agrag.eval.extraction.extraction_case

extraction_case(chunk_text:str, predicted:ExtractionResult, gold:ExtractionResult) -> LLMTestCase

Build a test case that holds a predicted and a gold extraction.

Parameters:

• chunk_text (str) – The text the extractor read.
• predicted (ExtractionResult) – The extractor output.
• gold (ExtractionResult) – The gold annotation.

Returns:

• LLMTestCase – A test case with serialized predicted and gold extractions.