The CLI

promptimize

💡¡promptimize!💡 CLI. p9e works too!

promptimize [OPTIONS] COMMAND [ARGS]...

report

report on how your suites of prompts are performing

promptimize report [OPTIONS] PATH

Options

-g, --groupby <groupby>

GROUPBY

Arguments

PATH

Required argument

run

run some prompts

promptimize run [OPTIONS] PATH

Options

-v, --verbose

Trigger more verbose output

-f, --force

Force run, do not skip

-h, --human

Human review, allowing a human to review and force pass/fail each prompt case

-r, --repair

Only re-run previously failed

-x, --dry-run

DRY run, don’t call the API

--shuffle

Shuffle the prompts in a random order

-s, --style <style>

json or yaml formatting

Options:

json | yaml

-m, --max-tokens <max_tokens>

max_tokens passed to the model

-l, --limit <limit>

limit how many prompt cases to run in a single batch

-t, --temperature <temperature>

max_tokens passed to the model

-e, --engine <engine>

model as accepted by the openai API

-k, --key <key>

The keys to run

-o, --output <output>

-s, --silent

Arguments

PATH

Required argument