CLI

LF AI Platform command line interface (CLI) is distributed as a lightweight Python package that allows programmatic interface for using LF AI Platform

You can use --help with any command of the CLI to understand what it does and what are its arguments.

lf --help
lf <command> --help

General

configure	Configure AI Platform CLI options.
switch	Switch AI app context.
status	Shows the current AI app context and the saved AI Platform CLI options.
init	Initialize a project in the current directory.
run	Create one or more evaluations from a run config file along with their dependencies and run them as an evaluation run or evaluation plan run.
rerun	Rerun an evaluation run with a given ID.
skills	Load LatticeFlow AI Platform agentic skills and download supporting resources.
dump	Dump an AI app with its evaluation runs, or all entities to a directory.
restore	Restore an AI app with its evaluation runs, or global entities from a directory.

Entity & Evaluation Management

add	Create/update entities from run config or entity YAML files.
set	Set entities from run config (policies, risk-policies).
list	List entities as JSON or in a table.
delete	Delete entities by key (or ID for evaluation runs).
overview	Show overview of entities (currently policies, risk policies, evaluation runs, and evaluation plan runs are supported).
export	Export entities or download evaluation run results.
cancel	Cancel evaluation run by ID.
test	Test models, dataset generation, and task specifications.
regenerate	Regenerate datasets using a dataset generator.

Administration

user	User commands.
secret	Secret management commands.
integration	Third-party integration commands.
tenant	Control plane (tenant & user) commands.

Environment Variables

Environment variables can be used in YAML files to pass sensitive or repetitive information that you might want to reuse. These can be specified in an .env. The CLI reads the .env in the current working directory.

For example, you can define the following .env file:

.env

MY_API_KEY="my_api_key"

and then use it within the configuration files as follows:

...
config:
  ...
  api_key: $MY_API_KEY