o {q i@sdZddlmZddlZddlZddlZddlZddlZddlZddl m Z ddl m Z m Z mZddlmZddlmZmZmZmZmZddlZddlmZdd lmZmZmZdd lmZm Z m!Z!m"Z"m#Z#m$Z$dd l%m&Z&dd l'm(Z(dd l)m*Z*ddl+m,Z,ddl-m.Z.ddl/m0Z0ddl1m2Z2ddl3m4Z4m5Z5m6Z6ddl7m8Z8ddl9m:Z:ddl;mZ>m?Z?m@Z@ddlAmBZBmCZCddlDmEZEddlFmGZGddlHmIZIddlJmKZKddlLmMZMddlNmOZOddlPmQZQeReSZTGdd d e>ZUGd!d"d"e>ZVGd#d$d$e,eeefZWGd%d&d&e,eeXeefZYGd'd(d(eUZZGd)d*d*eVZ[ed+eEd,d-Gd.d/d/eUZ\ed+eEd,d-Gd0d1d1eUZ]Gd2d3d3e:Z^eXeeeefZ_eeZe[fZ`Gd4d5d5eMZadS)6zEChain that takes in an input and produces an action and action input.) annotationsN)abstractmethod) AsyncIteratorIteratorSequence)Path)AnyCallableOptionalUnioncast) deprecated) AgentAction AgentFinish AgentStep)AsyncCallbackManagerForChainRunAsyncCallbackManagerForToolRunBaseCallbackManagerCallbackManagerForChainRunCallbackManagerForToolRun Callbacks)OutputParserException)BaseLanguageModel) BaseMessage)BaseOutputParser)BasePromptTemplate)FewShotPromptTemplate)PromptTemplate)RunnableRunnableConfig ensure_config) AddableDict)BaseTool)get_color_mapping) BaseModel ConfigDictmodel_validator)Selfoverride)AGENT_DEPRECATION_WARNING)AgentExecutorIterator) AgentType) InvalidTool)Chain)LLMChain)asyncio_timeoutcseZdZdZed0ddZd1ddZe d2d3ddZe d2d3ddZ eed0ddZ d4ddZ e d2d5d"d#Z ed6d$d%Zd7fd'd( Zd8d,d-Zd9d.d/ZZS):BaseSingleActionAgentzBase Single Action Agent class.return list[str]cCdgSReturn values of the agent.outputselfr7r7]/home/app/PaddleOCR-VL/.venv_paddleocr/lib/python3.10/site-packages/langchain/agents/agent.py return_values=z#BaseSingleActionAgent.return_valuesOptional[list[str]]cCsdSNr7r8r7r7r:get_allowed_toolsBsz'BaseSingleActionAgent.get_allowed_toolsNintermediate_stepslist[tuple[AgentAction, str]] callbacksrkwargsrUnion[AgentAction, AgentFinish]cKdS)0Given input, decided what to do. Args: intermediate_steps: Steps the LLM has taken to date, along with observations. callbacks: Callbacks to run. **kwargs: User inputs. Returns: Action specifying what tool to use. Nr7r9r@rBrCr7r7r:planEzBaseSingleActionAgent.plancdS)6Async given input, decided what to do. Args: intermediate_steps: Steps the LLM has taken to date, along with observations. callbacks: Callbacks to run. **kwargs: User inputs. Returns: Action specifying what tool to use. Nr7rGr7r7r:aplanXzBaseSingleActionAgent.aplancCrE7Return the input keys. :meta private: Nr7r8r7r7r: input_keyskrIz BaseSingleActionAgent.input_keysearly_stopping_methodstrrcK*|dkr tddidSd|d}t|)Return response when agent has been stopped due to max iterations. Args: early_stopping_method: Method to use for early stopping. intermediate_steps: Steps the LLM has taken to date, along with observations. **kwargs: User inputs. Returns: AgentFinish: Agent finish object. Raises: ValueError: If `early_stopping_method` is not supported. forcer63Agent stopped due to iteration limit or