
    ih                        U d Z ddlmZmZmZmZmZmZmZ ddl	m
Z
 ddlmZ ddlmZ ddlmZ ddlmZ ddlmZmZ dd	lmZmZ dd
lmZ ddlmZmZ ddlmZ ddl m!Z! ddl"m#Z#m$Z$m%Z% ddl&m'Z' ddl(m)Z)m*Z*m+Z+ ddl,m-Z-m.Z. ddl/m0Z0m1Z1 de2dee   fdZ3i e)jh                  e%e)jj                  e$e)jl                  e#e)jn                  ee)jp                  e.e)jr                  ee)jt                  e-e)jv                  ee)jx                  ee)jz                  ee)j|                  e1e)j~                  e0e)j                  ee)j                  ee)j                  ee)j                  ee)j                  ee)j                  e!e)j                  e'e)j                  eiZHee)eee*   ee   ee+   f   f   eId<   ddde)dee
   dedeee+f   fdZJddddee)   dee
   deeK   dedeeee+f      f
d ZLy)!z Loading datasets and evaluators.    )AnyDictListOptionalSequenceTypeUnion)BaseLanguageModel)Chain)TrajectoryEvalChain)PairwiseStringEvalChain)LabeledPairwiseStringEvalChain)CriteriaEvalChainLabeledCriteriaEvalChain)EmbeddingDistanceEvalChain"PairwiseEmbeddingDistanceEvalChain)ExactMatchStringEvaluator)JsonEqualityEvaluatorJsonValidityEvaluator)JsonEditDistanceEvaluator)JsonSchemaEvaluator)ContextQAEvalChainCotQAEvalChainQAEvalChain)RegexMatchStringEvaluator)EvaluatorTypeLLMEvalChainStringEvaluator)LabeledScoreStringEvalChainScoreStringEvalChain)PairwiseStringDistanceEvalChainStringDistanceEvalChainurireturnc                     	 ddl m}  |d|        }|d   D cg c]  }| c}S # t        $ r t        d      w xY wc c}w )a  Load a dataset from the `LangChainDatasets on HuggingFace <https://huggingface.co/LangChainDatasets>`_.

    Args:
        uri: The uri of the dataset to load.

    Returns:
        A list of dictionaries, each representing a row in the dataset.

    **Prerequisites**

    .. code-block:: shell

        pip install datasets

    Examples
    --------
    .. code-block:: python

        from langchain.evaluation import load_dataset
        ds = load_dataset("llm-math")
    r   )load_datasetzXload_dataset requires the `datasets` package. Please install with `pip install datasets`zLangChainDatasets/train)datasetsr&   ImportError)r#   r&   datasetds       Z/var/www/html/dev/engine/venv/lib/python3.12/site-packages/langchain/evaluation/loading.pyr&   r&   '   s[    ,
) /u56Gw'(!A((  
:
 	

 )s   & 	>;_EVALUATOR_MAPN)llm	evaluatorr.   kwargsc          	         | t         vr,t        d|  dt        t         j                                      t         |    }t	        |t
              r+	 	 ddlm} |xs  |ddd      } |j                  dd|i|S  |di |S # t        $ r# 	 ddl	m} n# t        $ r t        d      w xY wY Vw xY w# t        $ r}t        d	| d
      |d}~ww xY w)a<  Load the requested evaluation chain specified by a string.

    Parameters
    ----------
    evaluator : EvaluatorType
        The type of evaluator to load.
    llm : BaseLanguageModel, optional
        The language model to use for evaluation, by default None
    **kwargs : Any
        Additional keyword arguments to pass to the evaluator.

    Returns
    -------
    Chain
        The loaded evaluation chain.

