g3fi*dZddlmZddlmZddlmZmZddlm Z m Z ddl m Z ddl mZmZmZmZmZmZerddlmZGd d eZy ) zPrompt schema definition.) annotations)Path) TYPE_CHECKINGAny) BaseModelmodel_validator)override)DEFAULT_FORMATTER_MAPPINGPromptTemplateFormatStringPromptTemplatecheck_valid_templateget_template_variablesmustache_schema)RunnableConfigcdeZdZUdZeeddZeeddZde d< dZ de d< d Z d e d < e d eddZ eddfd ZddZeddZddZe d d!dZe d d"dZeddd d#dZxZS)$PromptTemplateaPrompt template for a language model. A prompt template consists of a string template. It accepts a set of parameters from the user that can be used to generate a prompt for a language model. The template can be formatted using either f-strings (default), jinja2, or mustache syntax. *Security warning*: Prefer using `template_format="f-string"` instead of `template_format="jinja2"`, or make sure to NEVER accept jinja2 templates from untrusted sources as they may lead to arbitrary Python code execution. As of LangChain 0.0.329, Jinja2 templates will be rendered using Jinja2's SandboxedEnvironment by default. This sand-boxing should be treated as a best-effort approach rather than a guarantee of security, as it is an opt-out rather than opt-in approach. Despite the sand-boxing, we recommend to never use jinja2 templates from untrusted sources. Example: ```python from langchain_core.prompts import PromptTemplate # Instantiation using from_template (recommended) prompt = PromptTemplate.from_template("Say {foo}") prompt.format(foo="bar") # Instantiation using initializer prompt = PromptTemplate(template="Say {foo}") ``` cd|jiS)Ntemplate_formatrselfs [/var/www/auto_recruiter/arenv/lib/python3.12/site-packages/langchain_core/prompts/prompt.py lc_attributeszPromptTemplate.lc_attributes;s t33  c gdS)zvGet the namespace of the LangChain object. Returns: `["langchain", "prompts", "prompt"]` ) langchainpromptsprompt)clss rget_lc_namespacezPromptTemplate.get_lc_namespaceBs 21rstrtemplatef-stringr rFboolvalidate_templatebefore)modec|jd|S|jdd|jdi|jdrM|ddk(r d}t|d|vr d }t||dt|dz}t |d|d||dr*t |d|dDcgc] }||dvr| c}|d<|Scc}w) z7Check that template and input variables are consistent.r#rr$partial_variablesr&mustachez'Mustache templates cannot be validated.input_variablesz:Input variables must be provided to validate the template.)get setdefault ValueErrorlistr r)r valuesmsg all_inputsvars rpre_init_validationz"PromptTemplate.pre_init_validationVs ::j ! )M +Z8-r2 ::) *'(J6? o% .R o% 12T&AT:U5VVJ z"F+<$=z  # $2:&/@(A)f%899 )F$ % )s/CNcj|jdk7rt| |St|jS)zGet the input schema for the prompt. Args: config: The runnable configuration. Returns: The input schema for the prompt. r+)rsuperget_input_schemarr#)rconfig __class__s rr8zPromptTemplate.get_input_schema|s2   : -7+F3 3t}}--rct|tr|j|jk7r d}t|t t |j t |j z}|j|jz}|jxr |j}t|jj}|jjD]\}}||vr d}t||||<t||||j|St|tr&tj||j} || zSdt|}t|)aOverride the + operator to allow for combining prompt templates. Raises: ValueError: If the template formats are not f-string or if there are conflicting partial variables. NotImplementedError: If the other object is not a `PromptTemplate` or str. Returns: A new `PromptTemplate` that is the combination of the two. z)Cannot add templates of different formatsz*Cannot have same variable partialed twice.)r#r,r*rr&rz Unsupported operand type for +: ) isinstancerrr/r0setr,r#r&dictr*itemsr" from_templatetypeNotImplementedError) rotherr2r,r#r&r*kvrs r__add__zPromptTemplate.