test_arun_on_dataset() — langchain Function Reference

Architecture documentation for the test_arun_on_dataset() function in test_runner_utils.py from the langchain codebase.

Function python LangChainCore Runnables

Entity Profile

LangChainCore→ Runnables→ test_arun_on_dataset() — langchain Function Reference

Dependency Diagram

graph TD
  a8706c8f_d4c8_7d16_1e26_8393c85d766e["test_arun_on_dataset()"]
  c6cd417d_d0bc_a309_dd34_61e338d2ac18["test_runner_utils.py"]
  a8706c8f_d4c8_7d16_1e26_8393c85d766e -->|defined in| c6cd417d_d0bc_a309_dd34_61e338d2ac18
  style a8706c8f_d4c8_7d16_1e26_8393c85d766e fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/tests/unit_tests/smith/evaluation/test_runner_utils.py lines 244–354

async def test_arun_on_dataset() -> None:
    dataset = Dataset(
        id=uuid.uuid4(),
        name="test",
        description="Test dataset",
        owner_id="owner",
        created_at=_CREATED_AT,
        tenant_id=_TENANT_ID,
        _host_url="http://localhost:1984",
    )
    uuids = [
        "0c193153-2309-4704-9a47-17aee4fb25c8",
        "0d11b5fd-8e66-4485-b696-4b55155c0c05",
        "90d696f0-f10d-4fd0-b88b-bfee6df08b84",
        "4ce2c6d8-5124-4c0c-8292-db7bdebcf167",
        "7b5a524c-80fa-4960-888e-7d380f9a11ee",
    ]
    examples = [
        Example(
            id=uuids[0],
            created_at=_CREATED_AT,
            inputs={"input": "1"},
            outputs={"output": "2"},
            dataset_id=str(uuid.uuid4()),
        ),
        Example(
            id=uuids[1],
            created_at=_CREATED_AT,
            inputs={"input": "3"},
            outputs={"output": "4"},
            dataset_id=str(uuid.uuid4()),
        ),
        Example(
            id=uuids[2],
            created_at=_CREATED_AT,
            inputs={"input": "5"},
            outputs={"output": "6"},
            dataset_id=str(uuid.uuid4()),
        ),
        Example(
            id=uuids[3],
            created_at=_CREATED_AT,
            inputs={"input": "7"},
            outputs={"output": "8"},
            dataset_id=str(uuid.uuid4()),
        ),
        Example(
            id=uuids[4],
            created_at=_CREATED_AT,
            inputs={"input": "9"},
            outputs={"output": "10"},
            dataset_id=str(uuid.uuid4()),
        ),
    ]

    def mock_read_dataset(*_: Any, **__: Any) -> Dataset:
        return dataset

    def mock_list_examples(*_: Any, **__: Any) -> Iterator[Example]:
        return iter(examples)

    async def mock_arun_chain(
        example: Example,
        *_: Any,
        **__: Any,
    ) -> dict[str, Any]:
        return {"result": f"Result for example {example.id}"}

    def mock_create_project(*_: Any, **__: Any) -> Any:
        proj = mock.MagicMock()
        proj.id = "123"
        return proj

    with (
        mock.patch.object(Client, "read_dataset", new=mock_read_dataset),
        mock.patch.object(Client, "list_examples", new=mock_list_examples),
        mock.patch(
            "langchain_classic.smith.evaluation.runner_utils._arun_llm_or_chain",
            new=mock_arun_chain,
        ),
        mock.patch.object(Client, "create_project", new=mock_create_project),