Package-level declarations
Types
Context for actions
Reusable AgentFunction. Allows use of AgentPlatform as a function from I to O, with different process options.
Typed operations over an agent platform
For use from Java
Tag interface to indicate that an implementing type should be built from the context from its bound fields. Provides a strongly typed way to wait on combined results. Makes a megazord! An aggregation should have multiple non-nullable fields, each of which will be bound to the blackboard. An aggregation is used as an input to the action.
Can be injected into components
OperationContext that execute actions. An ExecutingOperationContext can execute agents as sub-processes.
ActionContext with a single input
ActionContext with multiple inputs
An LLmReference exposes tools and is a prompt contributor. The prompt contribution might describe how to use the tools or can include relevant information directly. Consider, for example, a reference to an API which is so small it's included in the prompt, versus a large API which must be accessed via tools. The reference name is used in a strategy for tool naming, so should be fairly short. Description may be more verbose. If you want a custom naming strategy, use a ToolObject directly, and add the PromptContributor separately.
Try to resolve a stuck agent process by trying all handlers in order
Create an object of the given type from a prompt or messages. Allows setting strongly typed examples.
Context for any operation. Exposes blackboard and process context.
User code should always use this interface to execute prompts. Typically obtained from an OperationContext or ActionContext parameter, via OperationContext.ai A PromptRunner is immutable once constructed, and has determined LLM and hyperparameters. Use the "with" methods to evolve the state to your desired configuration before executing createObject, generateText or other LLM invocation methods. Thus, a PromptRunner can be reused within an action implementation. A contextual facade to LlmOperations.
User-facing interface for executing prompts.
Attempts to resolve stuck processes
Llm operations based on a compiled template. Similar to PromptRunnerOperations, but taking a model instead of a template string. Template names will be resolved by the TemplateRenderer provided.
Holds an annotated tool object. Adds a naming strategy and a filter to the object.
Tool statistics, indexed by tool name.
Transformation function signature
Functions
Expose the named agent as an action of the given transformation type
Run the given agent as a sub-process of this action context.
Creates a transformation action from an agent
Create an object of the given type
Turn user input into this type