RunnableRetry#

class langchain_core.runnables.retry.RunnableRetry[source]#

Bases: RunnableBindingBase[Input, Output]

Retry a Runnable if it fails.

RunnableRetry can be used to add retry logic to any object that subclasses the base Runnable.

Such retries are especially useful for network calls that may fail due to transient errors.

The RunnableRetry is implemented as a RunnableBinding. The easiest way to use it is through the .with_retry() method on all Runnables.

Example:

Here’s an example that uses a RunnableLambda to raise an exception

import time

def foo(input) -> None:
    '''Fake function that raises an exception.'''
    raise ValueError(f"Invoking foo failed. At time {time.time()}")

runnable = RunnableLambda(foo)

runnable_with_retries = runnable.with_retry(
    retry_if_exception_type=(ValueError,), # Retry only on ValueError
    wait_exponential_jitter=True, # Add jitter to the exponential backoff
    stop_after_attempt=2, # Try twice
)

# The method invocation above is equivalent to the longer form below:

runnable_with_retries = RunnableRetry(
    bound=runnable,
    retry_exception_types=(ValueError,),
    max_attempt_number=2,
    wait_exponential_jitter=True
)

This logic can be used to retry any Runnable, including a chain of Runnables, but in general it’s best practice to keep the scope of the retry as small as possible. For example, if you have a chain of Runnables, you should only retry the Runnable that is likely to fail, not the entire chain.

Example

from langchain_core.chat_models import ChatOpenAI
from langchain_core.prompts import PromptTemplate

template = PromptTemplate.from_template("tell me a joke about {topic}.")
model = ChatOpenAI(temperature=0.5)

# Good
chain = template | model.with_retry()

# Bad
chain = template | model
retryable_chain = chain.with_retry()

Create a RunnableBinding from a Runnable and kwargs.

Parameters:

bound – The underlying Runnable that this Runnable delegates calls to.
kwargs – optional kwargs to pass to the underlying Runnable, when running the underlying Runnable (e.g., via invoke, batch, transform, or stream or async variants) Defaults to None.
config – optional config to bind to the underlying Runnable. Defaults to None.
config_factories – optional list of config factories to apply to the config before binding to the underlying Runnable. Defaults to None.
custom_input_type – Specify to override the input type of the underlying Runnable with a custom type. Defaults to None.
custom_output_type – Specify to override the output type of the underlying Runnable with a custom type. Defaults to None.
**other_kwargs – Unpacked into the base class.

Note

RunnableRetry implements the standard Runnable Interface. 🏃

The Runnable Interface has additional methods that are available on runnables, such as with_types, with_retry, assign, bind, get_graph, and more.

param bound: Runnable[Input, Output] [Required]#: The underlying Runnable that this Runnable delegates to.

param config: RunnableConfig [Optional]#: The config to bind to the underlying Runnable.

param config_factories: List[Callable[[RunnableConfig], RunnableConfig]] [Optional]#: The config factories to bind to the underlying Runnable.

param custom_input_type: Any | None = None#

Override the input type of the underlying Runnable with a custom type.

The type can be a pydantic model, or a type annotation (e.g., List[str]).

param custom_output_type: Any | None = None#

Override the output type of the underlying Runnable with a custom type.

The type can be a pydantic model, or a type annotation (e.g., List[str]).

param kwargs: Mapping[str, Any] [Optional]#

kwargs to pass to the underlying Runnable when running.

For example, when the Runnable binding is invoked the underlying Runnable will be invoked with the same input but with these additional kwargs.

param max_attempt_number: int = 3#: The maximum number of attempts to retry the Runnable.

param retry_exception_types: Tuple[Type[BaseException], ...] = (<class 'Exception'>,)#

The exception types to retry on. By default all exceptions are retried.

In general you should only retry on exceptions that are likely to be transient, such as network errors.

Good exceptions to retry are all server errors (5xx) and selected client errors (4xx) such as 429 Too Many Requests.

param wait_exponential_jitter: bool = True#: Whether to add jitter to the exponential backoff.

async abatch(inputs: List[Input], config: RunnableConfig | List[RunnableConfig] | None = None, *, return_exceptions: bool = False, **kwargs: Any) → List[Output][source]#

Default implementation runs ainvoke in parallel using asyncio.gather.

The default implementation of batch works well for IO bound runnables.

Subclasses should override this method if they can batch more efficiently; e.g., if the underlying Runnable uses an API which supports a batch mode.

