All Classes and Interfaces

Class
Description
Base implementation of the Genai contract shared by concrete provider integrations.
Anthropic-backed implementation of Machai's Genai abstraction.
Genai implementation that integrates with EPAM CodeMie.
EmbeddingProvider defines the contract for AI embedding providers.
A runtime exception used to signal a tool or processing error, with a structured error payload that is serialized to JSON and included in the exception message.
Service-provider interface (SPI) for installing host-provided function tools.
Discovers and applies FunctionTools implementations using Java's ServiceLoader mechanism.
Contract for a generative-AI provider integration.
Delegating Genai implementation.
Utility class for dynamically loading and initializing generative AI providers and embedding providers.
No-op implementation of Genai that performs no AI processing.
OpenAI-backed Genai implementation.
Annotation to mark a method parameter marked as a Tool or Prompt parameter within the AI provider framework.
Descriptor for a parameter used in tool or prompt definitions within the AI provider framework.
Annotation to mark a method as a prompt within the AI provider framework.
Annotation used to declare a method as an executable resource provider within the generative-AI tools system.
Enumeration representing participant roles in an AI interaction context.
Exception used to signal the end of a task without terminating the application.
Indicates which application classes a FunctionTools implementation supports.
Annotation to mark a method as a tool function within the AI provider framework.
Functional interface representing a tool callable by a provider during a run.
Internal logging utility for tool inputs, results, and execution errors.
Defines the types of operations whose activity can be logged.
AI provider implementation for managing and invoking host-defined function tools.
Utility class for converting between Java types and their string representations, as well as mapping Java types to simplified type names (e.g., "string", "integer", "array").
Immutable token-usage metrics for a single generative AI interaction.
Central registry for aggregated GenAI token-usage statistics.