__add__s[ e^ ,##u'<'<<A o%"D(()C0E0E,FFO}}u~~5H $ 6 6 R5;R;R  $T%;%;%A%A%C D //557 )1))FC$S/)'(!!$  ) "! /"3 $ 4 4"3   eS !#11 $ 4 42F&= 0e >!#&&rcy)zReturn the prompt type key.rrrs r _prompt_typezPromptTemplate._prompt_typesrc l|jdi|}t|j|jfi|S)zFormat the prompt with the inputs. Args: **kwargs: Any arguments to be passed to the prompt template. Returns: A formatted string. r)!_merge_partial_and_user_variablesr rr#)rkwargss rformatzPromptTemplate.formats9877A&A()=)=>t}}WPVWWrc D|j|g||}|d||d|S)aTake examples in list format with prefix and suffix to create a prompt. Intended to be used as a way to dynamically create a prompt from examples. Args: examples: List of examples to use in the prompt. suffix: String to go after the list of examples. Should generally set up the user's input. input_variables: A list of variable names the final prompt template will expect. example_separator: The separator to use in between examples. Defaults to two new line characters. prefix: String that should go before any examples. Generally includes examples. Returns: The final prompt generated. )r,r#r)join)r examplessuffixr,example_separatorprefixrKr#s r from_exampleszPromptTemplate.from_exampless68%))6*EH*Ef*EFP?XPPPrc `t|j|}|jdd|i|S)aDLoad a prompt from a file. Args: template_file: The path to the file containing the prompt template. encoding: The encoding system for opening the template file. If not provided, will use the OS default. Returns: The prompt loaded from the file. )encodingr#r)r read_textr@)r template_filerUrKr#s r from_filezPromptTemplate.from_files7" &00(0C s  =(=f==r)rr*c vt||}|xsi}|r|Dcgc] }||vs| }}|d||||d|Scc}w)aLoad a prompt template from a template. *Security warning*: Prefer using `template_format="f-string"` instead of `template_format="jinja2"`, or make sure to NEVER accept jinja2 templates from untrusted sources as they may lead to arbitrary Python code execution. As of LangChain 0.0.329, Jinja2 templates will be rendered using Jinja2's SandboxedEnvironment by default. This sand-boxing should be treated as a best-effort approach rather than a guarantee of security, as it is an opt-out rather than opt-in approach. Despite the sand-boxing, we recommend never using jinja2 templates from untrusted sources. Args: template: The template to load. template_format: The format of the template. Use `jinja2` for jinja2, `mustache` for mustache, and `f-string` for f-strings. partial_variables: A dictionary of variables that can be used to partially fill in the template. For example, if the template is `"{variable1} {variable2}"`, and `partial_variables` is `{"variable1": "foo"}`, then the final prompt will be `"foo {variable2}"`. **kwargs: Any other arguments to pass to the prompt template. Returns: The prompt template loaded from the template. )r,r#rr*r)r)r r#rr*rKr,partial_variables_r4s rr@zPromptTemplate.from_templatespL1?K.4" .#=O2OO ++0     s 66)returnzdict[str, Any])r[ list[str])r1r>r[r)N)r9zRunnableConfig | Noner[ztype[BaseModel])rCrr[r)r[r")rKrr[r")z )rOr\rPr"r,r\rQr"rRr"rKrr[r)rWz str | PathrUz str | NonerKrr[r) r#r"rr r*zdict[str, Any] | NonerKrr[r)__name__ __module__ __qualname____doc__propertyr r classmethodr!__annotations__rr&rr5r8rFrHrLrSrXr@ __classcell__)r:s@rrrs D    22M,6O)66$t#8(#"$"H . .*'X X "( QQQ# Q  Q  QQ QQ< $>!>> >  >>& 1;37 3 3 . 3 1 3  3  3 3 rrN)ra __future__rpathlibrtypingrrpydanticrrtyping_extensionsr langchain_core.prompts.stringr r r r rrlangchain_core.runnables.configrrrrrrms8"%/&>W )W r