test_embed_with_kwargs_async() — langchain Function Reference

Architecture documentation for the test_embed_with_kwargs_async() function in test_base.py from the langchain codebase.

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ test_embed_with_kwargs_async() — langchain Function Reference

Dependency Diagram

graph TD
  8ee3cb85_1393_7ebf_e694_de518333a089["test_embed_with_kwargs_async()"]
  1b2604cc_dec7_a9eb_ce6b_1cbab7a6dc2e["test_base.py"]
  8ee3cb85_1393_7ebf_e694_de518333a089 -->|defined in| 1b2604cc_dec7_a9eb_ce6b_1cbab7a6dc2e
  style 8ee3cb85_1393_7ebf_e694_de518333a089 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/openai/tests/unit_tests/embeddings/test_base.py lines 82–100

async def test_embed_with_kwargs_async() -> None:
    embeddings = OpenAIEmbeddings(
        model="text-embedding-3-small",
        check_embedding_ctx_length=False,
        dimensions=4,  # also check that runtime kwargs take precedence
    )
    texts = ["text1", "text2"]
    with patch.object(embeddings.async_client, "create") as mock_create:
        mock_create.side_effect = [
            {"data": [{"embedding": [0.1, 0.2, 0.3]}, {"embedding": [0.4, 0.5, 0.6]}]}
        ]

        result = await embeddings.aembed_documents(texts, dimensions=3)
        client_kwargs = embeddings._invocation_params.copy()
        assert client_kwargs["dimensions"] == 4
        client_kwargs["dimensions"] = 3
        mock_create.assert_any_call(input=texts, **client_kwargs)

    assert result == [[0.1, 0.2, 0.3], [0.4, 0.5, 0.6]]