mirror of
https://github.com/Significant-Gravitas/AutoGPT.git
synced 2026-01-08 22:58:01 -05:00
Clean up and fix issues with env configuration and .env.template (#4630)
Co-authored-by: merwanehamadi <merwanehamadi@gmail.com>
This commit is contained in:
Erik Peterson
203
.env.template
203
.env.template
@@ -1,10 +1,16 @@
|
||||
# For further descriptions of these settings see docs/configuration/options.md or go to docs.agpt.co
|
||||
|
||||
################################################################################
|
||||
### AUTO-GPT - GENERAL SETTINGS
|
||||
################################################################################
|
||||
|
||||
## OPENAI_API_KEY - OpenAI API Key (Example: my-openai-api-key)
|
||||
OPENAI_API_KEY=your-openai-api-key
|
||||
|
||||
## EXECUTE_LOCAL_COMMANDS - Allow local command execution (Default: False)
|
||||
## RESTRICT_TO_WORKSPACE - Restrict file operations to workspace ./auto_gpt_workspace (Default: True)
|
||||
# EXECUTE_LOCAL_COMMANDS=False
|
||||
|
||||
## RESTRICT_TO_WORKSPACE - Restrict file operations to workspace ./auto_gpt_workspace (Default: True)
|
||||
# RESTRICT_TO_WORKSPACE=True
|
||||
|
||||
## USER_AGENT - Define the user-agent used by the requests library to browse website (string)
|
||||
@@ -18,67 +24,41 @@
|
||||
|
||||
## AUTHORISE COMMAND KEY - Key to authorise commands
|
||||
# AUTHORISE_COMMAND_KEY=y
|
||||
|
||||
## EXIT_KEY - Key to exit AUTO-GPT
|
||||
# EXIT_KEY=n
|
||||
|
||||
## PLAIN_OUTPUT - Enabeling plain output will disable spinner (Default: False)
|
||||
## Note: Spinner is used to indicate that Auto-GPT is working on something in the background
|
||||
## PLAIN_OUTPUT - Plain output, which disables the spinner (Default: False)
|
||||
# PLAIN_OUTPUT=False
|
||||
|
||||
## DISABLED_COMMAND_CATEGORIES - The list of categories of commands that are disabled. Each of the below are an option:
|
||||
## autogpt.commands.analyze_code
|
||||
## autogpt.commands.audio_text
|
||||
## autogpt.commands.execute_code
|
||||
## autogpt.commands.file_operations
|
||||
## autogpt.commands.git_operations
|
||||
## autogpt.commands.google_search
|
||||
## autogpt.commands.image_gen
|
||||
## autogpt.commands.improve_code
|
||||
## autogpt.commands.web_selenium
|
||||
## autogpt.commands.write_tests
|
||||
## autogpt.app
|
||||
## autogpt.commands.task_statuses
|
||||
## For example, to disable coding related features, uncomment the next line
|
||||
# DISABLED_COMMAND_CATEGORIES=autogpt.commands.analyze_code,autogpt.commands.execute_code,autogpt.commands.git_operations,autogpt.commands.improve_code,autogpt.commands.write_tests
