails* in Colang 2.0.
- [Dialog Rails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/getting-started/dialog-rails.md): This section explains how to create dialog rails using Colang.
- [LLM Flows](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/getting-started/llm-flows.md): This section explains how to create LLM-driven flows in Colang 2.0.
- [Multimodal Rails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/getting-started/multimodal-rails.md): This section explains how to create multimodal rails in Colang 2.0.
- [Recommended Next Steps](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/getting-started/recommended-next-steps.md): The Colang 2.0 getting started guide introduces you to a basic Hello World example, and then goes into Dialog Rails,  Input Rails, Multimodal Rails, and other Colang 2.0 concepts l
- [Colang 2.0 Language Reference](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/language-reference.md): Reference documentation for Colang 2.0 syntax, events, actions, flows, variables, and the standard library.
- [Introduction](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/language-reference/introduction.md): Colang is an event-based modeling language to enable the design of highly flexible conversational interactions between a human and a bot. Since learning a new language is not an ea
- [Event Generation & Matching](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/language-reference/event-generation-and-matching.md): When working with Colang, we assume to have a common event channel that contains all relevant events happening in the interactive system. From a Colang perspective, relevant events
- [Working with Actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/language-reference/working-with-actions.md): You have seen in section Event Generation & Matching how to work with events. We will now introduce actions that will enable you to better manage events and their temporal dependen
- [Defining Flows](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/language-reference/defining-flows.md): So far you have seen only one flow, the main flow. But in Colang we can define many different flows, like functions in other programming languages. A flow defines a specific intera
- [Working with Variables & Expressions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/language-reference/working-with-variables-and-expressions.md): Like Python, Colang supports these fundamental data types: `string`, `int`, `float`, `bool`, `list`, `set`, `dict`, in addition to the Colang specific event, action and flow refere
- [Flow control](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/language-reference/flow-control.md): Flow control is an essential tool in all programming languages, and Colang supports this as well. It enables branching and repetition of interaction patterns in a single flow.
- [Colang Standard Library (CSL)](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/language-reference/the-standard-library.md): The Colang Standard Library (CSL) provides an abstraction from the underlying event and action layer and offers a semantic interface to design interaction patterns between the bot
- [Fundamental Core Flows](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/language-reference/the-standard-library/core.md): The core library that contains all relevant flows related to user and bot utterance events and actions.
- [Timing Flows](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/language-reference/the-standard-library/timing.md): Flows related to timing and reacting to periods of silence.
- [LLM Flows](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/language-reference/the-standard-library/lmm.md): Trigger a bot utterance similar to given text
- [Interactive Avatar Modality Flows](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/language-reference/the-standard-library/avatars.md): **User Event Flows**
- [Guardrail Flows](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/language-reference/the-standard-library/guardrails.md): Flows to guardrail user inputs and LLM responses.
- [User Attention Flows](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/language-reference/the-standard-library/attention.md): Flows to handle user attention.
- [Make use of Large Language Models (LLM)](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/language-reference/make-use-of-llms.md): At its core, Colang does not require a Large Language Model (LLM) as backend. However, many of the more advanced mechanisms in the Colang Standard Library (CSL) depend on one.
- [More on Flows](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/language-reference/more-on-flows.md): In section Defining Flows, we learned the core mechanisms of flows. In this section will look at more advanced topics that are related to flows.
- [Python Actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/language-reference/python-actions.md): In the section Working with Actions, you have seen how actions can be used in the context of UMIM events. Additionally, you can also use the action concept to call custom python fu
- [Development and Debugging](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-2/language-reference/development-and-debugging.md): Currently, the Colang story designing and building environment is fairly limited, but will be improved on in the future.
- [Colang 1.0 Guide](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-1.md): Reference and tutorials for Colang 1.0 syntax for defining dialog flows and guardrails.
- [Colang 1.0 Language Syntax](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-1/colang-language-syntax-guide.md): Comprehensive syntax guide for Colang 1.0 including messages, flows, variables, and patterns.
- [Colang 1.0 Tutorials](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-1/tutorials.md): Step-by-step tutorials for building guardrails with Colang 1.0 from Hello World to RAG.
- [Hello World](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-1/tutorials/1-hello-world.md): Create your first guardrails configuration to control greeting behavior with Colang 1.0.
- [Core Colang Concepts](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-1/tutorials/2-core-colang-concepts.md): Learn essential Colang concepts including messages, flows, context variables, and LLM integration.
- [Demo Use Case](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-1/tutorials/3-demo-use-case.md): Introduction to the ABC Bot example used throughout the Colang 1.0 tutorial series.
- [Input Rails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-1/tutorials/4-input-rails.md): Add input rails to validate and filter user messages before LLM processing.
- [Output Rails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-1/tutorials/5-output-rails.md): Add output rails to filter and validate LLM responses before returning to users.
- [Topical Rails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-1/tutorials/6-topical-rails.md): Implement topical rails to keep conversations on-topic and prevent off-topic discussions.
- [Retrieval-Augmented Generation](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-1/tutorials/7-rag.md): Apply guardrails to RAG scenarios with knowledge base integration and fact checking.
- [Guardrailing Bot Reasoning Content](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/colang-1/bot-thinking-guardrails.md): Inspect and control LLM reasoning traces to block problematic patterns or enhance moderation decisions.