Parameters:

inputs (List[Input]) – A list of inputs to the Runnable.
config (RunnableConfig | List[RunnableConfig] | None) – A config to use when invoking the Runnable. The config supports standard keys like ‘tags’, ‘metadata’ for tracing purposes, ‘max_concurrency’ for controlling how much work to do in parallel, and other keys. Please refer to the RunnableConfig for more details. Defaults to None.
return_exceptions (bool) – Whether to return exceptions instead of raising them. Defaults to False.
kwargs (Any) – Additional keyword arguments to pass to the Runnable.

Returns:

A list of outputs from the Runnable.

Return type:

List[Output]

async abatch_as_completed(inputs: Sequence[Input], config: RunnableConfig | Sequence[RunnableConfig] | None = None, *, return_exceptions: bool = False, **kwargs: Any | None) → AsyncIterator[Tuple[int, Output | Exception]]#

Run ainvoke in parallel on a list of inputs, yielding results as they complete.

Parameters:

inputs (Sequence[Input]) – A list of inputs to the Runnable.
config (RunnableConfig | Sequence[RunnableConfig] | None) – A config to use when invoking the Runnable. The config supports standard keys like ‘tags’, ‘metadata’ for tracing purposes, ‘max_concurrency’ for controlling how much work to do in parallel, and other keys. Please refer to the RunnableConfig for more details. Defaults to None. Defaults to None.
return_exceptions (bool) – Whether to return exceptions instead of raising them. Defaults to False.
kwargs (Any | None) – Additional keyword arguments to pass to the Runnable.

Yields:

A tuple of the index of the input and the output from the Runnable.

Return type:

AsyncIterator[Tuple[int, Output | Exception]]

async ainvoke(input: Input, config: RunnableConfig | None = None, **kwargs: Any) → Output[source]#

Default implementation of ainvoke, calls invoke from a thread.

The default implementation allows usage of async code even if the Runnable did not implement a native async version of invoke.

Subclasses should override this method if they can run asynchronously.

Parameters:

input (Input) –
config (RunnableConfig | None) –
kwargs (Any) –

Return type:

Output

async astream(input: Input, config: RunnableConfig | None = None, **kwargs: Any | None) → AsyncIterator[Output]#

Default implementation of astream, which calls ainvoke. Subclasses should override this method if they support streaming output.

Parameters:

input (Input) – The input to the Runnable.
config (RunnableConfig | None) – The config to use for the Runnable. Defaults to None.
kwargs (Any | None) – Additional keyword arguments to pass to the Runnable.

Yields:

The output of the Runnable.

Return type:

AsyncIterator[Output]

async astream_events(input: Input, config: RunnableConfig | None = None, **kwargs: Any | None) → AsyncIterator[StandardStreamEvent | CustomStreamEvent]#

Beta

This API is in beta and may change in the future.

Generate a stream of events.

Use to create an iterator over StreamEvents that provide real-time information about the progress of the Runnable, including StreamEvents from intermediate results.

A StreamEvent is a dictionary with the following schema:

event: str - Event names are of the
format: on_[runnable_type]_(start|stream|end).
name: str - The name of the Runnable that generated the event.
run_id: str - randomly generated ID associated with the given execution of
the Runnable that emitted the event. A child Runnable that gets invoked as part of the execution of a parent Runnable is assigned its own unique ID.
parent_ids: List[str] - The IDs of the parent runnables that
generated the event. The root Runnable will have an empty list. The order of the parent IDs is from the root to the immediate parent. Only available for v2 version of the API. The v1 version of the API will return an empty list.
tags: Optional[List[str]] - The tags of the Runnable that generated
the event.
metadata: Optional[Dict[str, Any]] - The metadata of the Runnable
that generated the event.
data: Dict[str, Any]

Below is a table that illustrates some evens that might be emitted by various chains. Metadata fields have been omitted from the table for brevity. Chain definitions have been included after the table.

ATTENTION This reference table is for the V2 version of the schema.

event	name	chunk	input	output
on_chat_model_start	[model name]		{“messages”: [[SystemMessage, HumanMessage]]}
on_chat_model_stream	[model name]	AIMessageChunk(content=”hello”)
on_chat_model_end	[model name]		{“messages”: [[SystemMessage, HumanMessage]]}	AIMessageChunk(content=”hello world”)
on_llm_start	[model name]		{‘input’: ‘hello’}
on_llm_stream	[model name]	‘Hello’
on_llm_end	[model name]		‘Hello human!’
on_chain_start	format_docs
on_chain_stream	format_docs	“hello world!, goodbye world!”
on_chain_end	format_docs		[Document(…)]	“hello world!, goodbye world!”
on_tool_start	some_tool		{“x”: 1, “y”: “2”}
on_tool_end	some_tool			{“x”: 1, “y”: “2”}
on_retriever_start	[retriever name]		{“query”: “hello”}
on_retriever_end	[retriever name]		{“query”: “hello”}	[Document(…), ..]
on_prompt_start	[template_name]		{“question”: “hello”}
on_prompt_end	[template_name]		{“question”: “hello”}	ChatPromptValue(messages: [SystemMessage, …])

In addition to the standard events, users can also dispatch custom events (see example below).