|
||||
## DISABLED_COMMAND_CATEGORIES - The list of categories of commands that are disabled (Default: None)
|
||||
# DISABLED_COMMAND_CATEGORIES=
|
||||
|
||||
|
||||
################################################################################
|
||||
### LLM PROVIDER
|
||||
################################################################################
|
||||
|
||||
### OPENAI
|
||||
## OPENAI_API_KEY - OpenAI API Key (Example: my-openai-api-key)
|
||||
|
||||
|
||||
## NOTE: https://platform.openai.com/docs/api-reference/completions
|
||||
# The temperature setting in language models like GPT controls the balance between predictable and random responses.
|
||||
# Lower temperature makes the responses more focused and deterministic, while higher temperature makes them more
|
||||
# creative and varied. The temperature range typically goes from 0 to 2 in OpenAI's implementation.
|
||||
##
|
||||
## TEMPERATURE - Sets temperature in OpenAI (Default: 0)
|
||||
##
|
||||
###
|
||||
# TEMPERATURE=0
|
||||
|
||||
## OPENAI_ORGANIZATION - Your OpenAI Organization key (Default: None)
|
||||
# OPENAI_ORGANIZATION=
|
||||
|
||||
## USE_AZURE - Use Azure OpenAI or not (Default: False)
|
||||
OPENAI_API_KEY=your-openai-api-key
|
||||
# TEMPERATURE=0
|
||||
# USE_AZURE=False
|
||||
# OPENAI_ORGANIZATION=your-openai-organization-key-if-applicable
|
||||
|
||||
### AZURE
|
||||
# moved to `azure.yaml.template`
|
||||
|
||||
################################################################################
|
||||
### LLM MODELS
|
||||
################################################################################
|
||||
|
||||
## SMART_LLM_MODEL - Smart language model (Default: gpt-4)
|
||||
## SMART_LLM_MODEL - Smart language model (Default: gpt-3.5-turbo)
|
||||
# SMART_LLM_MODEL=gpt-3.5-turbo
|
||||
|
||||
## FAST_LLM_MODEL - Fast language model (Default: gpt-3.5-turbo)
|
||||
# SMART_LLM_MODEL=gpt-4
|
||||
# FAST_LLM_MODEL=gpt-3.5-turbo
|
||||
|
||||
### EMBEDDINGS
|
||||
## EMBEDDING_MODEL - Model to use for creating embeddings
|
||||
## EMBEDDING_MODEL - Model to use for creating embeddings
|
||||
# EMBEDDING_MODEL=text-embedding-ada-002
|
||||
|
||||
################################################################################
|
||||
@@ -100,124 +80,129 @@ OPENAI_API_KEY=your-openai-api-key
|
||||
### MEMORY
|
||||
################################################################################
|
||||
|
||||
### MEMORY_BACKEND - Memory backend type
|
||||
## json_file - Default
|
||||
## redis - Redis (if configured)
|
||||
## MEMORY_INDEX - Name of index created in Memory backend (Default: auto-gpt)
|
||||
# MEMORY_BACKEND=json_file
|
||||
# MEMORY_INDEX=auto-gpt-memory
|
||||
### General
|
||||
|
||||
## MEMORY_BACKEND - Memory backend type
|
||||
# MEMORY_BACKEND=json_file
|
||||
|
||||
## MEMORY_INDEX - Value used in the Memory backend for scoping, naming, or indexing (Default: auto-gpt)
|
||||
# MEMORY_INDEX=auto-gpt
|
||||
|
||||
### Redis
|
||||
|
||||
### REDIS
|
||||
## REDIS_HOST - Redis host (Default: localhost, use "redis" for docker-compose)
|
||||
## REDIS_PORT - Redis port (Default: 6379)
|
||||
## REDIS_PASSWORD - Redis password (Default: "")
|
||||
## WIPE_REDIS_ON_START - Wipes data / index on start (Default: True)
|
||||
# REDIS_HOST=localhost
|
||||
|
||||
## REDIS_PORT - Redis port (Default: 6379)
|
||||
# REDIS_PORT=6379
|
||||
|
||||
## REDIS_PASSWORD - Redis password (Default: "")
|
||||
# REDIS_PASSWORD=
|
||||
|
||||
## WIPE_REDIS_ON_START - Wipes data / index on start (Default: True)
|
||||
# WIPE_REDIS_ON_START=True
|
||||
|
||||
################################################################################
|
||||
### IMAGE GENERATION PROVIDER
|
||||
