aljaz/Auto-GPT
1
0
Fork 0
mirror of https://github.com/aljazceru/Auto-GPT.git synced 2025-12-17 05:54:26 +01:00
Code Issues Packages Projects Releases Wiki Activity
Files
39c46ef6be4e7772bc2a39e8b5b72066391ec689
Auto-GPT/docs/content/AutoGPT/configuration/options.md
Reinier van der Leer 39c46ef6be feat(agent/core): Add Anthropic Claude 3 support (#7085) 
- feat(agent/core): Add `AnthropicProvider`
  - Add `ANTHROPIC_API_KEY` to .env.template and docs

  Notable differences in logic compared to `OpenAIProvider`:
  - Merges subsequent user messages in `AnthropicProvider._get_chat_completion_args`
  - Merges and extracts all system messages into `system` parameter in `AnthropicProvider._get_chat_completion_args`
  - Supports prefill; merges prefill content (if any) into generated response

- Prompt changes to improve compatibility with `AnthropicProvider`
  Anthropic has a slightly different API compared to OpenAI, and has much stricter input validation. E.g. Anthropic only supports a single `system` prompt, where OpenAI allows multiple `system` messages. Anthropic also forbids sequences of multiple `user` or `assistant` messages and requires that messages alternate between roles.
  - Move response format instruction from separate message into main system prompt
  - Fix clock message format
  - Add pre-fill to `OneShot` generated prompt

- refactor(agent/core): Tweak `model_providers.schema`
  - Simplify `ModelProviderUsage`
     - Remove attribute `total_tokens` as it is always equal to `prompt_tokens + completion_tokens`
     - Modify signature of `update_usage(..)`; no longer requires a full `ModelResponse` object as input
  - Improve `ModelProviderBudget`
     - Change type of attribute `usage` to `defaultdict[str, ModelProviderUsage]` -> allow per-model usage tracking
     - Modify signature of `update_usage_and_cost(..)`; no longer requires a full `ModelResponse` object as input
     - Allow `ModelProviderBudget` zero-argument instantiation
  - Fix type of `AssistantChatMessage.role` to match `ChatMessage.role` (str -> `ChatMessage.Role`)
  - Add shared attributes and constructor to `ModelProvider` base class
  - Add `max_output_tokens` parameter to `create_chat_completion` interface
  - Add pre-filling as a global feature
    - Add `prefill_response` field to `ChatPrompt` model
    - Add `prefill_response` parameter to `create_chat_completion` interface
  - Add `ChatModelProvider.get_available_models()` and remove `ApiManager`
  - Remove unused `OpenAIChatParser` typedef in openai.py
  - Remove redundant `budget` attribute definition on `OpenAISettings`
  - Remove unnecessary `usage` in `OpenAIProvider` > `default_settings` > `budget`

- feat(agent): Allow use of any available LLM provider through `MultiProvider`
  - Add `MultiProvider` (`model_providers.multi`)
  - Replace all references to / uses of `OpenAIProvider` with `MultiProvider`
  - Change type of `Config.smart_llm` and `Config.fast_llm` from `str` to `ModelName`

- feat(agent/core): Validate function call arguments in `create_chat_completion`
    - Add `validate_call` method to `CompletionModelFunction` in `model_providers.schema`
    - Add `validate_tool_calls` utility function in `model_providers.utils`
    - Add tool call validation step to `create_chat_completion` in `OpenAIProvider` and `AnthropicProvider`
    - Remove (now redundant) command argument validation logic in agent.py and models/command.py

- refactor(agent): Rename `get_openai_command_specs` to `function_specs_from_commands`
2024-05-04 20:33:25 +02:00

5.0 KiB
Raw Blame History

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.yaml
  • 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
  • ANTHROPIC_API_KEY: Set this if you want to use Anthropic models with AutoGPT
  • AZURE_CONFIG_FILE: Location of the Azure Config file relative to the AutoGPT root directory. Default: azure.yaml
  • BROWSE_CHUNK_MAX_LENGTH: When browsing website, define the length of chunks to summarize. Default: 3000
  • BROWSE_SPACY_LANGUAGE_MODEL: spaCy language model to use when creating chunks. Default: en_core_web_sm
  • CHAT_MESSAGES_ENABLED: Enable chat messages. Optional
  • DISABLED_COMMANDS: Commands to disable. Use comma separated names of commands. See the list of commands from built-in components here. 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-3-small
  • EXECUTE_LOCAL_COMMANDS: If shell commands should be executed locally. Default: False
  • EXIT_KEY: Exit key accepted to exit. Default: n
  • FAST_LLM: LLM Model to use for most tasks. Default: gpt-3.5-turbo-0125
  • GITHUB_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 to False will allow you to see AutoGPT 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.
  • OPENAI_ORGANIZATION: Organization ID in OpenAI. Optional.
  • PLAIN_OUTPUT: Plain output, which disables the spinner. Default: False
  • PROMPT_SETTINGS_FILE: Location of the Prompt Settings file relative to the AutoGPT root directory. 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 AutoGPT. 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 AutoGPT. Only applies if SHELL_COMMAND_CONTROL is set to denylist. Default: sudo,su
  • SMART_LLM: LLM Model to use for "smart" tasks. Default: gpt-4-turbo-preview
  • 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