Custom events will be only be surfaced with in the v2 version of the API!

A custom event has following format:

Attribute	Type	Description
name	str	A user defined name for the event.
data	Any	The data associated with the event. This can be anything, though we suggest making it JSON serializable.

Here are declarations associated with the standard events shown above:

format_docs:

def format_docs(docs: List[Document]) -> str:
    '''Format the docs.'''
    return ", ".join([doc.page_content for doc in docs])

format_docs = RunnableLambda(format_docs)

some_tool:

@tool
def some_tool(x: int, y: str) -> dict:
    '''Some_tool.'''
    return {"x": x, "y": y}

prompt:

template = ChatPromptTemplate.from_messages(
    [("system", "You are Cat Agent 007"), ("human", "{question}")]
).with_config({"run_name": "my_template", "tags": ["my_template"]})

Example:

from langchain_core.runnables import RunnableLambda

async def reverse(s: str) -> str:
    return s[::-1]

chain = RunnableLambda(func=reverse)

events = [
    event async for event in chain.astream_events("hello", version="v2")
]

# will produce the following events (run_id, and parent_ids
# has been omitted for brevity):
[
    {
        "data": {"input": "hello"},
        "event": "on_chain_start",
        "metadata": {},
        "name": "reverse",
        "tags": [],
    },
    {
        "data": {"chunk": "olleh"},
        "event": "on_chain_stream",
        "metadata": {},
        "name": "reverse",
        "tags": [],
    },
    {
        "data": {"output": "olleh"},
        "event": "on_chain_end",
        "metadata": {},
        "name": "reverse",
        "tags": [],
    },
]

Example: Dispatch Custom Event

from langchain_core.callbacks.manager import (
    adispatch_custom_event,
)
from langchain_core.runnables import RunnableLambda, RunnableConfig
import asyncio


async def slow_thing(some_input: str, config: RunnableConfig) -> str:
    """Do something that takes a long time."""
    await asyncio.sleep(1) # Placeholder for some slow operation
    await adispatch_custom_event(
        "progress_event",
        {"message": "Finished step 1 of 3"},
        config=config # Must be included for python < 3.10
    )
    await asyncio.sleep(1) # Placeholder for some slow operation
    await adispatch_custom_event(
        "progress_event",
        {"message": "Finished step 2 of 3"},
        config=config # Must be included for python < 3.10
    )
    await asyncio.sleep(1) # Placeholder for some slow operation
    return "Done"

slow_thing = RunnableLambda(slow_thing)

async for event in slow_thing.astream_events("some_input", version="v2"):
    print(event)

Parameters:

input (Input) – The input to the Runnable.
config (RunnableConfig | None) – The config to use for the Runnable.
version – The version of the schema to use either v2 or v1. Users should use v2. v1 is for backwards compatibility and will be deprecated in 0.4.0. No default will be assigned until the API is stabilized. custom events will only be surfaced in v2.
include_names – Only include events from runnables with matching names.
include_types – Only include events from runnables with matching types.
include_tags – Only include events from runnables with matching tags.
exclude_names – Exclude events from runnables with matching names.
exclude_types – Exclude events from runnables with matching types.
exclude_tags – Exclude events from runnables with matching tags.
kwargs (Any | None) – Additional keyword arguments to pass to the Runnable. These will be passed to astream_log as this implementation of astream_events is built on top of astream_log.

Yields:

An async stream of StreamEvents.

Raises:

NotImplementedError – If the version is not v1 or v2.

Return type:

AsyncIterator[StandardStreamEvent | CustomStreamEvent]

batch(inputs: List[Input], config: RunnableConfig | List[RunnableConfig] | None = None, *, return_exceptions: bool = False, **kwargs: Any) → List[Output][source]#

Default implementation runs invoke in parallel using a thread pool executor.

The default implementation of batch works well for IO bound runnables.

Subclasses should override this method if they can batch more efficiently; e.g., if the underlying Runnable uses an API which supports a batch mode.