################################################################################
|
||||
|
||||
### COMMON SETTINGS
|
||||
## IMAGE_PROVIDER - Image provider - dalle, huggingface, or sdwebui
|
||||
## IMAGE_SIZE - Image size (Example: 256)
|
||||
## Image sizes for dalle: 256, 512, 1024
|
||||
### Common
|
||||
|
||||
## IMAGE_PROVIDER - Image provider (Default: dalle)
|
||||
# IMAGE_PROVIDER=dalle
|
||||
|
||||
## IMAGE_SIZE - Image size (Default: 256)
|
||||
# IMAGE_SIZE=256
|
||||
|
||||
### HUGGINGFACE
|
||||
## HUGGINGFACE_IMAGE_MODEL - Text-to-image model from Huggingface (Default: CompVis/stable-diffusion-v1-4)
|
||||
## HUGGINGFACE_API_TOKEN - HuggingFace API token (Example: my-huggingface-api-token)
|
||||
# HUGGINGFACE_IMAGE_MODEL=CompVis/stable-diffusion-v1-4
|
||||
# HUGGINGFACE_API_TOKEN=your-huggingface-api-token
|
||||
### Huggingface (IMAGE_PROVIDER=huggingface)
|
||||
|
||||
### STABLE DIFFUSION WEBUI
|
||||
## SD_WEBUI_AUTH - Stable diffusion webui username:password pair (Example: username:password)
|
||||
## SD_WEBUI_URL - Stable diffusion webui API URL (Example: http://127.0.0.1:7860)
|
||||
## HUGGINGFACE_IMAGE_MODEL - Text-to-image model from Huggingface (Default: CompVis/stable-diffusion-v1-4)
|
||||
# HUGGINGFACE_IMAGE_MODEL=CompVis/stable-diffusion-v1-4
|
||||
|
||||
## HUGGINGFACE_API_TOKEN - HuggingFace API token (Default: None)
|
||||
# HUGGINGFACE_API_TOKEN=
|
||||
|
||||
### Stable Diffusion (IMAGE_PROVIDER=sdwebui)
|
||||
|
||||
## SD_WEBUI_AUTH - Stable Diffusion Web UI username:password pair (Default: None)
|
||||
# SD_WEBUI_AUTH=
|
||||
# SD_WEBUI_URL=http://127.0.0.1:7860
|
||||
|
||||
## SD_WEBUI_URL - Stable Diffusion Web UI API URL (Default: http://localhost:7860)
|
||||
# SD_WEBUI_URL=http://localhost:7860
|
||||
|
||||
################################################################################
|
||||
### AUDIO TO TEXT PROVIDER
|
||||
################################################################################
|
||||
|
||||
### HUGGINGFACE
|
||||
# HUGGINGFACE_AUDIO_TO_TEXT_MODEL=facebook/wav2vec2-base-960h
|
||||
## AUDIO_TO_TEXT_PROVIDER - Audio-to-text provider (Default: huggingface)
|
||||
# AUDIO_TO_TEXT_PROVIDER=huggingface
|
||||
|
||||
## HUGGINGFACE_AUDIO_TO_TEXT_MODEL - The model for HuggingFace to use (Default: CompVis/stable-diffusion-v1-4)
|
||||
# HUGGINGFACE_AUDIO_TO_TEXT_MODEL=CompVis/stable-diffusion-v1-4
|
||||
|
||||
################################################################################
|
||||
### GIT Provider for repository actions
|
||||
################################################################################
|
||||
|
||||
### GITHUB
|
||||
## GITHUB_API_KEY - Github API key / PAT (Example: github_pat_123)
|
||||
## GITHUB_USERNAME - Github username
|
||||
# GITHUB_API_KEY=github_pat_123
|
||||
# GITHUB_USERNAME=your-github-username
|
||||
################################################################################
|
||||
|
||||
## GITHUB_API_KEY - Github API key / PAT (Default: None)
|
||||
# GITHUB_API_KEY=
|
||||
|
||||
## GITHUB_USERNAME - Github username (Default: None)
|
||||
# GITHUB_USERNAME=
|
||||
|
||||
################################################################################
|
||||
### WEB BROWSING
|
||||
################################################################################
|
||||
|
||||
### BROWSER
|
||||
## HEADLESS_BROWSER - Whether to run the browser in headless mode (default: True)
|
||||
## USE_WEB_BROWSER - Sets the web-browser driver to use with selenium (default: chrome).
|
||||
## Note: set this to either 'chrome', 'firefox', 'safari' or 'edge' depending on your current browser
|
||||
# HEADLESS_BROWSER=True
|
||||
|
||||
## USE_WEB_BROWSER - Sets the web-browser driver to use with selenium (default: chrome)
|
||||
