haive.agents.reasoning_and_critique.reflexion.models¶
Pydantic models for Reflexion structured output.
Classes¶
Initial answer with self-reflection and follow-up queries. |
|
Structured critique of a draft answer. |
|
Revised answer incorporating reflection and references. |
Module Contents¶
- class haive.agents.reasoning_and_critique.reflexion.models.AnswerQuestion(/, **data)¶
Bases:
pydantic.BaseModelInitial answer with self-reflection and follow-up queries.
Create a new model by parsing and validating input data from keyword arguments.
Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.
self is explicitly positional-only to allow self as a field name.
- Parameters:
data (Any)
- class haive.agents.reasoning_and_critique.reflexion.models.Reflection(/, **data)¶
Bases:
pydantic.BaseModelStructured critique of a draft answer.
Create a new model by parsing and validating input data from keyword arguments.
Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.
self is explicitly positional-only to allow self as a field name.
- Parameters:
data (Any)
- class haive.agents.reasoning_and_critique.reflexion.models.ReviseAnswer(/, **data)¶
Bases:
AnswerQuestionRevised answer incorporating reflection and references.
Create a new model by parsing and validating input data from keyword arguments.
Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.
self is explicitly positional-only to allow self as a field name.
- Parameters:
data (Any)