time limit.'Got unsupported early_stopping_method ``r ValueErrorr9rQr@rCmsgr7r7r:return_stopped_responsess z-BaseSingleActionAgent.return_stopped_responsellmrtoolsSequence[BaseTool]callback_managerOptional[BaseCallbackManager]cKt)a.Construct an agent from an LLM and tools. Args: llm: Language model to use. tools: Tools to use. callback_manager: Callback manager to use. kwargs: Additional arguments. Returns: BaseSingleActionAgent: Agent object. NotImplementedError)clsr_r`rbrCr7r7r:from_llm_and_toolssz(BaseSingleActionAgent.from_llm_and_toolscCrdz#Return Identifier of an agent type.rer8r7r7r: _agent_typez!BaseSingleActionAgent._agent_type builtins.dictc s\t}z|j}Wn tyd}Ynwt|tr$t|j|d<|S|dur,||d<|S)z{Return dictionary representation of agent. Returns: Dict: Dictionary representation of agent. N_type)super model_dumprjrf isinstancer+rRvalue)r9rC_dictrm __class__r7r:dicts    zBaseSingleActionAgent.dict file_pathUnion[Path, str]NonecCst|tr t|n|}|j}|jddd|}d|vr'd|d}t||jdkrL|d}t j ||dd Wd d S1sEwYd S|j d rr|d}t j ||d d Wd d S1skwYd S|d}t |)zSave the agent. Args: file_path: Path to file to save the agent to. Example: .. code-block:: python # If working with agent executor agent.agent.save(file_path="path/agent.yaml") Tparentsexist_okrmAgent z does not support saving.jsonwindentNz.yamlz.ymlFZdefault_flow_style must be json or yaml)rprRrparentmkdirrurfsuffixopenjsondumpendswithyamlr[)r9rv save_pathdirectory_path agent_dictr]fr7r7r:saves"    "  " zBaseSingleActionAgent.savecCiS#Return logging kwargs for tool run.r7r8r7r7r:tool_run_logging_kwargssz-BaseSingleActionAgent.tool_run_logging_kwargsr1r2r1r=r>r@rArBrrCrr1rDrQrRr@rArCrr1r) r_rr`rarbrcrCrr1r0r1rRrCrr1rlrvrwr1rxr1rl)__name__ __module__ __qualname____doc__propertyr;r?rrHrLrPr^ classmethodrhrjrurr __classcell__r7r7rsr:r0:s.     "r0cseZdZdZed(ddZd)ddZe d*d+ddZe d*d+ddZ eed(ddZ d,ddZ ed-ddZ d.fdd Z d/d$d%Zd0d&d'ZZS)1BaseMultiActionAgentzBase Multi Action Agent class.r1r2cCr3r4r7r8r7r7r:r;r<z"BaseMultiActionAgent.return_valuesr=cCrE)z]Get allowed tools. Returns: Optional[List[str]]: Allowed tools. Nr7r8r7r7r:r?sz&BaseMultiActionAgent.get_allowed_toolsNr@rArBrrCr%Union[list[AgentAction], AgentFinish]cKrE)a5Given input, decided what to do. Args: intermediate_steps: Steps the LLM has taken to date, along with the observations. callbacks: Callbacks to run. **kwargs: User inputs. Returns: Actions specifying what tool to use. Nr7rGr7r7r:rHrIzBaseMultiActionAgent.plancrJ)a;Async given input, decided what to do. Args: intermediate_steps: Steps the LLM has taken to date, along with the observations. callbacks: Callbacks to run. **kwargs: User inputs. Returns: Actions specifying what tool to use. Nr7rGr7r7r:rLrMzBaseMultiActionAgent.aplancCrErNr7r8r7r7r:rPrIzBaseMultiActionAgent.input_keysrQrRrcKrS)rTrUr6z$Agent stopped due