Parameters:

inputs (List[Input]) –
config (RunnableConfig | List[RunnableConfig] | None) –
return_exceptions (bool) –
kwargs (Any) –

Return type:

List[Output]

batch_as_completed(inputs: Sequence[Input], config: RunnableConfig | Sequence[RunnableConfig] | None = None, *, return_exceptions: bool = False, **kwargs: Any | None) → Iterator[Tuple[int, Output | Exception]]#

Run invoke in parallel on a list of inputs, yielding results as they complete.

Parameters:

inputs (Sequence[Input]) –
config (RunnableConfig | Sequence[RunnableConfig] | None) –
return_exceptions (bool) –
kwargs (Any | None) –

Return type:

Iterator[Tuple[int, Output | Exception]]

configurable_alternatives(which: ConfigurableField, *, default_key: str = 'default', prefix_keys: bool = False, **kwargs: Runnable[Input, Output] | Callable[[], Runnable[Input, Output]]) → RunnableSerializable[Input, Output]#

Configure alternatives for Runnables that can be set at runtime.

Parameters:

which (ConfigurableField) – The ConfigurableField instance that will be used to select the alternative.
default_key (str) – The default key to use if no alternative is selected. Defaults to “default”.
prefix_keys (bool) – Whether to prefix the keys with the ConfigurableField id. Defaults to False.
**kwargs (Runnable[Input, Output] | Callable[[], Runnable[Input, Output]]) – A dictionary of keys to Runnable instances or callables that return Runnable instances.

Returns:

A new Runnable with the alternatives configured.

Return type:

RunnableSerializable[Input, Output]

from langchain_anthropic import ChatAnthropic
from langchain_core.runnables.utils import ConfigurableField
from langchain_openai import ChatOpenAI

model = ChatAnthropic(
    model_name="claude-3-sonnet-20240229"
).configurable_alternatives(
    ConfigurableField(id="llm"),
    default_key="anthropic",
    openai=ChatOpenAI()
)

# uses the default model ChatAnthropic
print(model.invoke("which organization created you?").content)

# uses ChatOpenAI
print(
    model.with_config(
        configurable={"llm": "openai"}
    ).invoke("which organization created you?").content
)

configurable_fields(**kwargs: ConfigurableField | ConfigurableFieldSingleOption | ConfigurableFieldMultiOption) → RunnableSerializable[Input, Output]#

Configure particular Runnable fields at runtime.

Parameters:: **kwargs (ConfigurableField | ConfigurableFieldSingleOption | ConfigurableFieldMultiOption) – A dictionary of ConfigurableField instances to configure.
Returns:: A new Runnable with the fields configured.
Return type:: RunnableSerializable[Input, Output]

from langchain_core.runnables import ConfigurableField
from langchain_openai import ChatOpenAI

model = ChatOpenAI(max_tokens=20).configurable_fields(
    max_tokens=ConfigurableField(
        id="output_token_number",
        name="Max tokens in the output",
        description="The maximum number of tokens in the output",
    )
)

# max_tokens = 20
print(
    "max_tokens_20: ",
    model.invoke("tell me something about chess").content
)

# max_tokens = 200
print("max_tokens_200: ", model.with_config(
    configurable={"output_token_number": 200}
    ).invoke("tell me something about chess").content
)

invoke(input: Input, config: RunnableConfig | None = None, **kwargs: Any) → Output[source]#

Transform a single input into an output. Override to implement.

Parameters:

input (Input) – The input to the Runnable.
config (RunnableConfig | None) – A config to use when invoking the Runnable. The config supports standard keys like ‘tags’, ‘metadata’ for tracing purposes, ‘max_concurrency’ for controlling how much work to do in parallel, and other keys. Please refer to the RunnableConfig for more details.
kwargs (Any) –

Returns:

The output of the Runnable.

Return type:

Output

stream(input: Input, config: RunnableConfig | None = None, **kwargs: Any | None) → Iterator[Output]#

Default implementation of stream, which calls invoke. Subclasses should override this method if they support streaming output.

Parameters:

input (Input) – The input to the Runnable.
config (RunnableConfig | None) – The config to use for the Runnable. Defaults to None.
kwargs (Any | None) – Additional keyword arguments to pass to the Runnable.

Yields:

The output of the Runnable.

Return type:

Iterator[Output]

to_json() → SerializedConstructor | SerializedNotImplemented#

Serialize the Runnable to JSON.

Returns:: A JSON-serializable representation of the Runnable.
Return type:: SerializedConstructor | SerializedNotImplemented