> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/1.0.0/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/_mcp/server. # 1.0.0 ## Docs - [Release Notes](https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/1.0.0/release-notes.md): This is the first release of Llama 3.1 NemoGuard 8B TopicControl NIM. The microservice serves a GPU-accelerated LLM model for conversational dialog moderation to keep conversations on-topic and build - [Getting Started with TopicControl](https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/1.0.0/getting-started.md): A host with Docker Engine. Refer to the instructions from Docker. - [Prompt Templates](https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/1.0.0/prompt-template.md): Llama 3.1 NemoGuard 8B TopicControl NIM performs input moderation, such as ensuring that the user prompt is consistent with rules specified as part of the system prompt. - [Integrating with NeMo Guardrails](https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/1.0.0/integrate-guardrails.md): NeMo Guardrails uses the LangChain ChatNVIDIA connector to connect to a locally running NIM microservice like Llama 3.1 NemoGuard 8B TopicControl NIM. The topic control microservice exposes the standa - [Configuration](https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/1.0.0/configuration.md): Llama 3.1 NemoGuard 8B TopicControl NIM is packaged as a container. You can set environment variables and specify command-line arguments to configure the microservice. - [Air Gap Deployment](https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/1.0.0/air-gapped.md): The microservice supports serving models in an air gap system–also known as air wall, air-gapping, or disconnected network. - [Support Matrix](https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/1.0.0/support-matrix.md): The models for NVIDIA NIM microservices use model engines that are tuned for specific NVIDIA GPU models, number of GPUs, precision, and so on. NVIDIA produces model engines for several popular combina - [Observability](https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/1.0.0/observability.md): Llama 3.1 NemoGuard 8B TopicControl NIM supports exporting metrics and traces in an OpenTelemetry-compatible format. Additionally, the microservice and its underlying NVIDIA Triton Inference Server ex ## API Docs - API Reference [OpenAI-compatible chat endpoint](https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/1.0.0/api-reference/create-chat-completion-v-1-chat-completions-post.md) - API Reference [OpenAI-compatible completions endpoint](https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/1.0.0/api-reference/create-completion-v-1-completions-post.md) - API Reference [Service ready check](https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/1.0.0/api-reference/health-v-1-health-ready-get.md) - API Reference [Service liveness check](https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/1.0.0/api-reference/health-ready-v-1-health-live-get.md) - API Reference [List available models](https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/1.0.0/api-reference/show-available-models-v-1-models-get.md) - API Reference [Metadata](https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/1.0.0/api-reference/metadata-v-1-metadata-get.md) - API Reference [Returns version information about this NIM](https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/1.0.0/api-reference/show-version-v-1-version-get.md) - API Reference [Metrics](https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/1.0.0/api-reference/metrics-v-1-metrics-get.md) - API Reference [License](https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/1.0.0/api-reference/license-v-1-license-get.md) - API Reference [Manifest](https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/1.0.0/api-reference/manifest-v-1-manifest-get.md) ## OpenAPI Specification The raw OpenAPI 3.1 specification for this API is available at: - [OpenAPI JSON](https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/openapi.json) - [OpenAPI YAML](https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/openapi.yaml) > **Note:** This page contains both a page directory (above) and the landing page content (below). The page directory is generated for agent use and does not appear on the landing page. > For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/1.0.0/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/_mcp/server. # Llama 3.1 NemoGuard 8B TopicControl NIM > The microservice serves a GPU-accelerated LLM model for conversational dialog moderation to keep conversations on-topic and build trustworthy LLM applications. ## About the Microservice The microservice serves a GPU-accelerated LLM model for conversational dialog moderation to keep conversations on-topic and build trustworthy LLM applications. The model is a dialog moderation model trained by NVIDIA from a Llama 3.1 8B Instruct base model. The model is trained using the CantTalkAboutThis dataset – a carefully curated collection of 10 thousand dialogue samples – to detect and ensure user interactions are in line with developer-defined guidelines. The dataset has been released with a commercially friendly license. In contrast with content moderation models such as Shield Gemma and Llama Guard 3, that rely on a pre-defined taxonomy of harms, this model enables developers to specify their own boundaries regarding allowed and disallowed subjects. This adaptability makes it a more versatile and general-purpose complement to content moderation models. ## License | Component | Artifact Type | Artifact Licenses | | --------------------------------------- | ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Llama 3.1 NemoGuard 8B TopicControl NIM | [Container](https://registry.ngc.nvidia.com/orgs/nim/teams/nvidia/containers/llama-3.1-nemoguard-8b-topic-control) | [NVIDIA Software License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-software-license-agreement/) and the [Product-Specific Terms for NVIDIA AI Products](https://www.nvidia.com/en-us/agreements/enterprise-software/product-specific-terms-for-ai-products/). | | Llama Nemotron Topic Guard V1 | [Model](https://registry.ngc.nvidia.com/orgs/nim/teams/nvidia/models/llama-3.1-nemoguard-8b-topic-control) | [NVIDIA Community Model License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-community-models-license/). [Llama 3.1 Community License Agreement](https://www.llama.com/llama3_1/license/). Built with Llama. | ## Related Information * [CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues](https://aclanthology.org/2024.findings-emnlp.713.pdf). * [CantTalkAboutThis](https://huggingface.co/datasets/nvidia/CantTalkAboutThis-Topic-Control-Dataset) topic-control dataset on Hugging Face Hub. * The microservice is based on [NVIDIA NIM for LLMs](https://docs.nvidia.com/nim/large-language-models/latest/introduction.html).