test_inmemory_mmr() — langchain Function Reference

Architecture documentation for the test_inmemory_mmr() function in test_in_memory.py from the langchain codebase.

Function python LangChainCore MessageInterface

Entity Profile

LangChainCore→ MessageInterface→ test_inmemory_mmr() — langchain Function Reference

Dependency Diagram

graph TD
  e8196cf1_f26b_1988_d0fc_74bdbb8e113a["test_inmemory_mmr()"]
  a974d690_d5fa_ba65_671d_ce8278eefe7d["test_in_memory.py"]
  e8196cf1_f26b_1988_d0fc_74bdbb8e113a -->|defined in| a974d690_d5fa_ba65_671d_ce8278eefe7d
  style e8196cf1_f26b_1988_d0fc_74bdbb8e113a fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/tests/unit_tests/vectorstores/test_in_memory.py lines 65–83

async def test_inmemory_mmr() -> None:
    """Test MMR search."""
    texts = ["foo", "foo", "fou", "foy"]
    docsearch = await InMemoryVectorStore.afrom_texts(
        texts, DeterministicFakeEmbedding(size=6)
    )
    # make sure we can k > docstore size
    output = docsearch.max_marginal_relevance_search("foo", k=10, lambda_mult=0.1)
    assert len(output) == len(texts)
    assert output[0] == _any_id_document(page_content="foo")
    assert output[1] == _any_id_document(page_content="fou")

    # Check async version
    output = await docsearch.amax_marginal_relevance_search(
        "foo", k=10, lambda_mult=0.1
    )
    assert len(output) == len(texts)
    assert output[0] == _any_id_document(page_content="foo")
    assert output[1] == _any_id_document(page_content="fou")