gh\UdZddlmZddlmZmZmZddlmZddl m Z ddl m Z ddl mZddlmZdd lmZmZdd lmZmZdd lmZdd lmZmZdd lmZddlmZddl m!Z!m"Z"m#Z#ddl$m%Z%ddl&m'Z'm(Z(m)Z)ddl*m+Z+m,Z,ddl-m.Z.m/Z/de0de1e2fdZ3ie'j4e#e'j5e"e'j6e!e'j7ee'j8e,e'j9ee'j:e+e'j;e e'j<ee'j=ee'j>e/e'j?e.e'j@ee'jAee'jBee'jCee'jDee'jEee'jFe%e'jGeiZHe2e'eeIe(eIe eIe)ffeJd<ddde'deededee e)ffdZKddddee'deed ee2dede1ee e)ff d!ZLdS)"z Loading datasets and evaluators.)Sequence)AnyOptionalUnion)BaseLanguageModel)Chain)TrajectoryEvalChain)PairwiseStringEvalChain)LabeledPairwiseStringEvalChain)CriteriaEvalChainLabeledCriteriaEvalChain)EmbeddingDistanceEvalChain"PairwiseEmbeddingDistanceEvalChain)ExactMatchStringEvaluator)JsonEqualityEvaluatorJsonValidityEvaluator)JsonEditDistanceEvaluator)JsonSchemaEvaluator)ContextQAEvalChainCotQAEvalChain QAEvalChain)RegexMatchStringEvaluator) EvaluatorType LLMEvalChainStringEvaluator)LabeledScoreStringEvalChainScoreStringEvalChain)PairwiseStringDistanceEvalChainStringDistanceEvalChainurireturnc ddlm}n#t$rtdwxYw|d|}d|dDS)aLoad a dataset from the `LangChainDatasets on HuggingFace `_. 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`zLangChainDatasets/cg|]}|Sr%).0ds Y/var/www/FlaskApp/flask-venv/lib/python3.11/site-packages/langchain/evaluation/loading.py z load_dataset..Gs ( ( (!A ( ( (train)datasetsr# ImportError)r r#datasets r(r#r#(s, )))))))     :    l55566G ( (ww' ( ( ((s #_EVALUATOR_MAPN)llm evaluatorr0kwargsc |tvr9td|dttt|}t |t r ddlm}n5#t$r( ddl m}n#t$rtdwxYwYnwxYw|p |ddd}n&#t$r}td |d |d }~wwxYw|j d d |i|S|d i|S)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) zUnknown 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.zgpt-4*)modelseed temperaturezEvaluation 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.Nr0r%) r/ ValueErrorlistkeys issubclassrlangchain_openair4r-&langchain_community.chat_models.openai Exceptionfrom_llm)r1r0r2 evaluator_clsr4es r(load_evaluatorrCds6&& @y @ @"&~':':'<'<"="= @ @   #9-M-..'  7777777    #%? J'JJJCC   5}555    &}%88#8888}&&v&&&sN'A.-B4. B 9B?B BB B4B  B44 C>CC)r0config evaluatorsrDc g}|D]B}|r||ini}|t|fd|ii||C|S)aeLoad 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") r0)getappendrC)rEr0rDr2loadedr1_kwargss r(load_evaluatorsrKsrBFSS /5=&**Y+++2 nYQQCQ;Pf;P;PQQRRRR Mr*)M__doc__collections.abcrtypingrrrlangchain_core.language_modelsrlangchain.chains.baser1langchain.evaluation.agents.trajectory_eval_chainr langchain.evaluation.comparisonr *langchain.evaluation.comparison.eval_chainr (langchain.evaluation.criteria.eval_chainr r ,langchain.evaluation.embedding_distance.baserr%langchain.evaluation.exact_match.baser!langchain.evaluation.parsing.baserr*langchain.evaluation.parsing.json_distancer(langchain.evaluation.parsing.json_schemarlangchain.evaluation.qarrr%langchain.evaluation.regex_match.baserlangchain.evaluation.schemarrr'langchain.evaluation.scoring.eval_chainrr)langchain.evaluation.string_distance.baserrstrr:dictr#QACOT_QA CONTEXT_QAPAIRWISE_STRING SCORE_STRINGLABELED_PAIRWISE_STRINGLABELED_SCORE_STRINGAGENT_TRAJECTORYCRITERIALABELED_CRITERIASTRING_DISTANCEPAIRWISE_STRING_DISTANCEEMBEDDING_DISTANCEPAIRWISE_EMBEDDING_DISTANCE JSON_VALIDITY JSON_EQUALITYJSON_EDIT_DISTANCEJSON_SCHEMA_VALIDATION REGEX_MATCH EXACT_MATCHr/type__annotations__rCrKr%r*r(rws\&&&$$$$$$''''''''''<<<<<<''''''QQQQQQCCCCCCUUUUUULKKKKKQPPPPPHHHHHHSSSSSSSSSSKKKKKKTTTTTTTTTT )c)d4j))))Hk.0!#:   4  )+I &(C"$7-"$<!#:*,K$&@-/Q!6 !6!"$&?#$(*=88)5l+T%[$:OOPP:(,>'>'>'>' # $>' >'  5/ !" >'>'>'>'H(,! %%%'% # $% TN %  %  %& '( %%%%%%r*