Environment Variables#

Configure NIM for BGR behavior at container startup using the following environment variables.

Required Variables#

The following variable is required to download models from NGC:

Variable	Required	Default	Description
`NGC_API_KEY`	Yes (for MACE auto-download)	–	NGC authentication key. Required for the container to download the bundled MACE model from NGC.

Use the following variables to configure the NIM:

Variable	Type	Default	Description
`ALCHEMI_NIM_MODEL_TYPE`	string	`"mace"`	Model type: `mace`, `aimnet2`, or `tensornet`.
`ALCHEMI_NIM_MODEL_PATH`	string	null	Path to the model file or directory inside the container.
`ALCHEMI_NIM_PBC`	bool	true	Periodic boundary conditions mode.
`ALCHEMI_NIM_BATCH_SIZE`	int	null	Fixed batch size (`null` enables automatic estimation at startup).
`ALCHEMI_NIM_BGR_OPTTOL`	float	0.005	Force tolerance (eV/Å). Can be overridden per request.
`ALCHEMI_NIM_BGR_MAX_STEPS`	int	2000	Maximum optimization steps. Can be overridden per request.
`ALCHEMI_NIM_BGR_CELLOPT`	bool	false	Enable cell optimization. Can be overridden per request.
`ALCHEMI_NIM_BGR_OPTTOL_PRESSURE`	float	0.5	Pressure tolerance (kBar) for cell optimization. Can be overridden per request.
`ALCHEMI_NIM_BGR_OPTIMIZER_PRESET`	string	`"materials"`	Optimizer preset: `materials` or `molecules`.
`ALCHEMI_NIM_DFT3_ENABLED`	bool	false	Enable DFT-D3(BJ) dispersion correction.
`ALCHEMI_NIM_DFT3_PARAM`	string (JSON)	null	JSON string containing custom DFT-D3(BJ) parameters (for example, `{"s8": 0.3908, "a1": 0.5660, "a2": 3.1280}`). Refer to the ALCHEMI Toolkit-Ops documentation for details.

Use the following variables to configure the container runtime:

Variable	Required	Default	Description
`NIM_HTTP_API_PORT`	No	`8000`	HTTP port for the inference API.
`NIM_DISABLE_MODEL_DOWNLOAD`	No	false	Whether to automatically download the default MACE model from NGC.