# ExtractiveQASummary **`class ExtractiveQASummary`** 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 (str | None)` - `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