test_router_runnable_async() — langchain Function Reference

Architecture documentation for the test_router_runnable_async() function in test_runnable.py from the langchain codebase.

Function python LangChainCore Runnables calls 1

Entity Profile

LangChainCore→ Runnables→ test_router_runnable_async() — langchain Function Reference

Dependency Diagram

graph TD
  0220d3ab_db8c_f784_31f0_cfee558a3902["test_router_runnable_async()"]
  26df6ad8_0189_51d0_c3c1_6c3248893ff5["test_runnable.py"]
  0220d3ab_db8c_f784_31f0_cfee558a3902 -->|defined in| 26df6ad8_0189_51d0_c3c1_6c3248893ff5
  8652094c_ec57_c551_fc44_9566d00cf872["abatch()"]
  0220d3ab_db8c_f784_31f0_cfee558a3902 -->|calls| 8652094c_ec57_c551_fc44_9566d00cf872
  style 0220d3ab_db8c_f784_31f0_cfee558a3902 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/tests/unit_tests/runnables/test_runnable.py lines 2909–2931

async def test_router_runnable_async() -> None:
    chain1 = ChatPromptTemplate.from_template(
        "You are a math genius. Answer the question: {question}"
    ) | FakeListLLM(responses=["4"])
    chain2 = ChatPromptTemplate.from_template(
        "You are an english major. Answer the question: {question}"
    ) | FakeListLLM(responses=["2"])
    router = RouterRunnable({"math": chain1, "english": chain2})
    chain: Runnable = {
        "key": lambda x: x["key"],
        "input": {"question": lambda x: x["question"]},
    } | 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"]