    Examples
    --------
    >>> from langchain.evaluation import load_evaluator, EvaluatorType
    >>> evaluator = load_evaluator(EvaluatorType.QA)
    zUnknown evaluator type: z
Valid types are: r   )
ChatOpenAIzCould not import langchain_openai or fallback onto langchain_community. Please install langchain_openai or specify a language model explicitly. It's recommended to install langchain_openai AND specify a language model explicitly.zgpt-4*   )modelseedtemperaturezEvaluation with the z requires a language model to function. Failed to create the default 'gpt-4' model. Please manually provide an evaluation LLM or check your openai credentials.Nr.    )r-   
ValueErrorlistkeys
issubclassr   langchain_openair2   r)   &langchain_community.chat_models.openai	Exceptionfrom_llm)r/   r.   r0   evaluator_clsr2   es         r,   load_evaluatorrB   c   s   6 &&yk!$~':':'<"=!>@
 	
 #9-M-.	7  BAC &}%%8#888&v&&7   # %? "  	&}o 65 5 	sN   B B0 	B-BB-B''B-*B0 ,B--B0 0	C9C		C)r.   config
evaluatorsrC   c          	          g }| D ]9  }|r|j                  |i       ni }|j                  t        |fd|ii ||       ; |S )ae  Load evaluators specified by a list of evaluator types.

    Parameters
    ----------
    evaluators : Sequence[EvaluatorType]
        The list of evaluator types to load.
    llm : BaseLanguageModel, optional
        The language model to use for evaluation, if none is provided, a default
        ChatOpenAI gpt-4 model will be used.
    config : dict, optional
        A dictionary mapping evaluator types to additional keyword arguments,
        by default None
    **kwargs : Any
        Additional keyword arguments to pass to all evaluators.

    Returns
    -------
    List[Chain]
        The loaded evaluators.

    Examples
    --------
    >>> from langchain.evaluation import load_evaluators, EvaluatorType
    >>> evaluators = [EvaluatorType.QA, EvaluatorType.CRITERIA]
    >>> loaded_evaluators = load_evaluators(evaluators, criteria="helpfulness")
    r.   )getappendrB   )rD   r.   rC   r0   loadedr/   _kwargss          r,   load_evaluatorsrJ      s\    B F S	/5&**Y+2nYQCQ;Pf;P;PQRS M    )M__doc__typingr   r   r   r   r   r   r	   langchain_core.language_modelsr
   langchain.chains.baser   1langchain.evaluation.agents.trajectory_eval_chainr   langchain.evaluation.comparisonr   *langchain.evaluation.comparison.eval_chainr   (langchain.evaluation.criteria.eval_chainr   r   ,langchain.evaluation.embedding_distance.baser   r   %langchain.evaluation.exact_match.baser   !langchain.evaluation.parsing.baser   r   *langchain.evaluation.parsing.json_distancer   (langchain.evaluation.parsing.json_schemar   langchain.evaluation.qar   r   r   %langchain.evaluation.regex_match.baser   langchain.evaluation.schemar   r   r   'langchain.evaluation.scoring.eval_chainr   r    )langchain.evaluation.string_distance.baser!   r"   strr&   QACOT_QA
CONTEXT_QAPAIRWISE_STRINGSCORE_STRINGLABELED_PAIRWISE_STRINGLABELED_SCORE_STRINGAGENT_TRAJECTORYCRITERIALABELED_CRITERIASTRING_DISTANCEPAIRWISE_STRING_DISTANCEEMBEDDING_DISTANCEPAIRWISE_EMBEDDING_DISTANCEJSON_VALIDITYJSON_EQUALITYJSON_EDIT_DISTANCEJSON_SCHEMA_VALIDATIONREGEX_MATCHEXACT_MATCHr-   __annotations__rB   dictrJ   r7   rK   r,   <module>ru      s   & C C C < ' Q C U L Q H S S K T T)c )d4j )Hk. 0 !!#:	
  4 ))+I &&(C ""$7 - ""$< !!#: **,K $$&@ --/Q !6  !6!" $$&?#$ ((*=88) 5l+T%[$:OOPP : (,@'@' 
#	$@' 	@'
 5/!"@'L (,!	%'% 
#	$% TN	%
 % 
%&
'(%rK   