[Tut] Auto-GPT: Command Line Arguments and Usage

[xSicKxBot]

Auto-GPT: Command Line Arguments and Usage

4/5 – (1 vote)

This quick guide assumes you have already set up Auto-GPT. If you haven’t, follow our in-depth guide on the Finxter blog.

Use

Code:

./run.sh --help

(Linux/macOS) or

Code:

.\run.bat --help

(Windows) to list command line arguments. For Docker, substitute

Code:

docker-compose run --rm auto-gpt

in examples.

Common Auto-GPT arguments include:

Code:

--ai-settings <filename>

,

Code:

--prompt-settings <filename>

, and

Code:

--use-memory <memory-backend>

. Short forms such as

Code:

-m

for

Code:

--use-memory

exist. Substitute any angled brackets (

Code:

<>

) with your desired values.

Enable Text-to-Speech using

Code:

./run.sh --speak

.

Use continuous mode (potentially hazardous, may run indefinitely) with

Code:

./run.sh --continuous

. Exit with

Code:

Ctrl+C

.

Use Self-Feedback mode (increases token usage, costs) by entering

Code:

S

in the input field.

Run GPT-3.5 only mode with

Code:

./run.sh --gpt3only

or set

Code:

SMART_LLM_MODEL

in

Code:

.env

to

Code:

gpt-3.5-turbo

. For GPT-4 only, use

Code:

./run.sh --gpt4only

(raises API costs).

Find logs in

Code:

./output/logs

, debug with

Code:

./run.sh --debug

.

Disable commands by setting

Code:

DISABLED_COMMAND_CATEGORIES

in

Code:

.env

. For instance, to disable coding features, use:

Code:

DISABLED_COMMAND_CATEGORIES=autogpt.commands.analyze_code,autogpt.commands.execute_code,autogpt.commands.gi

.

Okay, this was dry, here’s a more fun article:

Recommended: 30 Creative AutoGPT Use Cases to Make Money Online