- [Colang Usage Examples](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/usage-examples.md): Practical examples of Colang patterns for bot messages, value extraction, and flow control.
- [Bot Message Instructions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/usage-examples/bot-message-instructions.md): Provide custom instructions to control how the LLM generates bot messages in Colang 1.0 and 2.0.
- [Extract User-provided Values](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/colang/usage-examples/extract-user-provided-values.md): Extract and store user-provided values like names, dates, and queries in context variables.
- [Other Configurations](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/other-configurations.md): Additional configuration topics including knowledge base setup and embedding search providers.
- [Knowledge Base Configuration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/other-configurations/knowledge-base.md): Configure the knowledge base folder for RAG-based responses using markdown documents.
- [Embedding Search Providers](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/other-configurations/embedding-search-providers.md): Configure embedding search providers for vector similarity search using FastEmbed, OpenAI, or custom implementations.
- [Caching Instructions and Prompts](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/caching.md): Configure in-memory caching for LLM calls and KV cache reuse to improve performance and reduce latency.
- [Memory Model Cache](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/caching/model-memory-cache.md): Configure in-memory caching to avoid repeated LLM calls for identical prompts using LFU eviction.
- [KV Cache Reuse for NemoGuard NIM](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/caching/kv-cache-reuse.md): Enable KV cache reuse in NVIDIA NIM for LLMs to reduce inference latency for NemoGuard models.
- [Exceptions and Error Handling](https://docs.nvidia.com/nemo/guardrails/v0.22.0/configure-guardrails/exceptions.md): Raise and handle exceptions in guardrails flows to control error behavior and custom responses.
- [About Running Guardrailed Inference](https://docs.nvidia.com/nemo/guardrails/v0.22.0/run-guardrailed-inference/run-rails.md): Run guardrailed inference using the Python API or Guardrails API server.
- [Use the NeMo Guardrails Python APIs](https://docs.nvidia.com/nemo/guardrails/v0.22.0/run-guardrailed-inference/using-python-apis.md): Run guardrailed inference using the NeMo Guardrails Python API.
- [Overview of the NeMo Guardrails Python APIs](https://docs.nvidia.com/nemo/guardrails/v0.22.0/run-guardrailed-inference/using-python-apis/overview.md): RailsConfig and LLMRails core classes for generating guarded responses.
- [Core Classes Reference](https://docs.nvidia.com/nemo/guardrails/v0.22.0/run-guardrailed-inference/using-python-apis/core-classes.md): RailsConfig and LLMRails class reference for loading and running guardrails.
- [Generation Options Reference](https://docs.nvidia.com/nemo/guardrails/v0.22.0/run-guardrailed-inference/using-python-apis/generation-options.md): Configure logging, LLM parameters, and rail selection for generation.
- [Streaming Responses](https://docs.nvidia.com/nemo/guardrails/v0.22.0/run-guardrailed-inference/using-python-apis/streaming.md): Stream LLM responses in real-time with the stream_async method.
- [Checking Messages Against Rails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/run-guardrailed-inference/using-python-apis/check-messages.md): Validate messages against input and output rails using check_async and check methods.
- [Event-Based API](https://docs.nvidia.com/nemo/guardrails/v0.22.0/run-guardrailed-inference/using-python-apis/event-based-api.md): Use generate_events for low-level control over guardrails execution.
- [Use the Guardrails API Server](https://docs.nvidia.com/nemo/guardrails/v0.22.0/run-guardrailed-inference/using-fastapi-server.md): Expose guardrails through an HTTP API using the Guardrails API server.
- [Overview of the NVIDIA NeMo Guardrails Library API Server](https://docs.nvidia.com/nemo/guardrails/v0.22.0/run-guardrailed-inference/using-fastapi-server/overview.md): The NVIDIA NeMo Guardrails library API server runs guardrails in a secure, isolated environment.
- [Run the Guardrails Server](https://docs.nvidia.com/nemo/guardrails/v0.22.0/run-guardrailed-inference/using-fastapi-server/run-guardrails-server.md): Start the Guardrails API server, configure CORS, and enable auto-reload.
- [Chat with Guardrailed Model](https://docs.nvidia.com/nemo/guardrails/v0.22.0/run-guardrailed-inference/using-fastapi-server/chat-with-guardrailed-model.md): Send chat requests, use streaming, and manage conversation threads.
- [List Guardrail Configurations](https://docs.nvidia.com/nemo/guardrails/v0.22.0/run-guardrailed-inference/using-fastapi-server/list-guardrail-configs.md): Retrieve available guardrails configurations from the server.
- [List Available Models](https://docs.nvidia.com/nemo/guardrails/v0.22.0/run-guardrailed-inference/using-fastapi-server/list-models.md): Query the available LLM models from the configured provider.
- [Use the Actions Server](https://docs.nvidia.com/nemo/guardrails/v0.22.0/run-guardrailed-inference/using-fastapi-server/actions-server.md): Run guardrail actions in a secure, isolated environment.
- [Evaluate Configuration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/evaluation/evaluate-configuration.md): Evaluate a guardrails configuration with policies, interactions, LLM-as-a-judge checks, and the Eval UI.
- [Evaluation Methodology](https://docs.nvidia.com/nemo/guardrails/v0.22.0/evaluation/evaluation-methodology.md): Design policy-based evaluation datasets and interpret compliance results for guardrails configurations.
