Configure NVIDIA NIM for Image OCR (NeMo Retriever OCR v1)

NVIDIA NIM for Image OCR (NeMo Retriever OCR v1) uses docker containers under the hood. Each NIM is its own Docker container and there are several ways to configure it. The remainder of this documentation describes the ways to configure a NIM container.

Use this documentation to learn how to configure NVIDIA NIM for Image OCR (NeMo Retriever OCR v1).

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:

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 in the NVIDIA Container Toolkit documentation for more information.

Shared Memory flag

Tokenization uses Triton’s Python backend capabilities that scales with the number of CPU cores available. You may need to increase the available shared memory given to the microservice container.

Example providing 1g of shared memory:

docker run ... --shm-size=1g ...

PID Limit

In certain deployment or container runtime environments, default process and thread limits (PID limits) can interfere with NIM startup. These set limits are set by Docker, Podman, Kubernetes, or the operating system.

If the PID limit is too low, you might see symptoms such as:

• NIM starts up partially, but fails to reach ready state, and then stalls.

• NIM starts up partially, but fails to reach ready state, and then crashes.

• NIM serves a small number of requests, and then fails.

To verify that PID limits are impacting the NIM container, you can remove or adjust the PID limit at the container, node, and operating system level. Removing the PID limit and then checking for success is a useful diagnostic step.

• To increase the PID limit in a docker run command, set --pids-limit=-1. For details, see docker container run.

• To increase the PID limit in a podman run command, --pids-limit=-1. For details, see Podman pids-limit.

• To increase the PID limit in Kubernetes, set the PodPidsLimit on the kubelet on each node. For details, see your Kubernetes distribution specific documentation.

• To increase the PID limit at the operating system level, see your OS-specific documentation.

Environment Variables

Note

The following NIMs do not support NIM_SERVED_MODEL_NAME:

• nemoretriever-graphic-elements-v1

• nemoretriever-page-elements-v2

• nemoretriever-table-structure-v1

• PaddleOCR

• nemoretriever-ocr-v1

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 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_LOG_LEVEL	Specifies the logging level. The microservice supports the following values: DEBUG, INFO, WARNING, ERROR, and CRITICAL.	INFO
NIM_LOGGING_JSONL	When set to true, the microservice creates log records in the JSONL format.	false
NIM_MANIFEST_ALLOW_UNSAFE	Set to 1 to enable selection of a model profile that is not included in the original model_manifest.yaml or a profile that is not detected to be compatible with the deployed hardware.	0
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_REPOSITORY_OVERRIDE	If set to a non-empty string, the NIM_REPOSITORY_OVERRIDE value replaces the hard-coded location of the repository and the protocol for access to the repository. The structure of the value for this environment variable is as follows: <repository type>://<repository location>. Only the protocols ngc://, s3://, and https:// are supported, and only the first component of the URI is replaced. For example: - If the URI in the manifest is ngc://org/meta/llama3-8b-instruct:hf?file=config.json and NIM_REPOSITORY_OVERRIDE=ngc://myrepo.ai/, the domain name for the API endpoint is set to myrepo.ai. - If NIM_REPOSITORY_OVERRIDE=s3://mybucket/, the result of the replacement will be s3://mybucket/nim%2Fmeta%2Fllama3-8b-instruct%3Ahf%3Ffile%3Dconfig.json. - If NIM_REPOSITORY_OVERRIDE=https://mymodel.ai/some_path, the result of the replacement will be https://mymodel.ai/some_path/nim%2Fmeta%2Fllama3-8b-instruct%3Ahf%3Ffile%3Dconfig.json. This repository override feature supports basic authentication mechanisms: - https assumes authorization using the Authorization header and the credential value in NIM_HTTPS_CREDENTIAL. - ngc requires a credential in the NGC_API_KEY environment variable. - s3 requires the environment variables AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, and (if using temporary credentials) AWS_SESSION_TOKEN.	None
NIM_TRITON_CUDA_MEMORY_POOL_MB	For the NVIDIA Triton Inference Server, specify the byte size for the CUDA memory pool for all GPUs visible to the container.	By default, Image Retriever NIMs automatically set the CUDA memory pool based on the maximum input data size for the loaded TensorRT engine. However, you might want to increase the CUDA memory pool size when you enable dynamic batching or run highly concurrent workloads. A typical error message that indicates that you should increase the CUDA memory pool is RuntimeError: CUDA error: invalid argument. When you run NIMs with NIM_TRITON_EXTRA_ARGS, any arguments to the underlying tritonserver command are overridden. If you specify NIM_TRITON_EXTRA_ARGS, you must include the options that are automatically configured for the underlying tritonserver command. For an up-to-date reference for what these arguments are, run the NIM without NIM_TRITON_EXTRA_ARGS, inspect the arguments used for the tritonserver process inside the container, and then run the NIM with NIM_TRITON_EXTRA_ARGS and include the extra arguments.
NIM_TRITON_DYNAMIC_BATCHING_MAX_QUEUE_DELAY_MICROSECONDS	For the NVIDIA Triton Inference Server, sets the max queue delayed time to allow other requests to join the dynamic batch. For more information, refer to the Triton User Guide.	100us (microseconds)
NIM_TRITON_GRPC_PORT	Specifies the gRPC port number, for NVIDIA Triton Inference Server.	8001
NIM_TRITON_LOG_VERBOSE	When set to 1, the container starts NVIDIA Triton Inference Server with verbose logging.	0
NIM_TRITON_MAX_QUEUE_SIZE	Sets the max queue size for the underlying Triton instance. For more information, refer to the Triton User Guide. Triton returns an InferenceServerException on new requests if you exceed the max queue size.	None
NIM_TRITON_MAX_BATCH_SIZE	Specify the maximum batch size that the underlying Triton instance can process. The value must be less than or equal to maximum batch size that was used to compile the engine. By default, the NIM uses the maximum possible batch size for a given model and GPU. To decrease the memory footprint of the server, choose a smaller maximum batch size. If the model uses the tensorrt backend, the value must exactly match a batch size in one of the engine’s profiles. Only discrete values are supported. For valid values, and their estimated memory footprint, refer to the support matrix page.	None
NIM_TRITON_OPTIMIZATION_MODE	Controls which TensorRT engine profiles are loaded when the NIM’s Triton server starts. Specify default to load one profile that spans the full range of supported batch sizes. Specify perf_opt to load all profiles except for the default profile. Specify vram_opt to load only the first (smallest) profile.	default

Volumes

The following table identifies the paths that are used in the container. Use this information to plan the local paths to bind mount into the container.

Container Path	Description	Example
/opt/nim/.cache or NIM_CACHE_PATH	Specifies the path, relative to the root of the container, for downloaded models. The typical use for this path is to bind mount a directory on the host with this path inside the container. For example, to use ~/.cache/nim on the host, run mkdir -p ~/.cache/nim before you start the container. When you start the container, specify the -v ~/.cache/nim:/opt/nim/.cache -u $(id -u) arguments to the docker run command. If you do not specify a bind or volume mount, as shown in the -v argument in the preceding command, the container downloads the model each time you start the container. The -u $(id -u) argument runs the container with your user ID to avoid file system permission issues and errors.	-v ~/.cache/nim:/opt/nim/.cache -u $(id -u)