init() — langchain Function Reference

Architecture documentation for the __init__() function in model_retry.py from the langchain codebase.

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ __init__() — langchain Function Reference

Dependency Diagram

graph TD
  092957e8_8312_02a4_3864_557cb176b0ce["__init__()"]
  5e783bd0_a142_0fd6_3238_fc2d9985440d["ModelRetryMiddleware"]
  092957e8_8312_02a4_3864_557cb176b0ce -->|defined in| 5e783bd0_a142_0fd6_3238_fc2d9985440d
  style 092957e8_8312_02a4_3864_557cb176b0ce fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain_v1/langchain/agents/middleware/model_retry.py lines 111–169

    def __init__(
        self,
        *,
        max_retries: int = 2,
        retry_on: RetryOn = (Exception,),
        on_failure: OnFailure = "continue",
        backoff_factor: float = 2.0,
        initial_delay: float = 1.0,
        max_delay: float = 60.0,
        jitter: bool = True,
    ) -> None:
        """Initialize `ModelRetryMiddleware`.

        Args:
            max_retries: Maximum number of retry attempts after the initial call.

                Must be `>= 0`.
            retry_on: Either a tuple of exception types to retry on, or a callable
                that takes an exception and returns `True` if it should be retried.

                Default is to retry on all exceptions.
            on_failure: Behavior when all retries are exhausted.

                Options:

                - `'continue'`: Return an `AIMessage` with error details,
                    allowing the agent to continue with an error response.
                - `'error'`: Re-raise the exception, stopping agent execution.
                - **Custom callable:** Function that takes the exception and returns a
                    string for the `AIMessage` content, allowing custom error
                    formatting.
            backoff_factor: Multiplier for exponential backoff.

                Each retry waits `initial_delay * (backoff_factor ** retry_number)`
                seconds.

                Set to `0.0` for constant delay.
            initial_delay: Initial delay in seconds before first retry.
            max_delay: Maximum delay in seconds between retries.

                Caps exponential backoff growth.
            jitter: Whether to add random jitter (`±25%`) to delay to avoid thundering herd.

        Raises:
            ValueError: If `max_retries < 0` or delays are negative.
        """
        super().__init__()

        # Validate parameters
        validate_retry_params(max_retries, initial_delay, max_delay, backoff_factor)

        self.max_retries = max_retries
        self.tools = []  # No additional tools registered by this middleware
        self.retry_on = retry_on
        self.on_failure = on_failure
        self.backoff_factor = backoff_factor
        self.initial_delay = initial_delay
        self.max_delay = max_delay
        self.jitter = jitter