test_scoped_full_fails_with_bad_source_ids() — langchain Function Reference

Source Code

libs/core/tests/unit_tests/indexing/test_indexing.py lines 922–969

def test_scoped_full_fails_with_bad_source_ids(
    record_manager: InMemoryRecordManager, vector_store: InMemoryVectorStore
) -> None:
    """Test Indexing with scoped_full strategy."""
    loader = ToyLoader(
        documents=[
            Document(
                page_content="This is a test document.",
                metadata={"source": "1"},
            ),
            Document(
                page_content="This is another document.",
                metadata={"source": "2"},
            ),
            Document(
                page_content="This is yet another document.",
                metadata={"source": None},
            ),
        ]
    )

    with pytest.raises(
        ValueError,
        match="Source id key is required when cleanup mode "
        "is incremental or scoped_full",
    ):
        # Should raise an error because no source id function was specified
        index(
            loader,
            record_manager,
            vector_store,
            cleanup="scoped_full",
            key_encoder="sha256",
        )

    with pytest.raises(
        ValueError,
        match="Source IDs are required when cleanup mode is incremental or scoped_full",
    ):
        # Should raise an error because no source id function was specified
        index(
            loader,
            record_manager,
            vector_store,
            cleanup="scoped_full",
            source_id_key="source",
            key_encoder="sha256",
        )