- [Evaluate NeMo Guardrails Library Performance](https://docs.nvidia.com/nemo/guardrails/v0.22.0/evaluation/evaluate-guardrails.md): Measure accuracy and performance of dialog, fact-checking, moderation, and hallucination rails.
- [LLM Vulnerability Scanning](https://docs.nvidia.com/nemo/guardrails/v0.22.0/evaluation/llm-vulnerability-scanning.md): Scan LLM applications for vulnerabilities using Garak and measure guardrails protection rates.
- [Observability Overview](https://docs.nvidia.com/nemo/guardrails/v0.22.0/observability/observability.md): Logging, tracing, and metrics for end-to-end visibility into the behavior of the NVIDIA NeMo Guardrails library.
- [Logging and Debugging Guardrails Generated Responses](https://docs.nvidia.com/nemo/guardrails/v0.22.0/observability/logging.md): Debug guardrails with verbose mode, explain method, and generation log options.
- [Tracing Guardrails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/observability/tracing.md): Enable distributed tracing with OpenTelemetry to monitor guardrails execution and LLM calls.
- [Quick Start for Tracing Guardrails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/observability/tracing/quick-start.md): Set up tracing in minutes with the OpenTelemetry SDK and console output.
- [Adapter Configurations](https://docs.nvidia.com/nemo/guardrails/v0.22.0/observability/tracing/adapter-configurations.md): Configure FileSystem, OpenTelemetry, or custom adapters for guardrails tracing.
- [OpenTelemetry Integration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/observability/tracing/opentelemetry-integration.md): Configure OpenTelemetry SDK with OTLP exporters for production monitoring backends.
- [Exporting Guardrails Logs to OpenTelemetry](https://docs.nvidia.com/nemo/guardrails/v0.22.0/observability/tracing/opentelemetry-logs.md): Forward Python logs from the NeMo Guardrails library into your OpenTelemetry backend with automatic trace correlation.
- [Troubleshooting](https://docs.nvidia.com/nemo/guardrails/v0.22.0/observability/tracing/troubleshooting.md): Resolve common tracing issues with OpenTelemetry SDK configuration and connectivity.
- [Metrics for Guardrails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/observability/metrics.md): Emit OpenTelemetry metrics from the opt-in IORails engine for SLO dashboards, capacity planning, and LLM cost tracking.
- [Enable Guardrails Metrics](https://docs.nvidia.com/nemo/guardrails/v0.22.0/observability/metrics/enable-metrics.md): Set up metrics in minutes with the OpenTelemetry SDK and console output.
- [OpenTelemetry Metrics Integration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/observability/metrics/opentelemetry-integration.md): Configure the OpenTelemetry SDK with OTLP and Prometheus exporters for production metrics backends.
- [Metric Reference](https://docs.nvidia.com/nemo/guardrails/v0.22.0/observability/metrics/reference.md): Reference every metric IORails emits, with instrument types, units, labels, and emission semantics.
- [About Deployment Options](https://docs.nvidia.com/nemo/guardrails/v0.22.0/more-deployment-options/deployment.md): Deploy guardrails using the local API server, Docker containers, or production microservices.
- [Deploy the NeMo Guardrails Library with Docker](https://docs.nvidia.com/nemo/guardrails/v0.22.0/more-deployment-options/using-docker.md): Build and run NeMo Guardrails Docker images for deployment and testing.
- [NeMo Guardrails Microservice for Production](https://docs.nvidia.com/nemo/guardrails/v0.22.0/more-deployment-options/using-microservice.md): Deploy guardrails as a production-ready microservice using the NeMo microservices platform.
- [LangChain Frameworks](https://docs.nvidia.com/nemo/guardrails/v0.22.0/integration-with-third-party-libraries/langchain.md): Integrate NeMo Guardrails with LangChain chains, runnables, and LangGraph workflows.
- [LangChain Integration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/integration-with-third-party-libraries/langchain/langchain-integration.md): Add guardrails to LangChain chains or use chains as actions inside guardrails configurations.
- [Agent Middleware](https://docs.nvidia.com/nemo/guardrails/v0.22.0/integration-with-third-party-libraries/langchain/agent-middleware.md): Add guardrails to LangChain agents using the GuardrailsMiddleware for automatic input and output safety checks on every model call.
- [RunnableRails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/integration-with-third-party-libraries/langchain/runnable-rails.md): Use RunnableRails to wrap LLMs and chains with guardrails using the Runnable Protocol.
- [Add Guardrails to a LangChain Chain](https://docs.nvidia.com/nemo/guardrails/v0.22.0/integration-with-third-party-libraries/langchain/chain-with-guardrails.md): Protect LangChain chains from jailbreak attempts using input rails and RunnableRails.
- [Use a Runnable as an Action in Guardrails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/integration-with-third-party-libraries/langchain/runnable-as-action.md): Register LangChain Runnables as actions and invoke them from Colang flows.
- [LangGraph Integration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/integration-with-third-party-libraries/langchain/langgraph-integration.md): Build safe multi-agent workflows with LangGraph and NeMo Guardrails protection.