# USE_WEB_BROWSER=chrome
|
||||
## BROWSE_CHUNK_MAX_LENGTH - When browsing website, define the length of chunks to summarize (in number of tokens, excluding the response. 75 % of FAST_TOKEN_LIMIT is usually wise )
|
||||
|
||||
## BROWSE_CHUNK_MAX_LENGTH - When browsing website, define the length of chunks to summarize (Default: 3000)
|
||||
# BROWSE_CHUNK_MAX_LENGTH=3000
|
||||
## BROWSE_SPACY_LANGUAGE_MODEL is used to split sentences. Install additional languages via pip, and set the model name here. Example Chinese: python -m spacy download zh_core_web_sm
|
||||
|
||||
## BROWSE_SPACY_LANGUAGE_MODEL - spaCy language model](https://spacy.io/usage/models) to use when creating chunks. (Default: en_core_web_sm)
|
||||
# BROWSE_SPACY_LANGUAGE_MODEL=en_core_web_sm
|
||||
|
||||
### GOOGLE
|
||||
## GOOGLE_API_KEY - Google API key (Example: my-google-api-key)
|
||||
## CUSTOM_SEARCH_ENGINE_ID - Custom search engine ID (Example: my-custom-search-engine-id)
|
||||
# GOOGLE_API_KEY=your-google-api-key
|
||||
# CUSTOM_SEARCH_ENGINE_ID=your-custom-search-engine-id
|
||||
## GOOGLE_API_KEY - Google API key (Default: None)
|
||||
# GOOGLE_API_KEY=
|
||||
|
||||
## GOOGLE_CUSTOM_SEARCH_ENGINE_ID - Google custom search engine ID (Default: None)
|
||||
# GOOGLE_CUSTOM_SEARCH_ENGINE_ID=
|
||||
|
||||
################################################################################
|
||||
### TTS PROVIDER
|
||||
### TEXT TO SPEECH PROVIDER
|
||||
################################################################################
|
||||
|
||||
### MAC OS
|
||||
## USE_MAC_OS_TTS - Use Mac OS TTS or not (Default: False)
|
||||
# USE_MAC_OS_TTS=False
|
||||
## TEXT_TO_SPEECH_PROVIDER - Which Text to Speech provider to use (Default: gtts)
|
||||
# TEXT_TO_SPEECH_PROVIDER=gtts
|
||||
|
||||
### STREAMELEMENTS
|
||||
## USE_BRIAN_TTS - Use Brian TTS or not (Default: False)
|
||||
# USE_BRIAN_TTS=False
|
||||
### Only if TEXT_TO_SPEECH_PROVIDER=streamelements
|
||||
## STREAMELEMENTS_VOICE - Voice to use for StreamElements (Default: Brian)
|
||||
# STREAMELEMENTS_VOICE=Brian
|
||||
|
||||
### ELEVENLABS
|
||||
## ELEVENLABS_API_KEY - Eleven Labs API key (Example: my-elevenlabs-api-key)
|
||||
## ELEVENLABS_VOICE_1_ID - Eleven Labs voice 1 ID (Example: my-voice-id-1)
|
||||
## ELEVENLABS_VOICE_2_ID - Eleven Labs voice 2 ID (Example: my-voice-id-2)
|
||||
# ELEVENLABS_API_KEY=your-elevenlabs-api-key
|
||||
# ELEVENLABS_VOICE_1_ID=your-voice-id-1
|
||||
# ELEVENLABS_VOICE_2_ID=your-voice-id-2
|
||||
### Only if TEXT_TO_SPEECH_PROVIDER=elevenlabs
|
||||
## ELEVENLABS_API_KEY - Eleven Labs API key (Default: None)
|
||||
# ELEVENLABS_API_KEY=
|
||||
|
||||
################################################################################
|
||||
### TWITTER API
|
||||
################################################################################
|
||||
|
||||
# TW_CONSUMER_KEY=
|
||||
# TW_CONSUMER_SECRET=
|
||||
# TW_ACCESS_TOKEN=
|
||||
# TW_ACCESS_TOKEN_SECRET=
|
||||
## ELEVENLABS_VOICE_ID - Eleven Labs voice ID (Example: None)
|
||||
# ELEVENLABS_VOICE_ID=
|
||||
|
||||
################################################################################
|
||||
### ALLOWLISTED PLUGINS
|
||||
################################################################################
|
||||
|
||||
#ALLOWLISTED_PLUGINS - Sets the listed plugins that are allowed (Example: plugin1,plugin2,plugin3)
|
||||
#DENYLISTED_PLUGINS - Sets the listed plugins that are not allowed (Example: plugin1,plugin2,plugin3)
|
||||
ALLOWLISTED_PLUGINS=
|
||||
DENYLISTED_PLUGINS=
|
||||
## ALLOWLISTED_PLUGINS - Sets the listed plugins that are allowed (Default: None)
|
||||
# ALLOWLISTED_PLUGINS=
|
||||
|
||||
## DENYLISTED_PLUGINS - Sets the listed plugins that are not allowed (Default: None)
|
