## build_prompt()


A few-shot prompt asking a model to annotate `text` in CANE.


Usage

``` python
build_prompt(
    text,
    *,
    examples,
    variant,
    labels=None,
    context=1,
    handles=False,
    on_unrepresentable="raise",
    on_mismatch="warn",
    parse_options=None,
    lossy="warn",
    dialect=ENGLISH
)
```


The layout follows the CANE paper: task, entity types, format and guideline, the 'Important' instruction, the worked examples, then the input. Examples are written with [dumps](dumps.md#cane_format.dumps) and the same options, so the prompt teaches exactly what [loads](loads.md#cane_format.loads) expects.


## Parameters


`text: str`  
The text to annotate.

`examples: Sequence[Document]`  
Annotated documents shown as few-shot examples.

`variant: Variant | str`  
The CANE variant.

`labels: Iterable[str] | None = None`  
The entity types in the order to list them (a set is sorted); by default the examples' labels, sorted. Required when there are no examples.

`context, handles, on_unrepresentable, on_mismatch, parse_options, lossy, dialect`  
As for [dumps](dumps.md#cane_format.dumps).