> This page is for version 1.10.1 (default). > For other versions, use one of these documentation indexes: > - 1.10.1 (default): https://docs.nvidia.com/nim/nemoguard-jailbreakdetect/1.10.1/llms.txt > - 1.0.0: https://docs.nvidia.com/nim/nemoguard-jailbreakdetect/1.0.0/llms.txt > For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.nvidia.com/nim/nemoguard-jailbreakdetect/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nim/nemoguard-jailbreakdetect/_mcp/server. # Configuration > NVIDIA NemoGuard JailbreakDetect NIM is packaged as a container. You can set environment variables and specify command-line arguments to configure the microservice. NVIDIA NemoGuard JailbreakDetect NIM is packaged as a container. You can set environment variables and specify command-line arguments to configure the microservice. ## GPU Selection The NIM container is GPU-accelerated and uses NVIDIA Container Toolkit for access to GPUs on the host. You can specify the `--gpus all` command-line argument to the `docker run` command if the host has one or more of the same GPU model. If the host has a combination of GPUs, such as an A6000 and a GeForce display GPU, run the container on compute-capable GPUs only. Expose specific GPUs to the container by using either of the following methods: * Specify the `--gpus` argument, such as `--gpus="device=1"`. * Set the `NVIDIA_VISIBLE_DEVICES` environment variable, such as `-e NVIDIA_VISIBLE_DEVICES=1`. Run the `nvidia-smi -L` command to list the device IDs to specify in the argument or environment variable: ```output GPU 0: Tesla H100 (UUID: GPU-b404a1a1-d532-5b5c-20bc-b34e37f3ac46) GPU 1: NVIDIA GeForce RTX 3080 (UUID: GPU-b404a1a1-d532-5b5c-20bc-b34e37f3ac46) ``` Refer to [GPU Enumeration](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/docker-specialized.html#gpu-enumeration) in the *NVIDIA Container Toolkit* documentation for more information. ## Environment Variables The following table identifies the environment variables that are used in the container. Set environment variables with the `-e` command-line argument to the `docker run` command. | Name | Description | Default Value | | -------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------ | | `NGC_API_KEY` | Set this variable to the value of your personal NGC API key. | None | | `NIM_CACHE_PATH` | Specifies the fully qualified path, in the container, for downloaded models. | `/opt/nim/.cache` | | `NIM_GRPC_API_PORT` | Specifies the network port number, in the container, for gRPC access to the microservice. | `50051` | | `NIM_HTTP_API_PORT` | Specifies the network port number, in the container, for HTTP access to the microservice.Refer to [Publishing ports](https://docs.docker.com/get-started/docker-concepts/running-containers/publishing-ports/#publishing-ports) | | | in the Docker documentation for more information about host and container network ports. | `8000` | | | `NIM_HTTP_MAX_WORKERS` | Specifies the number of worker threads to start for HTTP requests. | `1` | | `NIM_HTTP_TRITON_PORT` | Specifies the network port number, in the container, for NVIDIA Triton Inference Server. | `8080` | | `NIM_IGNORE_MODEL_DOWNLOAD_FAIL` | When set to `true` and the microservice fails to download a model from NGC, the microservice continues to run rather than exit. | | | This environment variable can be useful in an air-gapped environment. | `false` | | | `NIM_LOGGING_JSONL` | When set to `true`, the microservice creates log records in the JSONL format. | `false` | | `NIM_LOG_LEVEL` | Specifies the logging level. | | | The microservice supports the following values: DEBUG, INFO, WARNING, ERROR, and CRITICAL. | `INFO` | | | `NIM_MANIFEST_PATH` | Specifies the fully qualified path, in the container, for the model manifest YAML file. | `/opt/nim/etc/default/model_manifest.yaml` | | `NIM_MODEL_PROFILE` | Specifies the model profile ID to use with the container. | | | By default, the container attempts to automatically match the host GPU model and GPU count with the optimal model profile. | None | | | `NIM_SERVED_MODEL_NAME` | Specifies the model names used in the API. | | | Specify multiple names in a comma-separated list. | | | | If you specify multiple names, the server responds to any of the names. | | | | The name in the model field of a response is the first name in this list. | | | | By default, the model is inferred from the `model_manifest.yaml`. | None | | | `NIM_TRITON_LOG_VERBOSE` | When set to `1`, the container starts NVIDIA Triton Inference Server with verbose logging. | `0` | | `NIM_TRITON_GRPC_PORT` | Specifies the gRPC port number, for NVIDIA Triton Inference Server. | `8001` | ## Volumes The container stores downloaded models in `/opt/nim/.cache` by default. Set `NIM_CACHE_PATH` to use a different path inside the container. | Container path or variable | Description | | ------------------------------------- | ----------------------------------------- | | `/opt/nim/.cache` or `NIM_CACHE_PATH` | Container location for downloaded models. | To keep the model cache between runs, create a directory on the host: ```bash mkdir -p ~/.cache/nim ``` Bind-mount it to the container path when you run the container: ```bash -v ~/.cache/nim:/opt/nim/.cache -u "$(id -u)" ``` Without a bind mount, the container downloads the model again each time it starts. The `-u "$(id -u)"` option runs the container with your user ID to avoid file permission issues. If you set `NIM_CACHE_PATH` to a different container path, use that path as the bind mount destination.