||||
# DENYLISTED_PLUGINS=
|
||||
|
||||
################################################################################
|
||||
### CHAT PLUGIN SETTINGS
|
||||
### CHAT MESSAGES
|
||||
################################################################################
|
||||
# CHAT_MESSAGES_ENABLED - Enable chat messages (Default: False)
|
||||
|
||||
## CHAT_MESSAGES_ENABLED - Enable chat messages (Default: False)
|
||||
# CHAT_MESSAGES_ENABLED=False
|
||||
|
||||
@@ -44,6 +44,17 @@ def read_audio(audio: bytes, config: Config) -> str:
|
||||
Returns:
|
||||
str: The text from the audio
|
||||
"""
|
||||
if config.audio_to_text_provider == "huggingface":
|
||||
text = read_huggingface_audio(audio, config)
|
||||
if text:
|
||||
return f"The audio says: {text}"
|
||||
else:
|
||||
return f"Error, couldn't convert audio to text"
|
||||
|
||||
return "Error: No audio to text provider given"
|
||||
|
||||
|
||||
def read_huggingface_audio(audio: bytes, config: Config) -> str:
|
||||
model = config.huggingface_audio_to_text_model
|
||||
api_url = f"https://api-inference.huggingface.co/models/{model}"
|
||||
api_token = config.huggingface_api_token
|
||||
@@ -60,5 +71,5 @@ def read_audio(audio: bytes, config: Config) -> str:
|
||||
data=audio,
|
||||
)
|
||||
|
||||
text = json.loads(response.content.decode("utf-8"))["text"]
|
||||
return f"The audio says: {text}"
|
||||
response_json = json.loads(response.content.decode("utf-8"))
|
||||
return response_json.get("text")
|
||||
|
||||
@@ -56,7 +56,8 @@ def google_search(query: str, config: Config, num_results: int = 8) -> str:
|
||||
"google",
|
||||
"Google Search",
|
||||
'"query": "<query>"',
|
||||
lambda config: bool(config.google_api_key) and bool(config.custom_search_engine_id),
|
||||
lambda config: bool(config.google_api_key)
|
||||
and bool(config.google_custom_search_engine_id),
|
||||
"Configure google_api_key and custom_search_engine_id.",
|
||||
)
|
||||
def google_official_search(
|
||||
@@ -78,7 +79,7 @@ def google_official_search(
|
||||
try:
|
||||
# Get the Google API key and Custom Search Engine ID from the config file
|
||||
api_key = config.google_api_key
|
||||
custom_search_engine_id = config.custom_search_engine_id
|
||||
custom_search_engine_id = config.google_custom_search_engine_id
|
||||
|
||||
# Initialize the Custom Search API service
|
||||
service = build("customsearch", "v1", developerKey=api_key)
|
||||
|
||||
@@ -59,7 +59,7 @@ class Config(metaclass=Singleton):
|
||||
"PROMPT_SETTINGS_FILE", "prompt_settings.yaml"
|
||||
)
|
||||
self.fast_llm_model = os.getenv("FAST_LLM_MODEL", "gpt-3.5-turbo")
|
||||
self.smart_llm_model = os.getenv("SMART_LLM_MODEL", "gpt-4")
|
||||
self.smart_llm_model = os.getenv("SMART_LLM_MODEL", "gpt-3.5-turbo")
|
||||
self.embedding_model = os.getenv("EMBEDDING_MODEL", "text-embedding-ada-002")
|
||||
|
||||
self.browse_spacy_language_model = os.getenv(
|
||||
@@ -87,22 +87,34 @@ class Config(metaclass=Singleton):
|
||||
openai.organization = self.openai_organization
|
||||
|
||||
self.elevenlabs_api_key = os.getenv("ELEVENLABS_API_KEY")
|
||||
self.elevenlabs_voice_1_id = os.getenv("ELEVENLABS_VOICE_1_ID")
|
||||
self.elevenlabs_voice_2_id = os.getenv("ELEVENLABS_VOICE_2_ID")
|
||||
# ELEVENLABS_VOICE_1_ID is deprecated and included for backwards-compatibility
|
||||
self.elevenlabs_voice_id = os.getenv(
|
||||
"ELEVENLABS_VOICE_ID", os.getenv("ELEVENLABS_VOICE_1_ID")
|
||||
)
|
||||
self.streamelements_voice = os.getenv("STREAMELEMENTS_VOICE", "Brian")
|
||||
|
||||
self.use_mac_os_tts = False
|
||||
self.use_mac_os_tts = os.getenv("USE_MAC_OS_TTS")
|
||||
# Backwards-compatibility shim for deprecated env variables
|
||||
if os.getenv("USE_MAC_OS_TTS"):
|
||||
default_tts_provider = "macos"
|
||||
