Ng;,dZddlmZddlZddlZddlZddlmZmZm Z m Z ddl m Z ddl mZmZddlmZddlmZdd lmZmZdd lmZdd lmZdd lmZe d ddGddeZdS)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)sincemessageremovalcDeZdZUdZded<dZded< eZded< d Zd ed <d Z d ed <e ddZ e de d-dZed.dZed.dZd/dZd0d!Zd1d#Z d2d3d&Z d2d4d(Zed5d)Ze efd6d,ZdS)7 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_keyTforbid)arbitrary_types_allowedextrabefore)modevaluesrreturnrc ddl}n#t$rtdwxYwd|vrUtjdd|vr=|d5|dt }t |d||d<|S)NrzXLLMMathChain requires the numexpr package. Please install it with `pip install numexpr`.rzDirectly instantiating an LLMMathChain with an llm is deprecated. Please instantiate with llm_chain argument or using the from_llm class method.rrrr)numexpr ImportErrorwarningswarngetrr)clsr%r)rs Z/var/www/html/ai-engine/env/lib/python3.11/site-packages/langchain/chains/llm_math/base.pyraise_deprecationzLLMMathChain.raise_deprecations  NNNN   @   F?? M     &((VE]-FHf55&.6%=&P&P&P{# s! List[str]c|jgS)z2Expect input key. :meta private: )rselfs r/ input_keyszLLMMathChain.input_keyss c|jgS)z3Expect output key. :meta private: )rr3s r/ output_keyszLLMMathChain.output_keyss   r6 expressionc*ddl} tjtjd}t ||i|}n(#t$r}td|d|dd}~wwxYwtj dd|S) Nr)pie) global_dict local_dictzLLMMathChain._evaluate("z") raised error: z4. Please try again with a valid numerical expressionz^\[|\]$) r)mathr;r<revaluatestrip Exception ValueErrorresub)r4r9r)r>outputr<s r/_evaluate_expressionz!LLMMathChain._evaluate_expressions  $df55J  $$&& ")!FF   F:FFFFF  vj"f---sAA A<!A77A< llm_output run_managerr Dict[str, str]c&||d|j|}tjd|tj}|ri|d}||}|d|j||d|jd|z}nM|d r|}n5d |vrd| d d z}ntd ||j |iS Ngreen)colorverbosez^```text(.*?)```z Answer: )rPyellowzAnswer: zAnswer:zunknown format from LLM: on_textrPrBrEsearchDOTALLgrouprH startswithsplitrDrr4rIrJ text_matchr9rGrs r/_process_llm_resultz LLMMathChain._process_llm_results' Jgt|LLL%%'' Y2J JJ  G#))!,,J..z::F    dl  C C C   h  M M M&(FF  " "9 - - GFF * $ $*"2"29"="=b"AAFFEEEFF F((r6r cNK||d|jd{V|}tjd|tj}|ru|d}||}|d|jd{V||d|jd{Vd|z}nM|d r|}n5d |vrd| d d z}ntd ||j |iSrMrTr[s r/_aprocess_llm_resultz!LLMMathChain._aprocess_llm_resultsa !!*GT\!RRRRRRRRR%%'' Y2J JJ  G#))!,,J..z::F%%lDL%II I I I I I I I%%fHdl%SS S S S S S S S&(FF  " "9 - - GFF * $ $*"2"29"="=b"AAFFEEEFF F((r6inputs$Optional[CallbackManagerForChainRun]c|ptj}|||j|j||jdg|}|||SNz ```output)rstop callbacks)r get_noop_managerrUrrpredict get_childr]r4r`rJ _run_managerrIs r/_callzLLMMathChain._calls #S&@&Q&S&S VDN3444^++DN+",,..,  '' LAAAr6)Optional[AsyncCallbackManagerForChainRun]c6K|ptj}|||jd{V|j||jdg|d{V}|||d{VSrc)r rfrUrrapredictrhr_ris r/_acallzLLMMathChain._acalls #X&E&V&X&X ""6$.#9:::::::::>22DN+",,..3        ..z<HHHHHHHHHr6cdS)Nllm_math_chainr3s r/ _chain_typezLLMMathChain._chain_type$sr6r kwargsc 8t||}|dd|i|S)Nr(rrrr)r.rrrtrs r/from_llmzLLMMathChain.from_llm(s1V444 s11Y1&111r6)r%rr&r)r&r1)r9rr&r)rIrrJr r&rK)rIrrJr r&rK)N)r`rKrJrar&rK)r`rKrJrlr&rK)r&r)rr rr rtrr&r)__name__ __module__ __qualname____doc____annotations__rrrrrr model_configr classmethodr0propertyr5r8rHr]r_rkrorsrvrrr6r/rrsssj'+C++++*!'F''''IIJ: $L _(###[$#&   X !!!X!....*))))())))2=A B B B B B"BF I I I I I   X &,2222[222r6r)rz __future__rr@rEr+typingrrrrlangchain_core._apirlangchain_core.callbacksr r langchain_core.language_modelsr langchain_core.promptsr pydanticr rlangchain.chains.baserlangchain.chains.llmr langchain.chains.llm_math.promptrrrrr6r/rsvII"""""" ,,,,,,,,,,,,******=<<<<<55555500000000''''''))))))333333   m O2O2O2O2O25O2O2O2O2O2r6