a ag;,@sdZddlmZddlZddlZddlZddlmZmZm Z m Z ddl m Z ddl mZmZddlmZddlmZdd lmZmZdd lmZdd lmZdd lmZe d dddGdddeZdS)zCChain that interprets a prompt and executes python code to do math.) annotationsN)AnyDictListOptional) deprecated)AsyncCallbackManagerForChainRunCallbackManagerForChainRun)BaseLanguageModel)BasePromptTemplate) ConfigDictmodel_validator)ChainLLMChain)PROMPTz0.2.13zThis class is deprecated and will be removed in langchain 1.0. See API reference for replacement: https://api.python.langchain.com/en/latest/chains/langchain.chains.llm_math.base.LLMMathChain.htmlz1.0)ZsincemessageZremovalc@s"eZdZUdZded<dZded<eZded<d Zd ed <d Z d ed <e dddZ e dde dddddZeddddZeddddZd d ddd Zd d!d"d#d$d%Zd d&d"d#d'd(Zd6d"d)d"d*d+d,Zd7d"d-d"d*d.d/Zed dd0d1Ze efd2dddd3d4d5ZdS)8 LLMMathChainaChain that interprets a prompt and executes python code to do math. Note: this class is deprecated. See below for a replacement implementation using LangGraph. The benefits of this implementation are: - Uses LLM tool calling features; - Support for both token-by-token and step-by-step streaming; - Support for checkpointing and memory of chat history; - Easier to modify or extend (e.g., with additional tools, structured responses, etc.) Install LangGraph with: .. code-block:: bash pip install -U langgraph .. code-block:: python import math from typing import Annotated, Sequence from langchain_core.messages import BaseMessage from langchain_core.runnables import RunnableConfig from langchain_core.tools import tool from langchain_openai import ChatOpenAI from langgraph.graph import END, StateGraph from langgraph.graph.message import add_messages from langgraph.prebuilt.tool_node import ToolNode import numexpr from typing_extensions import TypedDict @tool def calculator(expression: str) -> str: """Calculate expression using Python's numexpr library. Expression should be a single line mathematical expression that solves the problem. Examples: "37593 * 67" for "37593 times 67" "37593**(1/5)" for "37593^(1/5)" """ local_dict = {"pi": math.pi, "e": math.e} return str( numexpr.evaluate( expression.strip(), global_dict={}, # restrict access to globals local_dict=local_dict, # add common mathematical functions ) ) llm = ChatOpenAI(model="gpt-4o-mini", temperature=0) tools = [calculator] llm_with_tools = llm.bind_tools(tools, tool_choice="any") class ChainState(TypedDict): """LangGraph state.""" messages: Annotated[Sequence[BaseMessage], add_messages] async def acall_chain(state: ChainState, config: RunnableConfig): last_message = state["messages"][-1] response = await llm_with_tools.ainvoke(state["messages"], config) return {"messages": [response]} async def acall_model(state: ChainState, config: RunnableConfig): response = await llm.ainvoke(state["messages"], config) return {"messages": [response]} graph_builder = StateGraph(ChainState) graph_builder.add_node("call_tool", acall_chain) graph_builder.add_node("execute_tool", ToolNode(tools)) graph_builder.add_node("call_model", acall_model) graph_builder.set_entry_point("call_tool") graph_builder.add_edge("call_tool", "execute_tool") graph_builder.add_edge("execute_tool", "call_model") graph_builder.add_edge("call_model", END) chain = graph_builder.compile() .. code-block:: python example_query = "What is 551368 divided by 82" events = chain.astream( {"messages": [("user", example_query)]}, stream_mode="values", ) async