- [Tools Integration with the NeMo Guardrails Library](https://docs.nvidia.com/nemo/guardrails/v0.22.0/integration-with-third-party-libraries/tools-integration.md): Integrate LangChain tools with guardrails using passthrough mode and output rail validation.
- [Colang Architecture Guide](https://docs.nvidia.com/nemo/guardrails/v0.22.0/reference/colang-architecture-guide.md): Explore the event-driven runtime, canonical messages, and server design.
- [Guardrails Sequence Diagrams](https://docs.nvidia.com/nemo/guardrails/v0.22.0/reference/guardrails-sequence-diagrams.md): View sequence diagrams showing input, retrieval, dialog, execution, and output stages.
- [Use Case Diagrams](https://docs.nvidia.com/nemo/guardrails/v0.22.0/reference/use-case-diagrams.md)
- [nemoguardrails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/reference/python-sdk-reference.md)
- [nemoguardrails._compat](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/_compat.md)
- [nemoguardrails._compat.langchain_kwargs](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/_compat/langchain_kwargs.md)
- [nemoguardrails.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/actions.md)
- [nemoguardrails.actions.action_dispatcher](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/actions/action_dispatcher.md)
- [nemoguardrails.actions.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/actions/actions.md)
- [nemoguardrails.actions.core](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/actions/core.md)
- [nemoguardrails.actions.llm](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/actions/llm.md)
- [nemoguardrails.actions.llm.generation](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/actions/llm/generation.md)
- [nemoguardrails.actions.llm.utils](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/actions/llm/utils.md)
- [nemoguardrails.actions.math](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/actions/math.md)
- [nemoguardrails.actions.output_mapping](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/actions/output_mapping.md)
- [nemoguardrails.actions.retrieve_relevant_chunks](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/actions/retrieve_relevant_chunks.md)
- [nemoguardrails.actions.v2_x](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/actions/v2_x.md)
- [nemoguardrails.actions.v2_x.generation](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/actions/v2_x/generation.md)
- [nemoguardrails.actions.validation](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/actions/validation.md)
- [nemoguardrails.actions.validation.base](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/actions/validation/base.md)
- [nemoguardrails.actions.validation.filter_secrets](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/actions/validation/filter_secrets.md)
- [nemoguardrails.actions_server](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/actions_server.md)
- [nemoguardrails.actions_server.actions_server](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/actions_server/actions_server.md)
- [nemoguardrails.cli](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/cli.md)
- [nemoguardrails.cli.chat](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/cli/chat.md)
- [nemoguardrails.cli.debugger](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/cli/debugger.md)
- [nemoguardrails.cli.migration](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/cli/migration.md)
- [nemoguardrails.cli.providers](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/cli/providers.md)
- [nemoguardrails.colang](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang.md)
- [nemoguardrails.colang.runtime](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/runtime.md)
- [nemoguardrails.colang.v1_0](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v1_0.md)
- [nemoguardrails.colang.v1_0.lang](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v1_0/lang.md)
- [nemoguardrails.colang.v1_0.lang.colang_parser](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v1_0/lang/colang_parser.md)
- [nemoguardrails.colang.v1_0.lang.comd_parser](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v1_0/lang/comd_parser.md)
- [nemoguardrails.colang.v1_0.lang.coyml_parser](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v1_0/lang/coyml_parser.md)
- [nemoguardrails.colang.v1_0.lang.parser](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v1_0/lang/parser.md)
- [nemoguardrails.colang.v1_0.lang.utils](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v1_0/lang/utils.md)
- [nemoguardrails.colang.v1_0.runtime](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v1_0/runtime.md)
- [nemoguardrails.colang.v1_0.runtime.eval](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v1_0/runtime/eval.md)
- [nemoguardrails.colang.v1_0.runtime.flows](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v1_0/runtime/flows.md)
- [nemoguardrails.colang.v1_0.runtime.runtime](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v1_0/runtime/runtime.md)
- [nemoguardrails.colang.v1_0.runtime.sliding](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v1_0/runtime/sliding.md)
- [nemoguardrails.colang.v1_0.runtime.utils](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v1_0/runtime/utils.md)
- [nemoguardrails.colang.v2_x](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v2_x.md)
- [nemoguardrails.colang.v2_x.lang](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v2_x/lang.md)
- [nemoguardrails.colang.v2_x.lang.colang_ast](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v2_x/lang/colang_ast.md)
- [nemoguardrails.colang.v2_x.lang.expansion](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v2_x/lang/expansion.md)
- [nemoguardrails.colang.v2_x.lang.grammar](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v2_x/lang/grammar.md)
- [nemoguardrails.colang.v2_x.lang.grammar.load](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v2_x/lang/grammar/load.md)
- [nemoguardrails.colang.v2_x.lang.parser](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v2_x/lang/parser.md)
- [nemoguardrails.colang.v2_x.lang.transformer](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v2_x/lang/transformer.md)
- [nemoguardrails.colang.v2_x.lang.utils](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v2_x/lang/utils.md)
- [nemoguardrails.colang.v2_x.runtime](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v2_x/runtime.md)
- [nemoguardrails.colang.v2_x.runtime.errors](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v2_x/runtime/errors.md)
- [nemoguardrails.colang.v2_x.runtime.eval](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v2_x/runtime/eval.md)
- [nemoguardrails.colang.v2_x.runtime.flows](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v2_x/runtime/flows.md)
- [nemoguardrails.colang.v2_x.runtime.runtime](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v2_x/runtime/runtime.md)
- [nemoguardrails.colang.v2_x.runtime.serialization](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v2_x/runtime/serialization.md)
