test_async_cleanup_with_different_batchsize() — langchain Function Reference

Source Code

libs/langchain/tests/unit_tests/indexes/test_indexing.py lines 1268–1307

async def test_async_cleanup_with_different_batchsize(
    arecord_manager: SQLRecordManager,
    vector_store: InMemoryVectorStore,
) -> None:
    """Check that we can clean up with different batch size."""
    docs = [
        Document(
            page_content="This is a test document.",
            metadata={"source": str(d)},
        )
        for d in range(1000)
    ]

    assert await aindex(docs, arecord_manager, vector_store, cleanup="full") == {
        "num_added": 1000,
        "num_deleted": 0,
        "num_skipped": 0,
        "num_updated": 0,
    }

    docs = [
        Document(
            page_content="Different doc",
            metadata={"source": str(d)},
        )
        for d in range(1001)
    ]

    assert await aindex(
        docs,
        arecord_manager,
        vector_store,
        cleanup="full",
        cleanup_batch_size=17,
    ) == {
        "num_added": 1001,
        "num_deleted": 1000,
        "num_skipped": 0,
        "num_updated": 0,
    }