steamship.agents.tools.image_generation package#
Submodules#
steamship.agents.tools.image_generation.dalle module#
Tool for generating images.
- class steamship.agents.tools.image_generation.dalle.DalleTool(*, name: str = 'DalleTool', agent_description: str = 'Used to generate still images from text prompts. Only use if the user has asked directly for an image. When using this tool, the input should be a plain text string that describes, in detail, the desired image.', human_description: str = 'Generates an image from text.', is_final: bool = False, cacheable: bool = True, generator_plugin_handle: str = 'dall-e', generator_plugin_instance_handle: str | None = None, generator_plugin_config: dict = {'n': 1, 'size': '256x256'}, merge_blocks: bool = False, make_output_public: bool = True)[source]#
Bases:
ImageGeneratorToolTool to generate images from text using OpenAI’s DALL-E.
steamship.agents.tools.image_generation.google_image_search module#
Tool for generating images.
- class steamship.agents.tools.image_generation.google_image_search.GoogleImageSearchTool(*, name: str = 'GoogleImageSearchTool', agent_description: str = 'Used to retrieve an image of a well known object, person, place, or idea. Only use if the user has asked directly for an image. Input: a plain text string that describes an object, person, place, or idea. Output: an image of that thing.', human_description: str = 'Fetches an image from Google Image Search.', is_final: bool = False, cacheable: bool = True, generator_plugin_handle: str = 'google-image-search', generator_plugin_instance_handle: str | None = None, generator_plugin_config: dict = {}, merge_blocks: bool = False, make_output_public: bool = True)[source]#
Bases:
ImageGeneratorToolTool to generate images from text by using Google Image Search.
steamship.agents.tools.image_generation.stable_diffusion module#
Tool for generating images.
- class steamship.agents.tools.image_generation.stable_diffusion.StableDiffusionTool(*, name: str = 'StableDiffusionTool', agent_description: str = 'Used to generate images from text prompts. Only use if the user has asked directly for an image. When using this tool, the input should be a plain text string that describes, in detail, the desired image.', human_description: str = 'Generates an image from text.', is_final: bool = False, cacheable: bool = True, generator_plugin_handle: str = 'stable-diffusion', generator_plugin_instance_handle: str | None = None, generator_plugin_config: dict = {'n': 1}, merge_blocks: bool = False, make_output_public: bool = True)[source]#
Bases:
ImageGeneratorToolTool to generate images from text using StableDiffusion.
Module contents#
- class steamship.agents.tools.image_generation.DalleTool(*, name: str = 'DalleTool', agent_description: str = 'Used to generate still images from text prompts. Only use if the user has asked directly for an image. When using this tool, the input should be a plain text string that describes, in detail, the desired image.', human_description: str = 'Generates an image from text.', is_final: bool = False, cacheable: bool = True, generator_plugin_handle: str = 'dall-e', generator_plugin_instance_handle: str | None = None, generator_plugin_config: dict = {'n': 1, 'size': '256x256'}, merge_blocks: bool = False, make_output_public: bool = True)[source]#
Bases:
ImageGeneratorToolTool to generate images from text using OpenAI’s DALL-E.
- agent_description: str#
Description for use in an agent in order to enable Action selection. It should include a short summary of what the Tool does, what the inputs to the Tool should be, and what the outputs of the tool are.
- cacheable: bool#
Whether runs of this Tool should be cached based on inputs (if caching is enabled in the AgentContext for a run). Setting this to False will make prevent any Actions that involve this tool from being cached, meaning that every Action using this Tool will result in a call to run. By default, Tools are considered cacheable.
- class steamship.agents.tools.image_generation.GoogleImageSearchTool(*, name: str = 'GoogleImageSearchTool', agent_description: str = 'Used to retrieve an image of a well known object, person, place, or idea. Only use if the user has asked directly for an image. Input: a plain text string that describes an object, person, place, or idea. Output: an image of that thing.', human_description: str = 'Fetches an image from Google Image Search.', is_final: bool = False, cacheable: bool = True, generator_plugin_handle: str = 'google-image-search', generator_plugin_instance_handle: str | None = None, generator_plugin_config: dict = {}, merge_blocks: bool = False, make_output_public: bool = True)[source]#
Bases:
ImageGeneratorToolTool to generate images from text by using Google Image Search.
- agent_description: str#
Description for use in an agent in order to enable Action selection. It should include a short summary of what the Tool does, what the inputs to the Tool should be, and what the outputs of the tool are.
- cacheable: bool#
Whether runs of this Tool should be cached based on inputs (if caching is enabled in the AgentContext for a run). Setting this to False will make prevent any Actions that involve this tool from being cached, meaning that every Action using this Tool will result in a call to run. By default, Tools are considered cacheable.
- class steamship.agents.tools.image_generation.StableDiffusionTool(*, name: str = 'StableDiffusionTool', agent_description: str = 'Used to generate images from text prompts. Only use if the user has asked directly for an image. When using this tool, the input should be a plain text string that describes, in detail, the desired image.', human_description: str = 'Generates an image from text.', is_final: bool = False, cacheable: bool = True, generator_plugin_handle: str = 'stable-diffusion', generator_plugin_instance_handle: str | None = None, generator_plugin_config: dict = {'n': 1}, merge_blocks: bool = False, make_output_public: bool = True)[source]#
Bases:
ImageGeneratorToolTool to generate images from text using StableDiffusion.
- agent_description: str#
Description for use in an agent in order to enable Action selection. It should include a short summary of what the Tool does, what the inputs to the Tool should be, and what the outputs of the tool are.
- cacheable: bool#
Whether runs of this Tool should be cached based on inputs (if caching is enabled in the AgentContext for a run). Setting this to False will make prevent any Actions that involve this tool from being cached, meaning that every Action using this Tool will result in a call to run. By default, Tools are considered cacheable.