- [nemoguardrails.colang.v2_x.runtime.statemachine](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v2_x/runtime/statemachine.md)
- [nemoguardrails.colang.v2_x.runtime.system_functions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v2_x/runtime/system_functions.md)
- [nemoguardrails.colang.v2_x.runtime.utils](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/colang/v2_x/runtime/utils.md)
- [nemoguardrails.context](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/context.md)
- [nemoguardrails.embeddings.index](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/embeddings.md)
- [nemoguardrails.embeddings.basic](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/embeddings/basic.md)
- [nemoguardrails.embeddings.cache](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/embeddings/cache.md)
- [nemoguardrails.embeddings.providers](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/embeddings/providers.md)
- [nemoguardrails.embeddings.providers.azureopenai](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/embeddings/providers/azureopenai.md)
- [nemoguardrails.embeddings.providers.base](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/embeddings/providers/base.md)
- [nemoguardrails.embeddings.providers.cohere](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/embeddings/providers/cohere.md)
- [nemoguardrails.embeddings.providers.fastembed](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/embeddings/providers/fastembed.md)
- [nemoguardrails.embeddings.providers.google](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/embeddings/providers/google.md)
- [nemoguardrails.embeddings.providers.nim](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/embeddings/providers/nim.md)
- [nemoguardrails.embeddings.providers.openai](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/embeddings/providers/openai.md)
- [nemoguardrails.embeddings.providers.registry](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/embeddings/providers/registry.md)
- [nemoguardrails.embeddings.providers.sentence_transformers](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/embeddings/providers/sentence_transformers.md)
- [nemoguardrails.eval](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/eval.md)
- [nemoguardrails.eval.check](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/eval/check.md)
- [nemoguardrails.eval.cli](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/eval/cli.md)
- [nemoguardrails.eval.eval](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/eval/eval.md)
- [nemoguardrails.eval.models](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/eval/models.md)
- [nemoguardrails.eval.ui](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/eval/ui.md)
- [nemoguardrails.eval.ui.README](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/eval/ui/README.md)
- [nemoguardrails.eval.ui.chart_utils](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/eval/ui/chart_utils.md)
- [nemoguardrails.eval.ui.common](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/eval/ui/common.md)
- [nemoguardrails.eval.ui.streamlit_utils](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/eval/ui/streamlit_utils.md)
- [nemoguardrails.eval.ui.utils](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/eval/ui/utils.md)
- [nemoguardrails.eval.utils](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/eval/utils.md)
- [nemoguardrails.evaluate](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/evaluate.md)
- [nemoguardrails.evaluate.cli](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/evaluate/cli.md)
- [nemoguardrails.evaluate.cli.evaluate](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/evaluate/cli/evaluate.md)
- [nemoguardrails.evaluate.cli.simplify_formatter](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/evaluate/cli/simplify_formatter.md)
- [nemoguardrails.evaluate.evaluate_factcheck](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/evaluate/evaluate_factcheck.md)
- [nemoguardrails.evaluate.evaluate_hallucination](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/evaluate/evaluate_hallucination.md)
- [nemoguardrails.evaluate.evaluate_moderation](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/evaluate/evaluate_moderation.md)
- [nemoguardrails.evaluate.evaluate_topical](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/evaluate/evaluate_topical.md)
- [nemoguardrails.evaluate.utils](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/evaluate/utils.md)
- [nemoguardrails.exceptions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/exceptions.md)
- [nemoguardrails.guardrails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/guardrails.md)
- [nemoguardrails.guardrails._http](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/guardrails/_http.md)
- [nemoguardrails.guardrails.api_engine](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/guardrails/api_engine.md)
- [nemoguardrails.guardrails.async_work_queue](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/guardrails/async_work_queue.md)
- [nemoguardrails.guardrails.base_engine](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/guardrails/base_engine.md)
- [nemoguardrails.guardrails.engine_registry](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/guardrails/engine_registry.md)
- [nemoguardrails.guardrails.guardrails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/guardrails/guardrails.md)
- [nemoguardrails.guardrails.guardrails_types](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/guardrails/guardrails_types.md)
- [nemoguardrails.guardrails.iorails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/guardrails/iorails.md)
- [nemoguardrails.guardrails.model_engine](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/guardrails/model_engine.md)
- [nemoguardrails.guardrails.rail_action](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/guardrails/rail_action.md)
- [nemoguardrails.guardrails.rails_manager](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/guardrails/rails_manager.md)
- [nemoguardrails.guardrails.telemetry](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/guardrails/telemetry.md)
- [nemoguardrails.imports](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/imports.md)
- [nemoguardrails.integrations](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/integrations.md)
- [nemoguardrails.integrations.langchain](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/integrations/langchain.md)
- [nemoguardrails.integrations.langchain.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/integrations/langchain/actions.md)
- [nemoguardrails.integrations.langchain.actions.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/integrations/langchain/actions/actions.md)
- [nemoguardrails.integrations.langchain.actions.safetools](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/integrations/langchain/actions/safetools.md)
- [nemoguardrails.integrations.langchain.exceptions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/integrations/langchain/exceptions.md)
- [nemoguardrails.integrations.langchain.helpers](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/integrations/langchain/helpers.md)
- [nemoguardrails.integrations.langchain.langchain_initializer](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/integrations/langchain/langchain_initializer.md)
- [nemoguardrails.integrations.langchain.llm_adapter](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/integrations/langchain/llm_adapter.md)
- [nemoguardrails.integrations.langchain.message_utils](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/integrations/langchain/message_utils.md)
- [nemoguardrails.integrations.langchain.middleware](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/integrations/langchain/middleware.md)
- [nemoguardrails.integrations.langchain.providers](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/integrations/langchain/providers.md)
- [nemoguardrails.integrations.langchain.providers.huggingface](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/integrations/langchain/providers/huggingface.md)
- [nemoguardrails.integrations.langchain.providers.huggingface.pipeline](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/integrations/langchain/providers/huggingface/pipeline.md)
- [nemoguardrails.integrations.langchain.providers.huggingface.streamers](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/integrations/langchain/providers/huggingface/streamers.md)
- [nemoguardrails.integrations.langchain.providers.providers](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/integrations/langchain/providers/providers.md)
- [nemoguardrails.integrations.langchain.providers.trtllm](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/integrations/langchain/providers/trtllm.md)
- [nemoguardrails.integrations.langchain.providers.trtllm.client](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/integrations/langchain/providers/trtllm/client.md)
- [nemoguardrails.integrations.langchain.providers.trtllm.llm](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/integrations/langchain/providers/trtllm/llm.md)
- [nemoguardrails.integrations.langchain.runnable_rails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/integrations/langchain/runnable_rails.md)
- [nemoguardrails.integrations.langchain.utils](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/integrations/langchain/utils.md)
- [nemoguardrails.kb](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/kb.md)
- [nemoguardrails.kb.kb](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/kb/kb.md)
- [nemoguardrails.kb.utils](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/kb/utils.md)
- [nemoguardrails.library](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library.md)
- [nemoguardrails.library.activefence](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/activefence.md)
- [nemoguardrails.library.activefence.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/activefence/actions.md)
- [nemoguardrails.library.ai_defense](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/ai_defense.md)
- [nemoguardrails.library.ai_defense.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/ai_defense/actions.md)
- [nemoguardrails.library.autoalign](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/autoalign.md)
- [nemoguardrails.library.autoalign.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/autoalign/actions.md)
- [nemoguardrails.library.clavata](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/clavata.md)
- [nemoguardrails.library.clavata.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/clavata/actions.md)
- [nemoguardrails.library.clavata.errs](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/clavata/errs.md)
- [nemoguardrails.library.clavata.request](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/clavata/request.md)
- [nemoguardrails.library.clavata.utils](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/clavata/utils.md)
- [nemoguardrails.library.cleanlab](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/cleanlab.md)
- [nemoguardrails.library.cleanlab.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/cleanlab/actions.md)
- [nemoguardrails.library.content_safety](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/content_safety.md)
- [nemoguardrails.library.content_safety.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/content_safety/actions.md)
- [nemoguardrails.library.crowdstrike_aidr](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/crowdstrike_aidr.md)
- [nemoguardrails.library.crowdstrike_aidr.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/crowdstrike_aidr/actions.md)
- [nemoguardrails.library.factchecking](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/factchecking.md)
- [nemoguardrails.library.factchecking.align_score](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/factchecking/align_score.md)
- [nemoguardrails.library.factchecking.align_score.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/factchecking/align_score/actions.md)
- [nemoguardrails.library.factchecking.align_score.request](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/factchecking/align_score/request.md)
- [nemoguardrails.library.factchecking.align_score.server](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/factchecking/align_score/server.md)
- [nemoguardrails.library.fiddler](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/fiddler.md)
- [nemoguardrails.library.fiddler.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/fiddler/actions.md)
- [nemoguardrails.library.gcp_moderate_text](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/gcp_moderate_text.md)
- [nemoguardrails.library.gcp_moderate_text.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/gcp_moderate_text/actions.md)
- [nemoguardrails.library.gliner](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/gliner.md)
- [nemoguardrails.library.gliner.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/gliner/actions.md)
- [nemoguardrails.library.gliner.models](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/gliner/models.md)
- [nemoguardrails.library.gliner.request](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/gliner/request.md)
- [nemoguardrails.library.guardrails_ai](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/guardrails_ai.md)
- [nemoguardrails.library.guardrails_ai.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/guardrails_ai/actions.md)
- [nemoguardrails.library.guardrails_ai.errors](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/guardrails_ai/errors.md)
- [nemoguardrails.library.guardrails_ai.registry](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/guardrails_ai/registry.md)
- [nemoguardrails.library.hallucination](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/hallucination.md)
- [nemoguardrails.library.hallucination.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/hallucination/actions.md)
- [nemoguardrails.library.injection_detection](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/injection_detection.md)
- [nemoguardrails.library.injection_detection.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/injection_detection/actions.md)