elif self.elevenlabs_api_key:
|
||||
default_tts_provider = "elevenlabs"
|
||||
elif os.getenv("USE_BRIAN_TTS"):
|
||||
default_tts_provider = "streamelements"
|
||||
else:
|
||||
default_tts_provider = "gtts"
|
||||
|
||||
self.chat_messages_enabled = os.getenv("CHAT_MESSAGES_ENABLED") == "True"
|
||||
|
||||
self.use_brian_tts = False
|
||||
self.use_brian_tts = os.getenv("USE_BRIAN_TTS")
|
||||
self.text_to_speech_provider = os.getenv(
|
||||
"TEXT_TO_SPEECH_PROVIDER", default_tts_provider
|
||||
)
|
||||
|
||||
self.github_api_key = os.getenv("GITHUB_API_KEY")
|
||||
self.github_username = os.getenv("GITHUB_USERNAME")
|
||||
|
||||
self.google_api_key = os.getenv("GOOGLE_API_KEY")
|
||||
self.custom_search_engine_id = os.getenv("CUSTOM_SEARCH_ENGINE_ID")
|
||||
# CUSTOM_SEARCH_ENGINE_ID is deprecated and included for backwards-compatibility
|
||||
self.google_custom_search_engine_id = os.getenv(
|
||||
"GOOGLE_CUSTOM_SEARCH_ENGINE_ID", os.getenv("CUSTOM_SEARCH_ENGINE_ID")
|
||||
)
|
||||
|
||||
self.image_provider = os.getenv("IMAGE_PROVIDER")
|
||||
self.image_size = int(os.getenv("IMAGE_SIZE", 256))
|
||||
@@ -110,6 +122,7 @@ class Config(metaclass=Singleton):
|
||||
self.huggingface_image_model = os.getenv(
|
||||
"HUGGINGFACE_IMAGE_MODEL", "CompVis/stable-diffusion-v1-4"
|
||||
)
|
||||
self.audio_to_text_provider = os.getenv("AUDIO_TO_TEXT_PROVIDER", "huggingface")
|
||||
self.huggingface_audio_to_text_model = os.getenv(
|
||||
"HUGGINGFACE_AUDIO_TO_TEXT_MODEL"
|
||||
)
|
||||
@@ -153,6 +166,8 @@ class Config(metaclass=Singleton):
|
||||
else:
|
||||
self.plugins_denylist = []
|
||||
|
||||
self.chat_messages_enabled = os.getenv("CHAT_MESSAGES_ENABLED") == "True"
|
||||
|
||||
def get_azure_deployment_id_for_model(self, model: str) -> str:
|
||||
"""
|
||||
Returns the relevant deployment id for the model specified.
|
||||
@@ -234,7 +249,7 @@ class Config(metaclass=Singleton):
|
||||
|
||||
def set_elevenlabs_voice_1_id(self, value: str) -> None:
|
||||
"""Set the ElevenLabs Voice 1 ID value."""
|
||||
self.elevenlabs_voice_1_id = value
|
||||
self.elevenlabs_voice_id = value
|
||||
|
||||
def set_elevenlabs_voice_2_id(self, value: str) -> None:
|
||||
"""Set the ElevenLabs Voice 2 ID value."""
|
||||
@@ -246,7 +261,7 @@ class Config(metaclass=Singleton):
|
||||
|
||||
def set_custom_search_engine_id(self, value: str) -> None:
|
||||
"""Set the custom search engine id value."""
|
||||
self.custom_search_engine_id = value
|
||||
self.google_custom_search_engine_id = value
|
||||
|
||||
def set_debug_mode(self, value: bool) -> None:
|
||||
"""Set the debug mode value."""
|
||||
|
||||
@@ -38,11 +38,11 @@ class ElevenLabsSpeech(VoiceBase):
|
||||
"xi-api-key": cfg.elevenlabs_api_key,
|
||||
}
|
||||
self._voices = default_voices.copy()
|
||||
if cfg.elevenlabs_voice_1_id in voice_options:
|
||||
cfg.elevenlabs_voice_1_id = voice_options[cfg.elevenlabs_voice_1_id]
|
||||
if cfg.elevenlabs_voice_id in voice_options:
|
||||
cfg.elevenlabs_voice_id = voice_options[cfg.elevenlabs_voice_id]
|
||||
if cfg.elevenlabs_voice_2_id in voice_options:
|
||||
cfg.elevenlabs_voice_2_id = voice_options[cfg.elevenlabs_voice_2_id]
|
||||
self._use_custom_voice(cfg.elevenlabs_voice_1_id, 0)
|
||||
self._use_custom_voice(cfg.elevenlabs_voice_id, 0)
|
||||
self._use_custom_voice(cfg.elevenlabs_voice_2_id, 1)
|
||||
|
||||
def _use_custom_voice(self, voice, voice_index) -> None:
|
||||
|
||||
@@ -4,10 +4,10 @@ from threading import Semaphore
|
||||
|
||||
from autogpt.config.config import Config
|
||||
from autogpt.speech.base import VoiceBase
|
||||
from autogpt.speech.brian import BrianSpeech
|
||||
from autogpt.speech.eleven_labs import ElevenLabsSpeech
|
||||
from autogpt.speech.gtts import GTTSVoice
|
||||
