akka optimize
Own your intelligence: cost, models, training and routing
Synopsis
akka-optimize drives the Akka Optimize services.
The command tree is written to drop into akka optimize unchanged, so nouns are plural, writes are apply, and --force is the only flag that skips a confirmation.
Options
--force Skip the confirmation prompt
-h, --help help for optimize
--jq string Filter the JSON output with a jq expression
--json string Output JSON with only these fields; --json= lists the fields a command offers
--no-color Print without color, as NO_COLOR does
--region string Region to use if the project has more than one region
--trainer-url string Trainer service URL (default http://localhost:9001, or TRAINER_URL)
--url string Optimize service URL (default http://localhost:9010, or OPTIMIZE_URL)
Options inherited from parent commands
--cache-file string location of cache file (default "~/.akka/cache.yaml")
--config string location of config file (default "~/.akka/config.yaml")
--context string configuration context to use
--disable-prompt Disable all interactive prompts when running akka commands. If input is required, defaults will be used, or an error will be raised.
This is equivalent to setting the environment variable AKKA_DISABLE_PROMPTS to true.
-o, --output string set output format to one of [text,json,json-compact,go-template=] (default "text")
--page-mode string the mode for paging, either paged, buffered or auto. (default "auto")
-q, --quiet set quiet output (helpful when used as part of a script)
--timeout duration client command timeout (default 10s)
--use-grpc-web use grpc-web when talking to Akka APIs. This is useful when behind corporate firewalls that decrypt traffic but don't support HTTP/2.
--verbose set verbose output
SEE ALSO
-
akka - Akka control
-
akka optimize callers - The callers the spend figures are attributed to
-
akka optimize captures - Recorded interaction artifacts, read off a filesystem
-
akka optimize datasets - Manage training and evaluation datasets
-
akka optimize eval - Datasets, experiments and the evaluators that score them
-
akka optimize incidents - The incident feed, unioned from its sources
-
akka optimize models - The corporate model registry
-
akka optimize pricing-catalog - What a unit of usage costs, and when that price was in force
-
akka optimize redteam - Adversarial datasets, red-team campaigns, techniques, hazards and corpora
-
akka optimize registry - The artifact registry: named models, datasets and bundles
-
akka optimize routing-classifiers - Named pointers to model providers, immutable once registered
-
akka optimize routing-policies - What serves a use-case, and in what share
-
akka optimize rulesets - Attribute-matching rules that choose a destination
-
akka optimize spend - What a period consumed, what it cost, and what one conversation cost
-
akka optimize status - Which services are answering, and at what address
-
akka optimize traffic - Recorded LLM exchanges, run through the gateway router’s routing chain
-
akka optimize trained-models - Manage trained models and baselines
-
akka optimize training - Base models, workloads, runs, snapshots, comparisons, pipelines, evaluations, endpoints and their data
-
akka optimize use-cases - Discovered use-cases, and the manifests frozen from them