g3fidZddlmZmZmZmZmZddlmZddl m Z m Z ddl m Z ddlmZddlmZddlmZmZdd lmZdd lmZmZmZmZdd lmZeGd d eZy)0Structured prompt template for a language model.) AsyncIteratorCallableIteratorMappingSequence)Any) BaseModelField)override)beta)BaseLanguageModel)ChatPromptTemplateMessageLikeRepresentation)PromptTemplateFormat)OtherRunnableRunnableSequenceRunnableSerializable)get_pydantic_field_namescVeZdZUdZeezed< eeZee e fed< ddddde e deee zdzdee e fdzd ed e d df fd Zed ee fd Zede e deezd e d efdZedee efeee geefzeee geefzee gefzee ee efee gefze zfzd eeeffdZdddee efeee geefzeee geefzee gefzee ee efee gefze zfzde dzd eeeffdZxZS)StructuredPromptrschema_)default_factorystructured_output_kwargsNzf-string)rtemplate_formatmessagesrkwargsreturnc |xs|jdd}|sd|}t||xsi}t|jt |j D]}|j|||<t |d||||d|y)aoCreate a structured prompt template. Args: messages: sequence of messages. schema_: schema for the structured prompt. structured_output_kwargs: additional kwargs for structured output. template_format: template format for the prompt. Raises: ValueError: if schema is not provided. schemaNz=Must pass in a non-empty structured output schema. Received: )rrrr)pop ValueErrorset differencer __class__super__init__) selfrrrrrerr_msgkr's _/var/www/auto_recruiter/arenv/lib/python3.12/site-packages/langchain_core/prompts/structured.pyr)zStructuredPrompt.__init__#s(7VZZ$7O) W% %#;#Ar V''(@(PQ 8A*0**Q- $Q ' 8  %=+    c8|jjdS)zGet the namespace of the LangChain object. For example, if the class is `langchain.llms.openai.OpenAI`, then the namespace is `["langchain", "llms", "openai"]` Returns: The namespace of the LangChain object. .) __module__split)clss r-get_lc_namespacez!StructuredPrompt.get_lc_namespaceIs~~##C((r.r!c |||fi|S)aCreate a chat prompt template from a variety of message formats. Examples: Instantiation from a list of message templates: ```python from langchain_core.prompts import StructuredPrompt class OutputSchema(BaseModel): name: str value: int template = StructuredPrompt( [ ("human", "Hello, how are you?"), ("ai", "I'm doing well, thanks!"), ("human", "That's good to hear."), ], OutputSchema, ) ``` Args: messages: Sequence of message representations. A message can be represented using the following formats: 1. `BaseMessagePromptTemplate` 2. `BaseMessage` 3. 2-tuple of `(message type, template)`; e.g., `("human", "{user_input}")` 4. 2-tuple of `(message class, template)` 5. A string which is shorthand for `("human", template)`; e.g., `"{user_input}"` schema: A dictionary representation of function call, or a Pydantic model. **kwargs: Any additional kwargs to pass through to `ChatModel.with_structured_output(schema, **kwargs)`. Returns: A structured prompt template r")r3rr!rs r-from_messages_and_schemaz)StructuredPrompt.from_messages_and_schemaUsb8V.v..r.otherc$|j|SN)pipe)r*r7s r-__or__zStructuredPrompt.__or__syyr.)nameothersr<c|rt|dtst|ddr;t||dj|j fi|j g|ddd|iSd}t|)amPipe the structured prompt to a language model. Args: others: The language model to pipe the structured prompt to. name: The name of the pipeline. Returns: A RunnableSequence object. Raises: NotImplementedError: If the first element of `others` is not a language model. rwith_structured_outputNr<z8Structured prompts need to be piped to a language model.) isinstancerhasattrrr?rrNotImplementedError)r*r<r=msgs r-r:zStructuredPrompt.pipes, z&)->?G 1I/E $0q 00LL$($A$A     I!#&&r.r9) __name__r1 __qualname____doc__dicttype__annotations__r rstrr rrr rr) classmethodlistr4rr6r rrrrrrrr;r: __classcell__)r's@r-rrs|: D[+/4T/Jd38nJ 26$ ;?0: $ 45$ Y'$.$ #'sCx.4"7 $ . $ $  $ L )c ) )0/450/t 0/ 0/  0/0/d U # HSM?HUO3 45 M#&'u)== >? C5%< ! #xU +hue|.DDsJJ K L  dEk *  " "'#u*% HSM?HUO3 45 M#&'u)== >? C5%< ! #xU +hue|.DDsJJ K L"'Dj"' dEk *"'r.rN)rGcollections.abcrrrrrtypingr pydanticr r typing_extensionsr "langchain_core._api.beta_decoratorr #langchain_core.language_models.baserlangchain_core.prompts.chatrrlangchain_core.prompts.stringrlangchain_core.runnables.baserrrrlangchain_core.utilsrrr"r.r-rYs[6PP&&3A? :Y')Y'Y'r.