for event in events: event["messages"][-1].pretty_print() .. code-block:: none ================================ Human Message ================================= What is 551368 divided by 82 ================================== Ai Message ================================== Tool Calls: calculator (call_MEiGXuJjJ7wGU4aOT86QuGJS) Call ID: call_MEiGXuJjJ7wGU4aOT86QuGJS Args: expression: 551368 / 82 ================================= Tool Message ================================= Name: calculator 6724.0 ================================== Ai Message ================================== 551368 divided by 82 equals 6724. Example: .. code-block:: python from langchain.chains import LLMMathChain from langchain_community.llms import OpenAI llm_math = LLMMathChain.from_llm(OpenAI()) r llm_chainNzOptional[BaseLanguageModel]llmr promptquestionstr input_keyanswer output_keyTZforbid)Zarbitrary_types_allowedextrabefore)moderr)valuesreturncCsrz ddl}Wnty&tdYn0d|vrntdd|vrn|ddurn|dt}t|d|d|d<|S)NrzXLLMMathChain requires the numexpr package. Please install it with `pip install numexpr`.rzDirectly instantiating an LLMMathChain with an llm is deprecated. Please instantiate with llm_chain argument or using the from_llm class method.rrrr)numexpr ImportErrorwarningswarngetrr)clsrr"rr(l/var/www/html/cobodadashboardai.evdpl.com/venv/lib/python3.9/site-packages/langchain/chains/llm_math/base.pyraise_deprecations    zLLMMathChain.raise_deprecationz List[str])r cCs|jgS)z2Expect input key. :meta private: )rselfr(r(r) input_keysszLLMMathChain.input_keyscCs|jgS)z3Expect output key. :meta private: )rr+r(r(r) output_keysszLLMMathChain.output_keys) expressionr c Cs|ddl}z*tjtjd}t|j|i|d}Wn:tyl}z"td|d|dWYd}~n d}~00t dd|S) Nr)pie)Z global_dict local_dictzLLMMathChain._evaluate("z") raised error: z4. Please try again with a valid numerical expressionz^\[|\]$) r"mathr0r1revaluatestrip Exception ValueErrorresub)r,r/r"r2outputr1r(r(r)_evaluate_expressionsz!LLMMathChain._evaluate_expressionr zDict[str, str]) llm_output run_managerr cCs|j|d|jd|}td|tj}|rn|d}||}|jd|jd|j|d|jdd|}n:|d r~|}n*d |vrd| d d }nt d ||j |iS Ngreen)colorverbosez^```text(.*?)```z Answer: )rByellowzAnswer: zAnswer:zunknown format from LLM: on_textrBr6r9searchDOTALLgroupr< startswithsplitr8rr,r=r>Z text_matchr/r;rr(r(r)_process_llm_results    z LLMMathChain._process_llm_resultrcs|j|d|jdIdH|}td|tj}|r|d}||}|jd|jdIdH|j|d|jdIdHd|}n:|d r|}n*d |vrd| d d }nt d ||j |iSr?rFrMr(r(r)_aprocess_llm_results    z!LLMMathChain._aprocess_llm_resultz$Optional[CallbackManagerForChainRun])inputsr>r cCsF|p t}|||j|jj||jdg|d}|||SNz ```output)rstop callbacks)r get_noop_managerrGrrZpredict get_childrNr,rPr>Z _run_managerr=r(r(r)_calls zLLMMathChain._callz)Optional[AsyncCallbackManagerForChainRun]csX|p t}|||jIdH|jj||jdg|dIdH}|||IdHSrQ)rrTrGrrZapredictrUrOrVr(r(r)_acalls  zLLMMathChain._acallcCsdS)NZllm_math_chainr(r+r(r(r) _chain_type$szLLMMathChain._chain_typer )rrkwargsr cKst||d}|fd|i|S)Nr!rr)r'rrrZrr(r(r)from_llm(s zLLMMathChain.from_llm)N)N)__name__ __module__ __qualname____doc____annotations__rrrrrr Z model_configr classmethodr*propertyr-r.r<rNrOrWrXrYr[r(r(r(r)rs: u    r)r_ __future__rr4r9r$typingrrrrZlangchain_core._apirZlangchain_core.callbacksrr Zlangchain_core.language_modelsr Zlangchain_core.promptsr Zpydanticr r Zlangchain.chains.baserZlangchain.chains.llmrZ langchain.chains.llm_math.promptrrr(r(r(r)s&