to max iterations.rWrXrYrZr\r7r7r:r^ s z,BaseMultiActionAgent.return_stopped_responsecCrdrirer8r7r7r:rj:rkz BaseMultiActionAgent._agent_typerlc sHt}ttt|j|d<Wd|S1swY|S)*Return dictionary representation of agent.rmN)rnro contextlibsuppressrfrRrjr9rCrrrsr7r:ru?s   zBaseMultiActionAgent.dictrvrwrxcCst|tr t|n|}|}d|vrd|d}t||j}|jddd|jdkrL|d}t j ||dd Wd d S1sEwYd S|j d rr|d}t j ||d d Wd d S1skwYd S|d}t |)aSave the agent. Args: file_path: Path to file to save the agent to. Raises: NotImplementedError: If agent does not support saving. ValueError: If file_path is not json or yaml. Example: .. code-block:: python # If working with agent executor agent.agent.save(file_path="path/agent.yaml") rmr|z does not support saving.Tryr}r~rrNrFrr)rprRrrurfrrrrrrrrr[)r9rvrrr]rrr7r7r:rFs"   "  " zBaseMultiActionAgent.savecCrrr7r8r7r7r:rlrkz,BaseMultiActionAgent.tool_run_logging_kwargsrrr>r@rArBrrCrr1rrrrrr)rrrrrr;r?rrHrLrPr^rjrurrrr7r7rsr:rs(     &rc@eZdZdZed ddZdS) AgentOutputParserz=Base class for parsing agent output into agent action/finish.textrRr1rDcCrE)z$Parse text into agent action/finish.Nr7r9rr7r7r:parseurIzAgentOutputParser.parseN)rrRr1rDrrrrrrr7r7r7r:rrsrc@r) MultiActionAgentOutputParserzBase class for parsing agent output into agent actions/finish. This is used for agents that can return multiple actions. rrRr1rcCrE)zParse text into agent actions/finish. Args: text: Text to parse. Returns: Union[List[AgentAction], AgentFinish]: List of agent actions or agent finish. Nr7rr7r7r:rrIz"MultiActionAgentOutputParser.parseN)rrRr1rrr7r7r7r:rzsrc@eZdZUdZded< gZded<gZded<dZded < edd Z e dd d Z e dddZ ddddZ ddddZdS) RunnableAgentAgent powered by Runnables.z/Runnable[dict, Union[AgentAction, AgentFinish]]runnabler2input_keys_argreturn_keys_argTboolstream_runnableZarbitrary_types_allowedr1cC|jSr5rr8r7r7r:r;r<zRunnableAgent.return_valuescCr)zReturn the input keys.rr8r7r7r:rPr<zRunnableAgent.input_keysNr@rArBrrCrrDcKfi|d|i}d}|jr'|jj|d|idD] }|dur |}q||7}q|S|jj|d|id}|SaPBased on past history and current inputs, decide what to do. Args: intermediate_steps: Steps the LLM has taken to date, along with the observations. callbacks: Callbacks to run. **kwargs: User inputs. Returns: Action specifying what tool to use. r@NrBconfigrrstreamZinvoker9r@rBrCinputs final_outputchunkr7r7r:rHs zRunnableAgent.plancxi|d|i}d}|jr-|jj|d|id2z3dHW}|dur%|}q||7}q6|S|jj|d|idIdH}|SaRAsync based on past history and current inputs, decide what to do. Args: intermediate_steps: Steps the LLM has taken to date, along with observations. callbacks: Callbacks to run. **kwargs: User inputs. Returns: Action specifying what tool to use. r@NrBrrrastreamZainvokerr7r7r:rLs$   zRunnableAgent.aplanrr>rrrrr__annotations__rrrr%Z model_configrr;rPrHrLr7r7r7r:rs&       