Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Python ai4sciencedocument-analysisdocxextract-datalayout-analysisocrparserpdfpdf-converterpdf-extractor-llmpdf-extractor-pretrainpdf-extractor-ragpdf-parserpptxpythonxlsx
test(vlm): accept page_vector_geometries kwarg in hybrid_stub retain_vlm_text
myhloli23be3d7c8b1b
diff --git a/tests/unittest/test_vlm_remote.py b/tests/unittest/test_vlm_remote.pyindex 778c35f5..c4ee87ff 100644--- a/tests/unittest/test_vlm_remote.py+++ b/tests/unittest/test_vlm_remote.py@@ -247,7 +247,12 @@ def hybrid_stub(monkeypatch: pytest.MonkeyPatch) -> None:monkeypatch.setattr(pipeline, "clean_memory", lambda device: None)def retain_vlm_text(- images: object, pages: object, blocks: list[list[dict[str, Any]]], *args: object+ images: object,+ pages: object,+ blocks: list[list[dict[str, Any]]],+ *args: object,+ page_vector_geometries: object,+ np_images: object,) -> list[list[dict[str, Any]]]:"""保留远程正文并模拟 Hybrid 提供的行框,满足 PDF 文本块校验合同。"""for page in blocks: