17.3. Getting Started

Thie document describes clara commands.

17.3.1. create model

Create a model from a directory. The Model Directory must conform to TRITON server specifications.

17.3.1.1. Usage

$ clara create model -p [MODEL_DIRECTORY] -t [MODEL_TYPE] [--raw]

17.3.1.2. Flags

Name Shorthand Default Usage
path p   Model path
type t   Model Type {“tensorflow”, “tensorrt”, “pytorch”, “unknown”}
raw r false Show output in raw format

17.3.2. list model

Lists information about models

17.3.2.1. Usage

$ clara list models [--quiet]

17.3.2.2. Flags

Name Shorthand Default Usage
quiet q false Only show model ids

17.3.3. delete models

Delete models.

17.3.3.1. Usage

$ clara delete models [MODEL_ID]...

17.3.3.2. Arguments

Name Default Usage
MODEL_ID   The full or partial unique identifier of the model. Partial unique identifiers can be used so long as it matches from left-to-right and uniquely identifies a model.

All the model ids passed as argument are deleted.

17.3.4. create job

Creates a job from a name, pipeline id, job priority and file or directory.

17.3.4.1. Usage

$ clara create job -n NAME -p PIPELINE_ID [-f [FILE | DIRECTORY]] [-i JOB_PRIORITY] [--start]

17.3.4.2. Flags

Name Shorthand Default Usage
name n   Name of the job
pipeline p   Pipeline id
priority i normal Job Priority {“low”, “normal”, “high”, “immediate}”
files f   Filename or directory to files used to create the job
start s false Start the job (without any arguments) after creating it
raw r false Show output in raw format

17.3.5. start job

Starts a created job from job id.

17.3.5.1. Usage

$ clara start job -j JOB_ID [-a KEY=VALUE]...

17.3.5.2. Flags

Name Shorthand Default Usage
args a   Argument to the job in KEY=VALUE format
job j   Job id

17.3.6. create pipelines

Creates a clara pipeline.

17.3.6.1. Usage

$ clara create pipeline -p PIPELINE_DEFINITION_FILE

17.3.6.2. Flags

Name Shorthand Default Usage
path p   Pipeline definition file path
raw r false Show output in raw format

17.3.7. list pipelines

Lists pipelines.

17.3.7.1. Usage

$ clara list pipelines

17.3.7.2. Flags

Name Shorthand Default Usage
quiet q false Only show pipeline ids

17.3.8. describe pipeline

Prints definition of the pipeline.

17.3.8.1. Usage

$ clara describe pipeline -p PIPELINE_ID

17.3.8.2. Flags

Name Shorthand Default Usage
pipeline p   The full or partial unique identifier of the Clara pipeline. Partial unique identifiers can be used so long as it matches from left-to-right and uniquely identifies a pipeline.

17.3.9. list jobs

Lists jobs.

17.3.9.1. Usage

$ clara list jobs

17.3.9.2. Flags

Name Shorthand Default Usage
quiet q false Only show job ids
all   false List all jobs including canceled ones
canceled   false List only canceled jobs
evicted   false List only evicted jobs
faulted   false List only faulted jobs
healthy   false List only healthy jobs
pending   false List only pending jobs
running   false List only running jobs
stopped   false List only stopped jobs
terminated   false List only terminated jobs

17.3.10. cancel jobs

Submit reuqest to cancel job(s).

17.3.10.1. Usage

$ clara cancel jobs [-j JOB_ID1,JOB_ID2...] [--all]
$ clara cancel jobs [-j JOB_ID1,JOB_ID2...] [--all]

17.3.10.2. Flags

Name Shorthand Default Usage
all   false Cancel all jobs

17.3.10.3. Arguments

Name Default Usage
JOB_ID   The full or partial unique identifier of the Clara job. Partial unique identifiers can be used so long as it matches from left-to-right and uniquely identifies a job.

17.3.11. upload payload

Uploads payloads

17.3.11.1. Usage

$ clara upload payload -p PAYLOAD_ID -f {FILE | DIRECTORY}

17.3.11.2. Flags

Name Shorthand Default Usage
files f   Payload file or directory to read from
payload p   Payload identifier

17.3.12. delete payloads

Delete payloads.

17.3.12.1. Usage

$ clara delete payloads -p PAYLOAD_ID1[,PAYLOAD_ID2...]
$ clara delete payload -p PAYLOAD_ID1[,PAYLOAD_ID2...]

17.3.12.2. Arguments

Name Default Usage
PAYLOAD_ID   Full unique identifier of the clara payload.

17.3.13. download

Download files associated with the selected job.

17.3.13.1. Usage

$ clara download JOB_ID:SRC_PATH [DEST_PATH] [flags]

17.3.13.2. Arguments

Name Default Usage
JOB_ID   The full or partial unique identifier of the Clara job from which to download content from. Partial unique identifiers can be used so long as it matches from left-to-right and uniquely identifies a job.
SRC_PATH   Source path of the file(s) to download. File names are relative to the root of the payload. Supports simple glob style pattern matching.
DEST_PATH . Optional destination path where the files will be downloaded. By default file(s) will be downloaded to the current directory.

17.3.14. describe job

Prints the information and status of the job.

17.3.14.1. Usage

$ clara describe job -j JOB_ID

17.3.14.2. Flags

Name Shorthand Default Usage
job j   The full or partial unique identifier of the Clara job from which to download content from. Partial unique identifiers can be used so long as it matches from left-to-right and uniquely identifies a job.

17.3.15. config

Configures NGC credentials for use by CLI.

17.3.15.1. Usage

If –orgteam is not specified, the orgteam defaults to ‘nvidia/clara’ which points to the publicly available Clara NGC artifacts

$ clara config [flags]

17.3.15.2. Flags

Name Shorthand Default Usage
key     NGC API Key
orgteam   nvidia/clara Org and team (input format: “{org}[/{team}]” team is optional)
yes y false Bypass the prompt

17.3.16. logs

Read clara job operator logs.

17.3.16.1. Usage

$ clara logs [flags]

17.3.16.2. Flags

Name Shorthand Default Usage
job j   Clara Job Id
operator o   Clara Job Operator

17.3.17. version

Displays the clara cli and clara platform version info

17.3.17.1. Usage

$ clara version