cognition.language.population¶
Filling a data structure with values based upon natural language input
Classes¶
Function to instantiate a model with values based upon an utterance |
Module Contents¶
- class cognition.language.population.ModelPopulator[T: pydantic.BaseModel](model_type, task_desc)¶
Function to instantiate a model with values based upon an utterance
- Parameters:
model_type (type[T]) – type needing instantiation
task_desc (str | None) – textual description of the task
- prompt(utterance, *extra)¶
Produces the prompt for a supplied utterance
- Parameters:
utterance (str) – user input
extra (str) – dynamic extra context to supply
- Returns:
resulting filler llm prompt
- Return type:
str
- __call__(utterance, llm, *extra, timeout_secs=10)¶
Produces a model instance based upon a timeout budget.
- Parameters:
utterance (str) – text to instantiate
llm (pydantic_ai.models.Model) – textual model to utilize
extra (str) – dynamic extra context to supply
timeout_secs (int)
- Timeout_secs:
time given per LLM call
- Returns:
model instance
- Return type:
T
- classmethod populate(utterance, model_type, llm, task_desc, *extra, timeout_secs=10)¶
One-off instantiation and calling of a populator
- Parameters:
utterance (str) – text to classify
model_type (type[T]) – type needing instantiation
llm (pydantic_ai.models.Model) – textual model to utilize
task_desc (str | None) – textual description of the task
extra (str) – dynamic extra context to supply
timeout_secs (int)
- Timeout_secs:
time given per LLM call
- Returns:
most common classification with confidence
- Return type:
T