Expand description
Inference integration for AIMX workflows.
This module orchestrates prompt construction, provider calls, response parsing, and validation for inference rules within workflows. Public re-exports expose the types required to build and execute inference requests.
Re-exports§
pub use inference::Inference;pub use inference::Model;pub use inference::Pattern;pub use inference::parse_inference;pub use item::Item;pub use item::parse_inline_item;pub use item::parse_item;pub use key::Suffix;pub use key::parse_key;pub use key::parse_ucid;pub use modifier::Modifier;pub use output_format::Capability;pub use output_format::OutputFormat;pub use prompt::Prompt;pub use provider::Api;pub use provider::Provider;pub use request::send_request;pub use response::Response;pub use response::parse_response;pub use validate::validate_responses;
Modules§
- inference
- item
- Parsing of list and task items in AIM inference content.
- key
- Parsing of UPPERCASE inference keys used in AIM prompts and responses.
- modifier
- output_
format - prompt
- Prompt construction for inference workflows.
- provider
- Inference provider configuration for external AI APIs used by AIMX. Defines serializable types for selecting APIs, endpoints, models, and runtime limits so hosts can configure inference behavior.
- request
- Inference request management for AI model providers.
- response
- Inference response parsing and conversion.
- validate
- Validation of inference responses into assignment rules.