langchain 0.3.9__py3-none-any.whl → 0.3.10__py3-none-any.whl

langchain/chains/router/multi_prompt.py

@@ -20,9 +20,8 @@ from langchain.chains.router.multi_prompt_prompt import MULTI_PROMPT_ROUTER_TEMP
     since="0.2.12",
     removal="1.0",
     message=(
-        "Use RunnableLambda to select from multiple prompt templates. See example "
-        "in API reference: "
-        "https://api.python.langchain.com/en/latest/chains/langchain.chains.router.multi_prompt.MultiPromptChain.html"  # noqa: E501
+        "Please see migration guide here for recommended implementation: "
+        "https://python.langchain.com/docs/versions/migrating_chains/multi_prompt_chain/"  # noqa: E501
     ),
 )
 class MultiPromptChain(MultiRouteChain):
@@ -37,60 +36,109 @@ class MultiPromptChain(MultiRouteChain):
 
             from operator import itemgetter
             from typing import Literal
-            from typing_extensions import TypedDict
 
             from langchain_core.output_parsers import StrOutputParser
             from langchain_core.prompts import ChatPromptTemplate
-            from langchain_core.runnables import RunnableLambda, RunnablePassthrough
+            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", "{query}"),
+                    ("human", "{input}"),
                 ]
             )
             prompt_2 = ChatPromptTemplate.from_messages(
                 [
                     ("system", "You are an expert on vegetables."),
-                    ("human", "{query}"),
+                    ("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", "{query}"),
+                    ("human", "{input}"),
                 ]
             )
 
 
+            # Define schema for output:
             class RouteQuery(TypedDict):
-                \"\"\"Route query to destination.\"\"\"
+                \"\"\"Route query to destination expert.\"\"\"
+
                 destination: Literal["animal", "vegetable"]
 
 
-            route_chain = (
-                route_prompt
-                | llm.with_structured_output(RouteQuery)
-                | itemgetter("destination")
-            )
+            route_chain = route_prompt | llm.with_structured_output(RouteQuery)
 
-            chain = {
-                "destination": route_chain,  # "animal" or "vegetable"
-                "query": lambda x: x["query"],  # pass through input query
-            } | RunnableLambda(
-                # if animal, chain_1. otherwise, chain_2.
-                lambda x: chain_1 if x["destination"] == "animal" else chain_2,
-            )
 
-            chain.invoke({"query": "what color are carrots"})
+            # 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"])
     """  # noqa: E501
 
     @property

{langchain-0.3.9.dist-info → langchain-0.3.10.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: langchain
-Version: 0.3.9
+Version: 0.3.10
 Summary: Building applications with LLMs through composability
 Home-page: https://github.com/langchain-ai/langchain
 License: MIT
@@ -11,11 +11,12 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Requires-Dist: PyYAML (>=5.3)
 Requires-Dist: SQLAlchemy (>=1.4,<3)
 Requires-Dist: aiohttp (>=3.8.3,<4.0.0)
 Requires-Dist: async-timeout (>=4.0.0,<5.0.0) ; python_version < "3.11"
-Requires-Dist: langchain-core (>=0.3.21,<0.4.0)
+Requires-Dist: langchain-core (>=0.3.22,<0.4.0)
 Requires-Dist: langchain-text-splitters (>=0.3.0,<0.4.0)
 Requires-Dist: langsmith (>=0.1.17,<0.2.0)
 Requires-Dist: numpy (>=1.22.4,<2) ; python_version < "3.12"

{langchain-0.3.9.dist-info → langchain-0.3.10.dist-info}/RECORD

@@ -327,7 +327,7 @@ langchain/chains/router/__init__.py,sha256=r66J28FWIORVB5QIZ1d8R_HsiBaV1eQMZDZvM
 langchain/chains/router/base.py,sha256=ws6i8C4nk7YWmBqkXBcJ-FybNx4OeDJE-L1IELLK3M4,4517
 langchain/chains/router/embedding_router.py,sha256=hR5hOuwBdMBo_U3lo9SSwBfnVACR0ZpNc-nmDpei5hw,3069
 langchain/chains/router/llm_router.py,sha256=6FQUTXvZ9pekVkPeTNvQsj1jD9JdmfpMkxIPMe4oTMU,6994
-langchain/chains/router/multi_prompt.py,sha256=pqBIW8fLH6esLd9uiuGS5aJeXuuPTQcv7jaOHU8YhSE,4887
+langchain/chains/router/multi_prompt.py,sha256=lLpJsYShzRBnvwtV3AaBbUcB8x6sK1PSxqDveCSC65A,6994
 langchain/chains/router/multi_prompt_prompt.py,sha256=T8UbIuxblnI6Byhw-BMAzwQcbB5ww3N6BiMqMJxS6Jc,1156
 langchain/chains/router/multi_retrieval_prompt.py,sha256=VUYGLWbwGiv03aSMW5sjdGNwsEa9FKgq0RcK5o3lkH4,1079
 langchain/chains/router/multi_retrieval_qa.py,sha256=tjIhHEbOwtF3CLq0qQ8Kd78ao5BXRKZLsm9UlmHrdtQ,4254
@@ -1335,8 +1335,8 @@ langchain/vectorstores/xata.py,sha256=HW_Oi5Hz8rH2JaUhRNWQ-3hLYmNzD8eAz6K5YqPArm
 langchain/vectorstores/yellowbrick.py,sha256=-lnjGcRE8Q1nEPOTdbKYTw5noS2cy2ce1ePOU804-_o,624
 langchain/vectorstores/zep.py,sha256=RJ2auxoA6uHHLEZknw3_jeFmYJYVt-PWKMBcNMGV6TM,798
 langchain/vectorstores/zilliz.py,sha256=XhPPIUfKPFJw0_svCoBgCnNkkBLoRVVcyuMfOnE5IxU,609
-langchain-0.3.9.dist-info/LICENSE,sha256=TsZ-TKbmch26hJssqCJhWXyGph7iFLvyFBYAa3stBHg,1067
-langchain-0.3.9.dist-info/METADATA,sha256=kWM48_6bifCEFs4A4ok2IMmndji2jzfNT7dbLA8WpiU,7077
-langchain-0.3.9.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
-langchain-0.3.9.dist-info/entry_points.txt,sha256=IgKjoXnkkVC8Nm7ggiFMCNAk01ua6RVTb9cmZTVNm5w,58
-langchain-0.3.9.dist-info/RECORD,,
+langchain-0.3.10.dist-info/LICENSE,sha256=TsZ-TKbmch26hJssqCJhWXyGph7iFLvyFBYAa3stBHg,1067
+langchain-0.3.10.dist-info/METADATA,sha256=P5V_UT3Cp3vgRhV8lYufDJquT0X09f0J-UoJ_dFGxPA,7129
+langchain-0.3.10.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+langchain-0.3.10.dist-info/entry_points.txt,sha256=IgKjoXnkkVC8Nm7ggiFMCNAk01ua6RVTb9cmZTVNm5w,58
+langchain-0.3.10.dist-info/RECORD,,

{langchain-0.3.9.dist-info → langchain-0.3.10.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 1.8.1
+Generator: poetry-core 1.9.1
 Root-Is-Purelib: true
 Tag: py3-none-any