c19ab2b24f
Remove many env vars and use component-level configuration that could be loaded from file instead. ### Changed - `BaseAgent` provides `serialize_configs` and `deserialize_configs` that can save and load all component configuration as json `str`. Deserialized components/values overwrite existing values, so not all values need to be present in the serialized config. - Decoupled `forge/content_processing/text.py` from `Config` - Kept `execute_local_commands` in `Config` because it's needed to know if OS info should be included in the prompt - Updated docs to reflect changes - Renamed `Config` to `AppConfig` ### Added - Added `ConfigurableComponent` class for components and following configs: - `ActionHistoryConfiguration` - `CodeExecutorConfiguration` - `FileManagerConfiguration` - now file manager allows to have multiple agents using the same workspace - `GitOperationsConfiguration` - `ImageGeneratorConfiguration` - `WebSearchConfiguration` - `WebSeleniumConfiguration` - `BaseConfig` in `forge` and moved `Config` (now inherits from `BaseConfig`) back to `autogpt` - Required `config_class` attribute for the `ConfigurableComponent` class that should be set to configuration class for a component `--component-config-file` CLI option and `COMPONENT_CONFIG_FILE` env var and field in `Config`. This option allows to load configuration from a specific file, CLI option takes precedence over env var. - Added comments to config models ### Removed - Unused `change_agent_id` method from `FileManagerComponent` - Unused `allow_downloads` from `Config` and CLI options (it should be in web component config if needed) - CLI option `--browser-name` (the option is inside `WebSeleniumConfiguration`) - Unused `workspace_directory` from CLI options - No longer needed variables from `Config` and docs - Unused fields from `Config`: `image_size`, `audio_to_text_provider`, `huggingface_audio_to_text_model` - Removed `files` and `workspace` class attributes from `FileManagerComponent`
2.1 KiB
Component Agents
!!! important Legacy plugins no longer work with AutoGPT. They have been replaced by components, although we're still working on a new system to load plug-in components.
This guide explains the component-based architecture of AutoGPT agents. It's a new way of building agents that is more flexible and easier to extend. Components replace some agent's logic and plugins with a more modular and composable system.
Agent is composed of components, and each component implements a range of protocols (interfaces), each one providing a specific functionality, e.g. additional commands or messages. Each protocol is handled in a specific order, defined by the agent. This allows for a clear separation of concerns and a more modular design.
This system is simple, flexible, requires basically no configuration, and doesn't hide any data - anything can still be passed or accessed directly from or between components.
Definitions & Guides
See Creating Components to get started! Or you can explore the following topics in detail:
- 🧩 Component: a class that implements one or more protocols. It can be added to an agent to provide additional functionality. See what's already provided in Built-in Components.
- ⚙️ Protocol: an interface that defines a set of methods that a component must implement. Protocols are used to group related functionality.
- 🛠️ Command: enable agent to interact with user and tools.
- 🤖 Agent: a class that is composed of components. It's responsible for executing pipelines and managing the components.
- Pipeline: a sequence of method calls on components. Pipelines are used to execute a series of actions in a specific order. As of now there's no formal class for a pipeline, it's just a sequence of method calls on components. There are two default pipelines implemented in the default agent:
propose_actionandexecute. See 🤖 Agent to learn more.