from autogpt.speech.macos_tts import MacOSTTS
|
||||
from autogpt.speech.stream_elements_speech import StreamElementsSpeech
|
||||
|
||||
_QUEUE_SEMAPHORE = Semaphore(
|
||||
1
|
||||
@@ -33,14 +33,14 @@ def say_text(text: str, voice_index: int = 0) -> None:
|
||||
|
||||
def _get_voice_engine(config: Config) -> tuple[VoiceBase, VoiceBase]:
|
||||
"""Get the voice engine to use for the given configuration"""
|
||||
default_voice_engine = GTTSVoice()
|
||||
if config.elevenlabs_api_key:
|
||||
tts_provider = config.text_to_speech_provider
|
||||
if tts_provider == "elevenlabs":
|
||||
voice_engine = ElevenLabsSpeech()
|
||||
elif config.use_mac_os_tts == "True":
|
||||
elif tts_provider == "macos":
|
||||
voice_engine = MacOSTTS()
|
||||
elif config.use_brian_tts == "True":
|
||||
voice_engine = BrianSpeech()
|
||||
elif tts_provider == "streamelements":
|
||||
voice_engine = StreamElementsSpeech()
|
||||
else:
|
||||
voice_engine = GTTSVoice()
|
||||
|
||||
return default_voice_engine, voice_engine
|
||||
return GTTSVoice(), voice_engine
|
||||
|
||||
@@ -7,23 +7,24 @@ from playsound import playsound
|
||||
from autogpt.speech.base import VoiceBase
|
||||
|
||||
|
||||
class BrianSpeech(VoiceBase):
|
||||
"""Brian speech module for autogpt"""
|
||||
class StreamElementsSpeech(VoiceBase):
|
||||
"""Streamelements speech module for autogpt"""
|
||||
|
||||
def _setup(self) -> None:
|
||||
"""Setup the voices, API key, etc."""
|
||||
|
||||
def _speech(self, text: str, _: int = 0) -> bool:
|
||||
"""Speak text using Brian with the streamelements API
|
||||
def _speech(self, text: str, voice: str, _: int = 0) -> bool:
|
||||
"""Speak text using the streamelements API
|
||||
|
||||
Args:
|
||||
text (str): The text to speak
|
||||
voice (str): The voice to use
|
||||
|
||||
Returns:
|
||||
bool: True if the request was successful, False otherwise
|
||||
"""
|
||||
tts_url = (
|
||||
f"https://api.streamelements.com/kappa/v2/speech?voice=Brian&text={text}"
|
||||
f"https://api.streamelements.com/kappa/v2/speech?voice={voice}&text={text}"
|
||||
)
|
||||
response = requests.get(tts_url)
|
||||
|
||||
54
docs/configuration/options.md
Normal file
54
docs/configuration/options.md
Normal file
@@ -0,0 +1,54 @@
|
||||
# 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 `Auto-GPT` folder and name it `.env`.
|
||||
|
||||
## Environment Variables
|
||||
|
||||
- `AI_SETTINGS_FILE`: Location of AI Settings file. Default: ai_settings.yaml
|
||||
- `ALLOWLISTED_PLUGINS`: List of plugins allowed. Optional.
|
||||
- `AUDIO_TO_TEXT_PROVIDER`: Audio To Text Provider. Only option currently is `huggingface`. Default: huggingface
|
||||
- `AUTHORISE_COMMAND_KEY`: Key response accepted when authorising commands. Default: y
|
||||
- `BROWSE_CHUNK_MAX_LENGTH`: When browsing website, define the length of chunks to summarize. Default: 3000
|
||||
- `BROWSE_SPACY_LANGUAGE_MODEL`: [spaCy language model](https://spacy.io/usage/models) to use when creating chunks. Default: en_core_web_sm
|
||||
- `CHAT_MESSAGES_ENABLED`: Enable chat messages. Optional
|
||||
- `DENYLISTED_PLUGINS`: List of plugins not allowed. Optional.
|
||||
- `DISABLED_COMMAND_CATEGORIES`: Command categories to disable. Command categories are Python module names, e.g. autogpt.commands.analyze_code. See the directory `autogpt/commands` in the source for all command modules. Default: None
|
||||
- `ELEVENLABS_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-002
|
||||
- `EXECUTE_LOCAL_COMMANDS`: If shell commands should be executed locally. Default: False
|
||||
- `EXIT_KEY`: Exit key accepted to exit. Default: n
|
||||
- `FAST_LLM_MODEL`: LLM Model to use for most tasks. Default: gpt-3.5-turbo
|
||||
- `GITHUB_API_KEY`: [Github API Key](https://github.com/settings/tokens). Optional.
