test_cleanup_with_different_batchsize() — langchain Function Reference

Architecture documentation for the test_cleanup_with_different_batchsize() function in test_indexing.py from the langchain codebase.

Function python LangChainCore MessageInterface

Entity Profile

LangChainCore→ MessageInterface→ test_cleanup_with_different_batchsize() — langchain Function Reference

Dependency Diagram

graph TD
  875469f1_06f0_219c_49e2_626bd0a426d3["test_cleanup_with_different_batchsize()"]
  9bc4e8b6_769a_ae11_3fc1_309cb678c248["test_indexing.py"]
  875469f1_06f0_219c_49e2_626bd0a426d3 -->|defined in| 9bc4e8b6_769a_ae11_3fc1_309cb678c248
  style 875469f1_06f0_219c_49e2_626bd0a426d3 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/tests/unit_tests/indexes/test_indexing.py lines 1225–1264

def test_cleanup_with_different_batchsize(
    record_manager: SQLRecordManager,
    vector_store: VectorStore,
) -> 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 index(docs, record_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 index(
        docs,
        record_manager,
        vector_store,
        cleanup="full",
        cleanup_batch_size=17,
    ) == {
        "num_added": 1001,
        "num_deleted": 1000,
        "num_skipped": 0,
        "num_updated": 0,
    }