Runnable that can be dynamically configured.
A RunnableConfigurableAlternatives should be initiated using the
configurable_alternatives method of a Runnable or can be
initiated directly as well.
Here is an example of using a RunnableConfigurableAlternatives that uses
alternative prompts to illustrate its functionality:
from langchain_core.runnables import ConfigurableField
from langchain_openai import ChatOpenAI
# This creates a RunnableConfigurableAlternatives for Prompt Runnable
# with two alternatives.
prompt = PromptTemplate.from_template(
"Tell me a joke about {topic}"
).configurable_alternatives(
ConfigurableField(id="prompt"),
default_key="joke",
poem=PromptTemplate.from_template("Write a short poem about {topic}"),
)
# When invoking the created RunnableSequence, you can pass in the
# value for your ConfigurableField's id which in this case will either be
# `joke` or `poem`.
chain = prompt | ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)
# The `with_config` method brings in the desired Prompt Runnable in your
# Runnable Sequence.
chain.with_config(configurable={"prompt": "poem"}).invoke({"topic": "bears"})Equivalently, you can initialize RunnableConfigurableAlternatives directly
and use in LCEL in the same way:
from langchain_core.runnables import ConfigurableField
from langchain_core.runnables.configurable import (
RunnableConfigurableAlternatives,
)
from langchain_openai import ChatOpenAI
prompt = RunnableConfigurableAlternatives(
which=ConfigurableField(id="prompt"),
default=PromptTemplate.from_template("Tell me a joke about {topic}"),
default_key="joke",
prefix_keys=False,
alternatives={
"poem": PromptTemplate.from_template("Write a short poem about {topic}")
},
)
chain = prompt | ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)
chain.with_config(configurable={"prompt": "poem"}).invoke({"topic": "bears"})The ConfigurableField to use to choose between alternatives.
The alternatives to choose from.
The enum value to use for the default option.
Whether to prefix configurable fields of each alternative with a namespace of the form <which.id>==<alternative_key>, e.g. a key named "temperature" used by the alternative named "gpt3" becomes "model==gpt3/temperature".
Return True as this class is serializable.
Get the namespace of the LangChain object.
Prepare the Runnable for invocation.
Invoke the retriever to get relevant documents.
Asynchronously invoke the retriever to get relevant documents.
Return True as this class is serializable.
Get the namespace of the LangChain object.
Return a unique identifier for this class for serialization purposes.
Convert the graph to a JSON-serializable format.
Serialize a "not implemented" object.
Get a JSON schema that represents the input to the Runnable.
Get a JSON schema that represents the output of the Runnable.
The type of config this Runnable accepts specified as a Pydantic model.
Get a JSON schema that represents the config of the Runnable.
Return a list of prompts used by this Runnable.
Pipe Runnable objects.
Pick keys from the output dict of this Runnable.
Merge the Dict input with the output produced by the mapping argument.
Invoke the retriever to get relevant documents.
Asynchronously invoke the retriever to get relevant documents.
Run invoke in parallel on a list of inputs.
Run ainvoke in parallel on a list of inputs.
Stream all output from a Runnable, as reported to the callback system.
Generate a stream of events.
Bind arguments to a Runnable, returning a new Runnable.
Bind lifecycle listeners to a Runnable, returning a new Runnable.
Bind async lifecycle listeners to a Runnable.
Bind input and output types to a Runnable, returning a new Runnable.
Create a new Runnable that retries the original Runnable on exceptions.
Map a function to multiple iterables.
Add fallbacks to a Runnable, returning a new Runnable.
Create a BaseTool from a Runnable.