- [nemoguardrails.library.injection_detection.yara_config](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/injection_detection/yara_config.md)
- [nemoguardrails.library.jailbreak_detection](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/jailbreak_detection.md)
- [nemoguardrails.library.jailbreak_detection.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/jailbreak_detection/actions.md)
- [nemoguardrails.library.jailbreak_detection.heuristics](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/jailbreak_detection/heuristics.md)
- [nemoguardrails.library.jailbreak_detection.heuristics.checks](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/jailbreak_detection/heuristics/checks.md)
- [nemoguardrails.library.jailbreak_detection.model_based](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/jailbreak_detection/model_based.md)
- [nemoguardrails.library.jailbreak_detection.model_based.checks](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/jailbreak_detection/model_based/checks.md)
- [nemoguardrails.library.jailbreak_detection.model_based.models](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/jailbreak_detection/model_based/models.md)
- [nemoguardrails.library.jailbreak_detection.request](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/jailbreak_detection/request.md)
- [nemoguardrails.library.jailbreak_detection.server](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/jailbreak_detection/server.md)
- [nemoguardrails.library.llama_guard](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/llama_guard.md)
- [nemoguardrails.library.llama_guard.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/llama_guard/actions.md)
- [nemoguardrails.library.pangea](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/pangea.md)
- [nemoguardrails.library.pangea.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/pangea/actions.md)
- [nemoguardrails.library.patronusai](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/patronusai.md)
- [nemoguardrails.library.patronusai.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/patronusai/actions.md)
- [nemoguardrails.library.policyai](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/policyai.md)
- [nemoguardrails.library.policyai.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/policyai/actions.md)
- [nemoguardrails.library.privateai](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/privateai.md)
- [nemoguardrails.library.privateai.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/privateai/actions.md)
- [nemoguardrails.library.privateai.request](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/privateai/request.md)
- [nemoguardrails.library.prompt_security](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/prompt_security.md)
- [nemoguardrails.library.prompt_security.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/prompt_security/actions.md)
- [nemoguardrails.library.regex](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/regex.md)
- [nemoguardrails.library.regex.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/regex/actions.md)
- [nemoguardrails.library.self_check](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/self_check.md)
- [nemoguardrails.library.self_check.facts](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/self_check/facts.md)
- [nemoguardrails.library.self_check.facts.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/self_check/facts/actions.md)
- [nemoguardrails.library.self_check.input_check](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/self_check/input_check.md)
- [nemoguardrails.library.self_check.input_check.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/self_check/input_check/actions.md)
- [nemoguardrails.library.self_check.output_check](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/self_check/output_check.md)
- [nemoguardrails.library.self_check.output_check.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/self_check/output_check/actions.md)
- [nemoguardrails.library.sensitive_data_detection](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/sensitive_data_detection.md)
- [nemoguardrails.library.sensitive_data_detection.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/sensitive_data_detection/actions.md)
- [nemoguardrails.library.topic_safety](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/topic_safety.md)
- [nemoguardrails.library.topic_safety.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/topic_safety/actions.md)
- [nemoguardrails.library.trend_micro](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/trend_micro.md)
- [nemoguardrails.library.trend_micro.actions](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/library/trend_micro/actions.md)
- [nemoguardrails.llm](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/llm.md)
- [nemoguardrails.llm.cache](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/llm/cache.md)
- [nemoguardrails.llm.cache.interface](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/llm/cache/interface.md)
- [nemoguardrails.llm.cache.lfu](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/llm/cache/lfu.md)
- [nemoguardrails.llm.cache.utils](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/llm/cache/utils.md)
- [nemoguardrails.llm.clients](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/llm/clients.md)
- [nemoguardrails.llm.clients._errors](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/llm/clients/_errors.md)
- [nemoguardrails.llm.clients._sse](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/llm/clients/_sse.md)
- [nemoguardrails.llm.clients.base](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/llm/clients/base.md)
- [nemoguardrails.llm.clients.constants](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/llm/clients/constants.md)
- [nemoguardrails.llm.clients.openai_compatible](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/llm/clients/openai_compatible.md)
- [nemoguardrails.llm.constants](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/llm/constants.md)
- [nemoguardrails.llm.filters](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/llm/filters.md)
- [nemoguardrails.llm.frameworks](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/llm/frameworks.md)
- [nemoguardrails.llm.frameworks.default](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/llm/frameworks/default.md)
- [nemoguardrails.llm.frameworks.registry](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/llm/frameworks/registry.md)
- [nemoguardrails.llm.openai_reasoning](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/llm/openai_reasoning.md)
- [nemoguardrails.llm.output_parsers](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/llm/output_parsers.md)
- [nemoguardrails.llm.prompts](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/llm/prompts.md)
- [nemoguardrails.llm.taskmanager](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/llm/taskmanager.md)
- [nemoguardrails.llm.types](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/llm/types.md)
- [nemoguardrails.logging](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/logging.md)
