aparse_result(
self,
result: list[Generation],
*,
partial: bool = False
)| Name | Type | Description |
|---|---|---|
result* | list[Generation] | |
partial | bool | Default: False |
Parse a list of candidate model Generation objects into a specific format.
The return value is parsed from only the first Generation in the result, which
is assumed to be the highest-likelihood Generation.
This method is used by ainvoke and abatch. The default implementation
runs parse_result in an executor; it does not call aparse. Override this
method to provide native async parsing, for example when using async I/O or
clients bound to the caller's event loop. Synchronous parsers can use the
default implementation.
A list of Generation to be parsed.
The Generation objects are assumed to be different candidate outputs
for a single model input.
Whether to parse the output as a partial result.
This is useful for parsers that can parse partial results.