'rc@r)RunnableMultiActionAgentrz5Runnable[dict, Union[list[AgentAction], AgentFinish]]rr2rrTrrrr1cCrrrr8r7r7r:r;r<z&RunnableMultiActionAgent.return_valuescCr)QReturn the input keys. Returns: List of input keys. rr8r7r7r:rPsz#RunnableMultiActionAgent.input_keysNr@rArBrrCrrcKrrrrr7r7r:rH s zRunnableMultiActionAgent.plancrrrrr7r7r:rLGs$  zRunnableMultiActionAgent.aplanrr>rrr7r7r7r:rs&       *rz0.1.0z1.0)messageZremovalcsveZdZUdZded< ded< ded< edd d Zdfdd Z ddddZ ddddZ d ddZ Z S)!LLMSingleActionAgentz$Base class for single action agents.r. llm_chainr output_parserr2stopr1cCtt|jjdhS)rr@listsetrrPr8r7r7r:rPszLLMSingleActionAgent.input_keysrCrrlc t}|d=|Srrrnrurrsr7r:ru zLLMSingleActionAgent.dictNr@rArBrrDcKs(|jjd||j|d|}|j|S)a4Given input, decided what to do. Args: intermediate_steps: Steps the LLM has taken to date, along with the observations. callbacks: Callbacks to run. **kwargs: User inputs. Returns: Action specifying what tool to use. r@rrBNr7)rrunrrrr9r@rBrCr6r7r7r:rHs zLLMSingleActionAgent.plancs0|jjd||j|d|IdH}|j|S)rKrNr7)rarunrrrrr7r7r:rLs zLLMSingleActionAgent.aplancCs&dt|jdkr ddS|jddS)rrWr llm_prefixobservation_prefix)lenrr8r7r7r:rs z,LLMSingleActionAgent.tool_run_logging_kwargsrrr>rr) rrrrrrrPrurHrLrrr7r7rsr:rus    rcsFeZdZUdZded< ded< dZded< dKfd d ZdLddZedMddZ dNddZ edMddZ dOddZ dPdQd"d#Z dPdQd$d%ZdRd'd(ZedMd)d*Zed+d,dSd.d/ZeedTd0d1ZeedTd2d3ZeedUd7d8ZedVd:d;ZeedWdz,Agent.from_llm_and_tools..)rrrNr7)r r.r r ) rgr_r`rbrrCrZ tool_namesZ_output_parserr7r7r:rhs  zAgent.from_llm_and_toolsrQrc Ks|dkr tddidS|dkrXd}|D]\}}||j7}|d|j|d|j7}q|d7}||jd}i||}|jjd i|} |j| } t | trQ| Std| i| Sd |} t | ) aReturn response when agent has been stopped due to max iterations. Args: early_stopping_method: Method to use for early stopping. intermediate_steps: Steps the LLM has taken to date, along with observations. **kwargs: User inputs. Returns: AgentFinish: Agent finish object. Raises: ValueError: If `early_stopping_method` is not in ['force', 'generate']. rUr6rVrWgeneraterzB I now need to return a final answer based on the previous steps:rzBearly_stopping_method should be one of `force` or `generate`, got Nr7) rrrrrrrrrrpr[) r9rQr@rCrrrrrrZ parsed_outputr]r7r7r:r^s6      zAgent.return_stopped_responsecCs|j|jdS)rrrr8r7r7r:rszAgent.tool_run_logging_kwargsrrr)rrRr1rR)r@rAr1rr>r)r@rArCrr1rr1r'r)r`rar1r)r`rar1rx)rCrr1r)NN) r_rr`rarbrcrr rCrr1rrr)rrrrrrrur?rr;rrrrHrLrrPr&rrrrrr r r rhr^rrr7r7rsr:rsZ             #7rc@sJeZdZUdZdZded< dZded< ddd d Z ddddZdS) ExceptionToolz!Tool that just returns the query. _ExceptionrRrzException tool descriptionNquery run_manager#Optional[CallbackManagerForToolRun]r1cCs|Sr>r7r9rrr7r7r:_runszExceptionTool._run(Optional[AsyncCallbackManagerForToolRun]cs|Sr>r7rr7r7r:_arunszExceptionTool._arunr>)rrRrrr1rR)rrRrrr1rR) rrrrrrrrr r7r7r7r:rs     rc@seZdZUdZded< ded< dZded< d Zd ed < d Zd ed< dZded< dZ ded< dZ ded< e ddddZ e dddd!d"Ze d#de dd&d'Zedd)d*Zdd.d/Zdd0d1Z dddd2dd7d8Zedd:d;Zeddmsz/AgentExecutor.validate_tools..zAllowed tools (z!) different than provided tools (cSr r7rrr7r7r:rrrz0AgentExecutor.validate_tools..))r#r`r?rr[)r9r#r`rr]r7r7r:validate_tools]s  zAgentExecutor.validate_toolsbeforevaluesruc Cs|d}|rJt|trJz|j}Wnty%}zd}WYd}~nd}~ww|ttttfk}| dd}|rBt ||d|d<|St ||d|d<|S)zConvert runnable to agent if passed in. Args: values: Values to validate. Returns: Dict: Validated values. r#FNrT)rr) getrprZ OutputType Exceptionr rrrpoprr)rgr0r# output_type_Z multi_actionrr7r7r:validate_runnable_agentws*      z%AgentExecutor.validate_runnable_agent2Union[BaseSingleActionAgent, BaseMultiActionAgent]cCst|jtr tt|jS|jS)aCType cast self.agent. If the `agent` attribute is a Runnable, it will be converted one of RunnableAgentType in the validate_runnable_agent root_validator. To support instantiating with a Runnable, here we explicitly cast the type to reflect the changes made in the root_validator. )rpr#rr RunnableAgentTyper8r7r7r: _action_agents zAgentExecutor._action_agentrvrwrxcCr)zRaise error - saving not supported for Agent Executors. Args: file_path: Path to save to. Raises: ValueError: Saving not supported for agent executors. zpSaving not supported for agent executors. If you are trying to save the agent, please use the `.save_agent(...)`r)r9rvr]r7r7r:rs zAgentExecutor.savecCs |j|S)zZSave the underlying agent. Args: file_path: Path to save to. )r9r)r9rvr7r7r: save_agents zAgentExecutor.save_agent)include_run_infoasync_rr;r<r*cCst||||j|dS)agEnables iteration over steps taken to reach final output. Args: inputs: Inputs to the agent. callbacks: Callbacks to run. include_run_info: Whether to include run info. async_: Whether to run async. (Ignored) Returns: AgentExecutorIterator: Agent executor iterator object. )tagsr;)r*r=)r9rrBr;r<r7r7r:iterszAgentExecutor.iterr2cCs|jjS)rO)r9rPr8r7r7r:rPszAgentExecutor.input_keyscCs|jr g|jjdS|jjS)z@Return the singular output key. :meta private: r@)r$r9r;r8r7r7r: output_keysszAgentExecutor.output_keysrr"cCsdd|jD|S)zLookup tool by name. Args: name: Name of tool. Returns: BaseTool: Tool object. cSi|]}|j|qSr7rrr7r7r: z-AgentExecutor.lookup_tool..)r`)r9rr7r7r: lookup_tools zAgentExecutor.lookup_tool iterationsint time_elapsedfloatcCs,|jdur ||jkr dS|jdup||jkS)NF)r&r')r9rDrFr7r7r:_should_continueszAgentExecutor._should_continuer6rr@rr$Optional[CallbackManagerForChainRun]dict[str, Any]cCs.