|
||||
- `GITHUB_USERNAME`: GitHub Username. Optional.
|
||||
- `GOOGLE_API_KEY`: Google API key. Optional.
|
||||
- `GOOGLE_CUSTOM_SEARCH_ENGINE_ID`: [Google custom search engine ID](https://programmablesearchengine.google.com/controlpanel/all). Optional.
|
||||
- `HEADLESS_BROWSER`: Use a headless browser while Auto-GPT uses a web browser. Setting to `False` will allow you to see Auto-GPT operate the browser. Default: True
|
||||
- `HUGGINGFACE_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-v1-4
|
||||
- `HUGGINGFACE_IMAGE_MODEL`: HuggingFace model to use for image generation. Default: CompVis/stable-diffusion-v1-4
|
||||
- `IMAGE_PROVIDER`: Image provider. Options are `dalle`, `huggingface`, and `sdwebui`. Default: dalle
|
||||
- `IMAGE_SIZE`: Default size of image to generate. Default: 256
|
||||
- `MEMORY_BACKEND`: Memory back-end to use. Currently `json_file` is the only supported and enabled backend. Default: json_file
|
||||
- `MEMORY_INDEX`: Value used in the Memory backend for scoping, naming, or indexing. Default: auto-gpt
|
||||
- `OPENAI_API_KEY`: *REQUIRED*- Your [OpenAI API Key](https://platform.openai.com/account/api-keys).
|
||||
- `OPENAI_ORGANIZATION`: Organization ID in OpenAI. Optional.
|
||||
- `PLAIN_OUTPUT`: Plain output, which disables the spinner. Default: False
|
||||
- `PROMPT_SETTINGS_FILE`: Location of Prompt Settings file. Default: prompt_settings.yaml
|
||||
- `REDIS_HOST`: Redis Host. Default: localhost
|
||||
- `REDIS_PASSWORD`: Redis Password. Optional. Default:
|
||||
- `REDIS_PORT`: Redis Port. Default: 6379
|
||||
- `RESTRICT_TO_WORKSPACE`: The restrict file reading and writing to the workspace directory. Default: True
|
||||
- `SD_WEBUI_AUTH`: Stable Diffusion Web UI username:password pair. Optional.
|
||||
- `SD_WEBUI_URL`: Stable Diffusion Web UI URL. Default: http://localhost:7860
|
||||
- `SHELL_ALLOWLIST`: List of shell commands that ARE allowed to be executed by Auto-GPT. Only applies if `SHELL_COMMAND_CONTROL` is set to `allowlist`. Default: None
|
||||
- `SHELL_COMMAND_CONTROL`: Whether to use `allowlist` or `denylist` to determine what shell commands can be executed (Default: denylist)
|
||||
- `SHELL_DENYLIST`: List of shell commands that ARE NOT allowed to be executed by Auto-GPT. Only applies if `SHELL_COMMAND_CONTROL` is set to `denylist`. Default: sudo,su
|
||||
- `SMART_LLM_MODEL`: LLM Model to use for "smart" tasks. Default: gpt-3.5-turbo
|
||||
- `STREAMELEMENTS_VOICE`: StreamElements voice to use. Default: Brian
|
||||
- `TEMPERATURE`: 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-temperature
|
||||
- `TEXT_TO_SPEECH_PROVIDER`: Text to Speech Provider. Options are `gtts`, `macos`, `elevenlabs`, and `streamelements`. Default: gtts
|
||||
- `USER_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: False
|
||||
- `USE_WEB_BROWSER`: Which web browser to use. Options are `chrome`, `firefox`, `safari` or `edge` Default: chrome
|
||||
- `WIPE_REDIS_ON_START`: Wipes data / index on start. Default: True
|
||||
@@ -20,7 +20,7 @@ def test_initial_values(config: Config):
|
||||
assert config.continuous_mode == False
|
||||
assert config.speak_mode == False
|
||||
assert config.fast_llm_model == "gpt-3.5-turbo"
|
||||
assert config.smart_llm_model == "gpt-4"
|
||||
assert config.smart_llm_model == "gpt-3.5-turbo"
|
||||
|
||||
|
||||
def test_set_continuous_mode(config: Config):
|
||||
|
||||
Reference in New Issue
Block a user