Configuration¶
Configuration is controlled through the Config
object. You can set configuration variables via the .env
file. If you don't have a .env
file, create a copy of .env.template
in your AutoGPT
folder and name it .env
.
Environment Variables¶
AI_SETTINGS_FILE
: Location of the AI Settings file relative to the AutoGPT root directory. Default: ai_settings.yamlAUDIO_TO_TEXT_PROVIDER
: Audio To Text Provider. Only option currently ishuggingface
. Default: huggingfaceAUTHORISE_COMMAND_KEY
: Key response accepted when authorising commands. Default: yAZURE_CONFIG_FILE
: Location of the Azure Config file relative to the AutoGPT root directory. Default: azure.yamlBROWSE_CHUNK_MAX_LENGTH
: When browsing website, define the length of chunks to summarize. Default: 3000BROWSE_SPACY_LANGUAGE_MODEL
: spaCy language model to use when creating chunks. Default: en_core_web_smCHAT_MESSAGES_ENABLED
: Enable chat messages. OptionalDISABLED_COMMAND_CATEGORIES
: Command categories to disable. Command categories are Python module names, e.g. autogpt.commands.execute_code. See the directoryautogpt/commands
in the source for all command modules. Default: NoneELEVENLABS_API_KEY
: ElevenLabs API Key. Optional.ELEVENLABS_VOICE_ID
: ElevenLabs Voice ID. Optional.EMBEDDING_MODEL
: LLM Model to use for embedding tasks. Default: text-embedding-ada-002EXECUTE_LOCAL_COMMANDS
: If shell commands should be executed locally. Default: FalseEXIT_KEY
: Exit key accepted to exit. Default: nFAST_LLM
: LLM Model to use for most tasks. Default: gpt-3.5-turboGITHUB_API_KEY
: Github API Key. Optional.GITHUB_USERNAME
: GitHub Username. Optional.GOOGLE_API_KEY
: Google API key. Optional.GOOGLE_CUSTOM_SEARCH_ENGINE_ID
: Google custom search engine ID. Optional.HEADLESS_BROWSER
: Use a headless browser while AutoGPT uses a web browser. Setting toFalse
will allow you to see AutoGPT operate the browser. Default: TrueHUGGINGFACE_API_TOKEN
: HuggingFace API, to be used for both image generation and audio to text. Optional.HUGGINGFACE_AUDIO_TO_TEXT_MODEL
: HuggingFace audio to text model. Default: CompVis/stable-diffusion-v1-4HUGGINGFACE_IMAGE_MODEL
: HuggingFace model to use for image generation. Default: CompVis/stable-diffusion-v1-4IMAGE_PROVIDER
: Image provider. Options aredalle
,huggingface
, andsdwebui
. Default: dalleIMAGE_SIZE
: Default size of image to generate. Default: 256MEMORY_BACKEND
: Memory back-end to use. Currentlyjson_file
is the only supported and enabled backend. Default: json_fileMEMORY_INDEX
: Value used in the Memory backend for scoping, naming, or indexing. Default: auto-gptOPENAI_API_KEY
: REQUIRED- Your OpenAI API Key.OPENAI_ORGANIZATION
: Organization ID in OpenAI. Optional.PLAIN_OUTPUT
: Plain output, which disables the spinner. Default: FalsePLUGINS_CONFIG_FILE
: Path of the Plugins Config file relative to the AutoGPT root directory. Default: plugins_config.yamlPROMPT_SETTINGS_FILE
: Location of the Prompt Settings file relative to the AutoGPT root directory. Default: prompt_settings.yamlREDIS_HOST
: Redis Host. Default: localhostREDIS_PASSWORD
: Redis Password. Optional. Default:REDIS_PORT
: Redis Port. Default: 6379RESTRICT_TO_WORKSPACE
: The restrict file reading and writing to the workspace directory. Default: TrueSD_WEBUI_AUTH
: Stable Diffusion Web UI username:password pair. Optional.SD_WEBUI_URL
: Stable Diffusion Web UI URL. Default: http://localhost:7860SHELL_ALLOWLIST
: List of shell commands that ARE allowed to be executed by AutoGPT. Only applies ifSHELL_COMMAND_CONTROL
is set toallowlist
. Default: NoneSHELL_COMMAND_CONTROL
: Whether to useallowlist
ordenylist
to determine what shell commands can be executed (Default: denylist)SHELL_DENYLIST
: List of shell commands that ARE NOT allowed to be executed by AutoGPT. Only applies ifSHELL_COMMAND_CONTROL
is set todenylist
. Default: sudo,suSMART_LLM
: LLM Model to use for "smart" tasks. Default: gpt-4STREAMELEMENTS_VOICE
: StreamElements voice to use. Default: BrianTEMPERATURE
: Value of temperature given to OpenAI. Value from 0 to 2. Lower is more deterministic, higher is more random. See https://platform.openai.com/docs/api-reference/completions/create#completions/create-temperatureTEXT_TO_SPEECH_PROVIDER
: Text to Speech Provider. Options aregtts
,macos
,elevenlabs
, andstreamelements
. Default: gttsUSER_AGENT
: User-Agent given when browsing websites. Default: "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36"USE_AZURE
: Use Azure's LLM Default: FalseUSE_WEB_BROWSER
: Which web browser to use. Options arechrome
,firefox
,safari
oredge
Default: chromeWIPE_REDIS_ON_START
: Wipes data / index on start. Default: True