|r |j|d|jd|j}|jr||d<|SNgreen)colorverboser@Zon_agent_finishrNr;r$r9r6r@rrr7r7r:_returns zAgentExecutor._return)Optional[AsyncCallbackManagerForChainRun]cs6|r|j|d|jdIdH|j}|jr||d<|SrKrOrPr7r7r:_areturns zAgentExecutor._areturnNextStepOutput1Union[AgentFinish, list[tuple[AgentAction, str]]]cCs<t|dtrt|dkrd}t||dSdd|DS)Nr)z>Expected a single AgentFinish output, but got multiple values.cSs"g|] }t|tr|j|jfqSr7)rprrrrar7r7r:r"s"z4AgentExecutor._consume_next_step..)rprrr[)r9r0r]r7r7r:_consume_next_steps  z AgentExecutor._consume_next_stepname_to_tool_mapdict[str, BaseTool] color_mappingdict[str, str]rAc Cs|t||||||Sr>)rYr_iter_next_stepr9rZr\rr@rr7r7r:_take_next_step$szAgentExecutor._take_next_step4Iterator[Union[AgentFinish, AgentAction, AgentStep]]c csz||}|jj|fd|r|ndi|}Wnty}zt|jtr-|j }nd}|r;d|} t| |t |} t|jtrV|j rSt |j } t |j } nd} nt|jt r`|j} nt |jrk||} nd} t| |td| | }|r|j|dd |j} tj|jf|jd|r|ndd | } t|| d VWYd}~dSd}~wwt|tr|VdSt|tr|gn|} | D]}|Vq| D] }|||||VqdS) Take a single step in the thought-action-observation loop. Override this to take control of how the agent makes and acts on choices. rBNFAn output parsing error occurred. In order to pass this error back to the agent and have it try again, pass `handle_parsing_errors=True` to the AgentExecutor. This is the error: Invalid or incomplete response.Got unexpected type of `handle_parsing_errors`rrLrMrNrMrBrr)_prepare_intermediate_stepsr9rH get_childrrpr(rr[rR send_to_llmr llm_outputcallableron_agent_actionrrr tool_inputrNrr_perform_agent_action)r9rZr\rr@rr6e raise_errorr]rrtool_run_kwargsactions agent_actionr7r7r:r^8s~               *zAgentExecutor._iter_next_steprurrc Cs|r |j|dd|j|vr<||j}|j}||j}|j}|r&d|d<|j|jf|j||r4|ndd|} n"|j}t j|jt | df|jd|rW|ndd|} t || dS)NrLrfrWrrgZrequested_tool_nameZavailable_tool_namesrh) rnr return_directr9rrrorNrjr,rkeysr r9rZr\rurrrwrMrsrr7r7r:rps>       z#AgentExecutor._perform_agent_actionc s*|dd||||||2IdHS)Ncsg|z3dHW}|q6Sr>r7rWr7r7r:rs z2AgentExecutor._atake_next_step..)rY_aiter_next_stepr_r7r7r:_atake_next_steps zAgentExecutor._atake_next_step9AsyncIterator[Union[AgentFinish, AgentAction, AgentStep]]c sz|}jj|fdrndi|IdH}Wnty}ztjtr0j }nd}|r>d|} t| |t |} tjtrY|j rVt |j } t |j } nd} ntjt rcj} nt jrn|} nd} t| |td| | }j} tj|jfjdrndd| IdH} t|| d VWYd}~dSd}~wwt|tr|VdSt|tr|gn|} | D]}|Vqtjfd d | DIdH}|D]}|VqdS) rbrBNFrcrdrerrgrhcsg|] }|qSr7)_aperform_agent_action)rrur\rZrr9r7r:r sz2AgentExecutor._aiter_next_step..)rir9rLrjrrpr(rr[rRrkrrlrmrrrrrorNrrasynciogather)r9rZr\rr@rr6rqrrr]rrrsrtruresultrr7r~r:rzsz               (  zAgentExecutor._aiter_next_stepc s|r|j||jddIdH|j|vrE||j}|j}||j}|j}|r,d|d<|j|jf|j||r:|ndd|IdH} n%|j}t j|jt | df|jd|r`|ndd|IdH} t || dS)NrL)rNrMrWrrgrvrh) rnrNrrwr9rrrorjr,rrxrryr7r7r:r}sH       z$AgentExecutor._aperform_agent_actionc Csdd|jD}tdd|jDddgd}g}d}d }t}|||rm|j|||||d } t| tr=|j| ||d S|| t | d kr]| d} | | } | d ur]|j| ||d S|d 7}t|}|||s&|j j |j |fi|} |j| ||d S) z(Run text through and get agent response.cSr@r7rrr7r7r:rALrBz'AgentExecutor._call..cSr r7rrr7r7r:rOrz'AgentExecutor._call..rLredZexcluded_colorsrrrVN)r`r#timerHr`rprrQextendr_get_tool_returnr9r^rQ r9rrrZr\r@rDrF start_timenext_step_outputZnext_step_actionZ tool_returnr6r7r7r:_callEsV       zAgentExecutor._callc sdd|jD}tdd|jDdgd}g}d}d}t}zt|j4Id H|||r|j|||||d Id H} t| trY|j | ||d Id HWd Id HWS| | t | d kr| d} | | } | d ur|j | ||d Id HWd Id HWS|d 7}t|}|||s1|j j|j|fi|} |j | ||d Id HWd Id HWS1Id HswYWd Sttjfy|j j|j|fi|} |j | ||d Id HYSw) z.Async run text through and get agent response.cSr@r7rrr7r7r:rArBz(AgentExecutor._acall..cSr r7rrr7r7r:rrz(AgentExecutor._acall..rLrrrNrrV)r`r#rr/r'rHr{rprrSrrrr9r^rQ TimeoutErrorrrr7r7r:_acall{s          4(zAgentExecutor._acallrtuple[AgentAction, str]Optional[AgentFinish]cCs`|\}}dd|jD}d}t|jjdkr|jjd}|j|vr.||jjr.t||idSdS)z&Check if the tool is a returning tool.cSr@r7rrr7r7r:rArBz2AgentExecutor._get_tool_return..r6rrWN)r`rr9r;rrwr)r9rrurrZZreturn_value_keyr7r7r:rs   zAgentExecutor._get_tool_returncCs>t|jtr|jdkr||j dSt|jr||S|S)Nr)rpr*rErm)r9r@r7r7r:ris    z)AgentExecutor._prepare_intermediate_stepsinputUnion[dict[str, Any], Any]rOptional[RunnableConfig]Iterator[AddableDict]cksVt|}t|||df|d|d|d|ddd|}|EdHdS) aEnables streaming over steps taken to reach final output. Args: input: Input to the agent. config: Config to use. kwargs: Additional arguments. Yields: AddableDict: Addable dictionary. rBr=metadatarun_namerun_idTr=rrrZ yield_actionsNr r*r1)r9rrrCiteratorr7r7r:rs   zAgentExecutor.streamAsyncIterator[AddableDict]cKsft|}t|||df|d|d|d|ddd|}|2z 3dHW}|Vq&6dS) a Async enables streaming over steps taken to reach final output. Args: input: Input to the agent. config: Config to use. kwargs: Additional arguments. Yields: AddableDict: Addable dictionary. rBr=rrrTrNr)r9rrrCrstepr7r7r:rs$  zAgentExecutor.astreamr>) r#r"r`rarBrrCrr1r!r)r0rur1r)r1r7r) rrrBrr;rr<rr1r*r)rrRr1r")rDrErFrGr1r)r6rr@rrrIr1rJ)r6rr@rrrRr1rJ)r0rTr1rU) rZr[r\r]rr]r@rArrIr1rU) rZr[r\r]rr]r@rArrIr1ra) rZr[r\r]rurrrIr1r) rZr[r\r]rr]r@rArrRr1rU) rZr[r\r]rr]r@rArrRr1r|) rZr[r\r]rurrrRr1r)rr]rrIr1rJ)rr]rrRr1r])rrr1r)r@rAr1rA)rrrrrCrr1r)rrrrrCrr1r))rrrrrr$r&r'rQr(r*rr+r&r.r6rr9rr:r>rPr?rCrHrQrSrYr`r^rpr{rzr}rrrrir(rrr7r7r7r:r!s                  T -  \ . 9 I  r!)br __future__rrbuiltinsrrloggingrabcrcollections.abcrrrpathlibrtypingrr r r r rZlangchain_core._apir Zlangchain_core.agentsrrrZlangchain_core.callbacksrrrrrrZlangchain_core.exceptionsrZlangchain_core.language_modelsrZlangchain_core.messagesrZlangchain_core.output_parsersrZlangchain_core.promptsrZlangchain_core.prompts.few_shotrZlangchain_core.prompts.promptrZlangchain_core.runnablesrrr Zlangchain_core.runnables.utilsr!Zlangchain_core.toolsr"Zlangchain_core.utils.inputr#Zpydanticr$r%r&Ztyping_extensionsr'r(Zlangchain._api.deprecationr)Zlangchain.agents.agent_iteratorr*Zlangchain.agents.agent_typesr+Zlangchain.agents.toolsr,Zlangchain.chains.baser-Zlangchain.chains.llmr.Zlangchain.utilities.asyncior/ getLoggerrrr0rrrrrrrrrrTr8r!r7r7r7r:s                       ) owS'