test_higher_order_lambda_runnable_async() — langchain Function Reference
Architecture documentation for the test_higher_order_lambda_runnable_async() function in test_runnable.py from the langchain codebase.
Entity Profile
Dependency Diagram
graph TD d3230587_b866_4309_a37d_9fdfe73dd2ed["test_higher_order_lambda_runnable_async()"] 26df6ad8_0189_51d0_c3c1_6c3248893ff5["test_runnable.py"] d3230587_b866_4309_a37d_9fdfe73dd2ed -->|defined in| 26df6ad8_0189_51d0_c3c1_6c3248893ff5 8652094c_ec57_c551_fc44_9566d00cf872["abatch()"] d3230587_b866_4309_a37d_9fdfe73dd2ed -->|calls| 8652094c_ec57_c551_fc44_9566d00cf872 style d3230587_b866_4309_a37d_9fdfe73dd2ed fill:#6366f1,stroke:#818cf8,color:#fff
Relationship Graph
Source Code
libs/core/tests/unit_tests/runnables/test_runnable.py lines 2993–3056
async def test_higher_order_lambda_runnable_async(mocker: MockerFixture) -> None:
math_chain = ChatPromptTemplate.from_template(
"You are a math genius. Answer the question: {question}"
) | FakeListLLM(responses=["4"])
english_chain = ChatPromptTemplate.from_template(
"You are an english major. Answer the question: {question}"
) | FakeListLLM(responses=["2"])
input_map = RunnableParallel(
key=lambda x: x["key"],
input={"question": lambda x: x["question"]},
)
def router(value: dict[str, Any]) -> Runnable:
if value["key"] == "math":
return itemgetter("input") | math_chain
if value["key"] == "english":
return itemgetter("input") | english_chain
msg = f"Unknown key: {value['key']}"
raise ValueError(msg)
chain: Runnable = input_map | router
result = await chain.ainvoke({"key": "math", "question": "2 + 2"})
assert result == "4"
result2 = await chain.abatch(
[
{"key": "math", "question": "2 + 2"},
{"key": "english", "question": "2 + 2"},
]
)
assert result2 == ["4", "2"]
# Test ainvoke
async def arouter(params: dict[str, Any]) -> Runnable:
if params["key"] == "math":
return itemgetter("input") | math_chain
if params["key"] == "english":
return itemgetter("input") | english_chain
msg = f"Unknown key: {params['key']}"
raise ValueError(msg)
achain: Runnable = input_map | arouter
math_spy = mocker.spy(math_chain.__class__, "ainvoke")
tracer = FakeTracer()
assert (
await achain.ainvoke(
{"key": "math", "question": "2 + 2"}, {"callbacks": [tracer]}
)
== "4"
)
assert math_spy.call_args.args[1] == {
"key": "math",
"input": {"question": "2 + 2"},
}
assert len([r for r in tracer.runs if r.parent_run_id is None]) == 1
parent_run = next(r for r in tracer.runs if r.parent_run_id is None)
assert len(parent_run.child_runs) == 2
router_run = parent_run.child_runs[1]
assert router_run.name == "arouter"
assert len(router_run.child_runs) == 1
math_run = router_run.child_runs[0]
assert math_run.name == "RunnableSequence"
assert len(math_run.child_runs) == 3
Domain
Subdomains
Calls
Source
Frequently Asked Questions
What does test_higher_order_lambda_runnable_async() do?
test_higher_order_lambda_runnable_async() is a function in the langchain codebase, defined in libs/core/tests/unit_tests/runnables/test_runnable.py.
Where is test_higher_order_lambda_runnable_async() defined?
test_higher_order_lambda_runnable_async() is defined in libs/core/tests/unit_tests/runnables/test_runnable.py at line 2993.
What does test_higher_order_lambda_runnable_async() call?
test_higher_order_lambda_runnable_async() calls 1 function(s): abatch.
Analyze Your Own Codebase
Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.
Try Supermodel Free