Ah9SrSSKJr SSKJrJr SSKJr SSKJ r SSK J r SSK J r SSKJr SS KJr SS KJr SS KJrJr SS KJr \"S SSS9"SS\55rg)zCUse a single chain to route an input to one of multiple llm chains.) annotations)AnyOptional) deprecated)BaseLanguageModel)PromptTemplate)ConversationChain)Chain)LLMChain)MultiRouteChain)LLMRouterChainRouterOutputParser)MULTI_PROMPT_ROUTER_TEMPLATEz0.2.12z1.0zPlease see migration guide here for recommended implementation: https://python.langchain.com/docs/versions/migrating_chains/multi_prompt_chain/)sinceremovalmessagecX\rSrSrSr\SSj5r\SS Sjj5rSr g) MultiPromptChainaGA multi-route chain that uses an LLM router chain to choose amongst prompts. This class is deprecated. See below for a replacement, which offers several benefits, including streaming and batch support. Below is an example implementation: .. code-block:: python from operator import itemgetter from typing import Literal from langchain_core.output_parsers import StrOutputParser from langchain_core.prompts import ChatPromptTemplate from langchain_core.runnables import RunnableConfig from langchain_openai import ChatOpenAI from langgraph.graph import END, START, StateGraph from typing_extensions import TypedDict llm = ChatOpenAI(model="gpt-4o-mini") # Define the prompts we will route to prompt_1 = ChatPromptTemplate.from_messages( [ ("system", "You are an expert on animals."), ("human", "{input}"), ] ) prompt_2 = ChatPromptTemplate.from_messages( [ ("system", "You are an expert on vegetables."), ("human", "{input}"), ] ) # Construct the chains we will route to. These format the input query # into the respective prompt, run it through a chat model, and cast # the result to a string. chain_1 = prompt_1 | llm | StrOutputParser() chain_2 = prompt_2 | llm | StrOutputParser() # Next: define the chain that selects which branch to route to. # Here we will take advantage of tool-calling features to force # the output to select one of two desired branches. route_system = "Route the user's query to either the animal or vegetable expert." route_prompt = ChatPromptTemplate.from_messages( [ ("system", route_system), ("human", "{input}"), ] ) # Define schema for output: class RouteQuery(TypedDict): """Route query to destination expert.""" destination: Literal["animal", "vegetable"] route_chain = route_prompt | llm.with_structured_output(RouteQuery) # For LangGraph, we will define the state of the graph to hold the query, # destination, and final answer. class State(TypedDict): query: str destination: RouteQuery answer: str # We define functions for each node, including routing the query: async def route_query(state: State, config: RunnableConfig): destination = await route_chain.ainvoke(state["query"], config) return {"destination": destination} # And one node for each prompt async def prompt_1(state: State, config: RunnableConfig): return {"answer": await chain_1.ainvoke(state["query"], config)} async def prompt_2(state: State, config: RunnableConfig): return {"answer": await chain_2.ainvoke(state["query"], config)} # We then define logic that selects the prompt based on the classification def select_node(state: State) -> Literal["prompt_1", "prompt_2"]: if state["destination"] == "animal": return "prompt_1" else: return "prompt_2" # Finally, assemble the multi-prompt chain. This is a sequence of two steps: # 1) Select "animal" or "vegetable" via the route_chain, and collect the answer # alongside the input query. # 2) Route the input query to chain_1 or chain_2, based on the # selection. graph = StateGraph(State) graph.add_node("route_query", route_query) graph.add_node("prompt_1", prompt_1) graph.add_node("prompt_2", prompt_2) graph.add_edge(START, "route_query") graph.add_conditional_edges("route_query", select_node) graph.add_edge("prompt_1", END) graph.add_edge("prompt_2", END) app = graph.compile() result = await app.ainvoke({"query": "what color are carrots"}) print(result["destination"]) print(result["answer"]) cS/$)Ntext)selfs \/var/www/html/shao/venv/lib/python3.13/site-packages/langchain/chains/router/multi_prompt.py output_keysMultiPromptChain.output_keyss xNc xUVs/sHoUSSUS3PM nnSRU5n[R"US9n[US/[ 5S9n [ R "X5n 0n UH%n U Sn U Sn[US/S 9n[XS 9nUX'M' U=(d [US S 9nU"SU U US .UD6$s snf)zCConvenience constructor for instantiating from destination prompts.namez: description ) destinationsinput)templateinput_variables output_parserprompt_template)r$r%)llmpromptr)r( output_key) router_chaindestination_chains default_chainr) joinrformatrrr from_llmr r )clsr( prompt_infosr-kwargspr"destinations_strrouter_template router_promptr+r,p_inforr'r)chain_default_chains r from_promptsMultiPromptChain.from_promptssEQQLqV9+R-(8'9:L Q99\26==) '$$I,. &..sB "F&>D$%67O#_wiXF4E',  $ # 'W*;PV*W %1(    'RsB7r)returnz list[str])N) r(rr2zlist[dict[str, str]]r-zOptional[Chain]r3rr=r) __name__ __module__ __qualname____firstlineno____doc__propertyr classmethodr;__static_attributes__rrrrrsfrh *.    +  '        rrN)rB __future__rtypingrrlangchain_core._apirlangchain_core.language_modelsrlangchain_core.promptsrlangchain.chainsr langchain.chains.baser langchain.chains.llmr langchain.chains.router.baser "langchain.chains.router.llm_routerr r+langchain.chains.router.multi_prompt_promptrrrrrrQsXI" *<1.')8QT   Z Z Z Z r