Prompt
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.
See also
Inheritors
Properties
Whether to generate examples for the prompt. Defaults to unknown: Set to false if generating your own examples.
Images added to this PromptRunner
Filter that determines which properties to include when creating objects.
Tool groups exposed. This will include directly registered tool groups and tool groups resolved from ToolGroups.
Additional objects with @Tool annotation for use in this PromptRunner
Functions
Extension function to safely cast PromptRunner to streaming operations. Pure casting - assumes streaming support already verified.
Extension function to safely convert PromptRunner to streaming operations. Includes validation - checks streaming support before casting.
Create an object from multimodal content (text + images)
Create an object of the given type using the given prompt and LLM options from context (process context or implementing class). Prompts are typically created within the scope of an
Create an object from messages
Create an object of the given type
Try to create an object from multimodal content (text + images)
Try to create an object of the given type using the given prompt and LLM options from context (process context or implementing class). Prompt is typically created within the scope of an
Generate text from multimodal content (text + images)
Generate text
Respond in a conversation
Respond in a conversation with multimodal content
Create streaming operations for this prompt runner configuration.
Check if true reactive streaming is supported by the underlying LLM model. Always check this before calling stream() to avoid exceptions.
Add a prompt contributor that can see context
Add multiple framework-agnostic Tools to the prompt runner (varargs version).
Set whether to generate examples of the output in the prompt on a per-PromptRunner basis. This overrides platform defaults. Note that adding individual examples with com.embabel.agent.api.common.nested.ObjectCreator.withExample will always override this.
Add a list of handoffs to agents on this platform
Set the interaction id for this prompt runner.
Add an image that will be included in the final prompt. Images will be combined with the prompt text when operations are executed.
Add an image from a file
Add an image from a path
Add an image with explicit MIME type and data
Set an interaction id for this prompt runner.
Specify an LLM for the PromptRunner
Add a message that will be included in the final prompt.
Add a prompt contributor that can add to the prompt. Facilitates reuse of prompt elements.
Add varargs of prompt contributors and contextual prompt elements.
Adds a filter that determines which properties are to be included when creating an object.
Add a reference which provides tools and prompt contribution.
Add varargs of references which provide tools and prompt contributions.
Add a list of references which provide tools and prompt contributions.
Add a list of subagents to hand off to.
Add a literal system prompt
Use operations from a given template
Add a framework-agnostic Tool to the prompt runner.
Allows for dynamic tool groups to be added to the PromptRunner.
Add a tool group to the PromptRunner
Add a tool object
Add a tool object to the prompt runner. The tool object should have @Tool annotations.
Add a set of tool groups to the PromptRunner
Add multiple framework-agnostic Tools to the prompt runner.