test_prediction_tokens() — langchain Function Reference

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

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ test_prediction_tokens() — langchain Function Reference

Dependency Diagram

graph TD
  76cb5eeb_804b_66dd_6905_0c38a9bc0d83["test_prediction_tokens()"]
  bd382a4e_442c_13ae_530c_6e34bc43623d["test_base.py"]
  76cb5eeb_804b_66dd_6905_0c38a9bc0d83 -->|defined in| bd382a4e_442c_13ae_530c_6e34bc43623d
  style 76cb5eeb_804b_66dd_6905_0c38a9bc0d83 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/openai/tests/integration_tests/chat_models/test_base.py lines 960–1001

def test_prediction_tokens() -> None:
    code = dedent(
        """
    /// <summary>
    /// Represents a user with a first name, last name, and username.
    /// </summary>
    public class User
    {
        /// <summary>
        /// Gets or sets the user's first name.
        /// </summary>
        public string FirstName { get; set; }

        /// <summary>
        /// Gets or sets the user's last name.
        /// </summary>
        public string LastName { get; set; }

        /// <summary>
        /// Gets or sets the user's username.
        /// </summary>
        public string Username { get; set; }
    }
    """
    )

    llm = ChatOpenAI(model="gpt-4.1-nano")
    query = (
        "Replace the Username property with an Email property. "
        "Respond only with code, and with no markdown formatting."
    )
    response = llm.invoke(
        [{"role": "user", "content": query}, {"role": "user", "content": code}],
        prediction={"type": "content", "content": code},
    )
    assert isinstance(response, AIMessage)
    assert response.response_metadata is not None
    output_token_details = response.response_metadata["token_usage"][
        "completion_tokens_details"
    ]
    assert output_token_details["accepted_prediction_tokens"] > 0
    assert output_token_details["rejected_prediction_tokens"] > 0