ExtractiveQASummary#

class ExtractiveQASummary(*args, **kwds)#

extractive-qa | Build abstract based on extractive QA results on top ranked results

Build an abstract based on the Extracted answer, by highlighting the answer and its surrounding context.

pydantic model PluginConfig#
Fields
  • on_top_n (int)

  • query (Optional[str])

  • worker (str)

PluginConfig.plugin_name: ClassVar[str] = 'extractive-qa'#

Used to register and reference the plugin within a query.

field PluginConfig.on_top_n: int = 2#

Run QA on top-N paragraphs

field PluginConfig.query: Optional[str] = ''#

left side of the text-pair, as used for cross-encoding. Per default fetches to supplied searchbar user-terms

field PluginConfig.worker: str = 'accurate'#

What deployed QA worker (@transformer-service) should be used