- [nemoguardrails.logging.explain](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/logging/explain.md)
- [nemoguardrails.logging.llm_tracker](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/logging/llm_tracker.md)
- [nemoguardrails.logging.processing_log](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/logging/processing_log.md)
- [nemoguardrails.logging.simplify_formatter](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/logging/simplify_formatter.md)
- [nemoguardrails.logging.stats](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/logging/stats.md)
- [nemoguardrails.logging.verbose](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/logging/verbose.md)
- [nemoguardrails.patch_asyncio](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/patch_asyncio.md)
- [nemoguardrails.rails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/rails.md)
- [nemoguardrails.rails.llm](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/rails/llm.md)
- [nemoguardrails.rails.llm.buffer](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/rails/llm/buffer.md)
- [nemoguardrails.rails.llm.config](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/rails/llm/config.md)
- [nemoguardrails.rails.llm.llmrails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/rails/llm/llmrails.md)
- [nemoguardrails.rails.llm.options](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/rails/llm/options.md)
- [nemoguardrails.rails.llm.utils](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/rails/llm/utils.md)
- [nemoguardrails.registry](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/registry.md)
- [nemoguardrails.server](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/server.md)
- [nemoguardrails.server.api](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/server/api.md)
- [nemoguardrails.server.app](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/server/app.md)
- [nemoguardrails.server.datastore](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/server/datastore.md)
- [nemoguardrails.server.datastore.datastore](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/server/datastore/datastore.md)
- [nemoguardrails.server.datastore.memory_store](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/server/datastore/memory_store.md)
- [nemoguardrails.server.datastore.redis_store](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/server/datastore/redis_store.md)
- [nemoguardrails.singleton](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/singleton.md)
- [nemoguardrails.streaming](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/streaming.md)
- [nemoguardrails.telemetry](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/telemetry.md)
- [nemoguardrails.testing](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/testing.md)
- [nemoguardrails.testing.chat_harness](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/testing/chat_harness.md)
- [nemoguardrails.testing.fake_model](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/testing/fake_model.md)
- [nemoguardrails.testing.fixtures](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/testing/fixtures.md)
- [nemoguardrails.tracing](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/tracing.md)
- [nemoguardrails.tracing.adapters](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/tracing/adapters.md)
- [nemoguardrails.tracing.adapters.base](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/tracing/adapters/base.md)
- [nemoguardrails.tracing.adapters.filesystem](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/tracing/adapters/filesystem.md)
- [nemoguardrails.tracing.adapters.opentelemetry](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/tracing/adapters/opentelemetry.md)
- [nemoguardrails.tracing.adapters.registry](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/tracing/adapters/registry.md)
- [nemoguardrails.tracing.constants](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/tracing/constants.md)
- [nemoguardrails.tracing.interaction_types](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/tracing/interaction_types.md)
- [nemoguardrails.tracing.span_extractors](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/tracing/span_extractors.md)
- [nemoguardrails.tracing.span_format](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/tracing/span_format.md)
- [nemoguardrails.tracing.span_formatting](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/tracing/span_formatting.md)
- [nemoguardrails.tracing.spans](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/tracing/spans.md)
- [nemoguardrails.tracing.tracer](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/tracing/tracer.md)
- [nemoguardrails.types](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/types.md)
- [nemoguardrails.utils](https://docs.nvidia.com/nemo/guardrails/v0.22.0/guardrails-python-sdk/nemoguardrails/utils.md)
- [NeMo Guardrails Library CLI Reference](https://docs.nvidia.com/nemo/guardrails/v0.22.0/reference/cli.md): Use the nemoguardrails command-line interface to chat, serve, evaluate, and convert configurations.
- [Migrating to 0.22](https://docs.nvidia.com/nemo/guardrails/v0.22.0/reference/0-22.md): How to update a working 0.21 configuration for NeMo Guardrails 0.22, in which LangChain becomes optional and a built-in OpenAI-compatible client handles most engines.
- [NVIDIA NeMo Guardrails Library Troubleshooting Guide](https://docs.nvidia.com/nemo/guardrails/v0.22.0/troubleshooting/troubleshooting.md): Diagnose and resolve common NVIDIA NeMo Guardrails library configuration, runtime, and observability issues.
- [Security Guidelines for LLM Integrations](https://docs.nvidia.com/nemo/guardrails/v0.22.0/resources/guidelines.md): Follow security best practices when integrating LLMs with external resources and APIs.
- [Telemetry](https://docs.nvidia.com/nemo/guardrails/v0.22.0/resources/telemetry.md)
- [Research on Guardrails](https://docs.nvidia.com/nemo/guardrails/v0.22.0/resources/research.md)

## API Docs

- Guardrails API Server > Chat Completions [Create Chat Completion](https://docs.nvidia.com/nemo/guardrails/v0.22.0/reference/guardrails-api-server/chat-completions/chat-completions.md)
- Guardrails API Server > Models [List Models](https://docs.nvidia.com/nemo/guardrails/v0.22.0/reference/guardrails-api-server/models/list-models.md)
- Guardrails API Server > Configurations [List Guardrails Configurations](https://docs.nvidia.com/nemo/guardrails/v0.22.0/reference/guardrails-api-server/configurations/list-guardrails-configurations.md)
- Guardrails API Server > Challenges [List Challenges](https://docs.nvidia.com/nemo/guardrails/v0.22.0/reference/guardrails-api-server/challenges/list-challenges.md)
- Guardrails API Server > Health [Get Server Health or Chat UI](https://docs.nvidia.com/nemo/guardrails/v0.22.0/reference/guardrails-api-server/health/get-root.md)

## OpenAPI Specification

The raw OpenAPI 3.1 specification for this API is available at:
- [OpenAPI JSON](https://docs.nvidia.com/nemo/guardrails/openapi.json)
- [OpenAPI YAML](https://docs.nvidia.com/nemo/guardrails/openapi.yaml)