a dg?@sddlZddlmZmZmZmZmZmZddlm Z ddl m Z ddl m Z ddlmZddlmZddlmZmZmZdd lmZGd d d eZdS) N)AnyDictListOptionalUnioncast)Chain)LLMChain)BaseLanguageModel)FewShotPromptTemplate)is_basemodel_instance) BaseModel ConfigDictmodel_validator)Selfc@seZdZUdZeed<dZeeed<gZ e ed<dZ ee ed<dZ eed<ed d Zed d ed ddZeeedddZeeeeefefddddZeeeeeedddZdeeeeeeedddZdS)SyntheticDataGeneratoraGenerate synthetic data using the given LLM and few-shot template. Utilizes the provided LLM to produce synthetic data based on the few-shot prompt template. Attributes: template (FewShotPromptTemplate): Template for few-shot prompting. llm (Optional[BaseLanguageModel]): Large Language Model to use for generation. llm_chain (Optional[Chain]): LLM chain with the LLM and few-shot template. example_input_key (str): Key to use for storing example inputs. Usage Example: >>> template = FewShotPromptTemplate(...) >>> llm = BaseLanguageModel(...) >>> generator = SyntheticDataGenerator(template=template, llm=llm) >>> results = generator.generate(subject="climate change", runs=5) templateNllmresults llm_chainexampleexample_input_keyT)Zvalidate_assignmentafter)mode)returncCs@|j}|j}|j}|s<|dus&|dur.tdt||d|_|S)NzJBoth llm and few_shot_template must be provided if llm_chain is not given.)rprompt)rrr ValueErrorr )selfrrZfew_shot_templater/var/www/html/cobodadashboardai.evdpl.com/venv/lib/python3.9/site-packages/langchain_experimental/tabular_synthetic_data/base.py set_llm_chain*sz$SyntheticDataGenerator.set_llm_chain) input_dictrcCsddd|D}|S)Nz, cSsg|]\}}|d|qS)z: r).0keyvaluerrr =zASyntheticDataGenerator._format_dict_to_string..)joinitems)r!Z formatted_strrrr_format_dict_to_string:sz-SyntheticDataGenerator._format_dict_to_string)rrcCsp|jrl|jjrlt|r,|tt|}nt|trB||}nt|}|jj d|jj |j |idS)zYPrevents duplicates by adding previously generated examples to the few shot list.rN) rZexamplesr r)rr dict isinstancestrpopappendr)rrZformatted_examplerrr_update_examplesAs   z'SyntheticDataGenerator._update_examples)subjectrunsargskwargsrcOsR|jdurtdt|D]0}|jj|d|i|}|j|||q|jS)aGenerate synthetic data using the given subject string. Args: subject (str): The subject the synthetic data will be about. runs (int): Number of times to generate the data. extra (str): Extra instructions for steerability in data generation. Returns: List[str]: List of generated synthetic data. Usage Example: >>> results = generator.generate(subject="climate change", runs=5, extra="Focus on environmental impacts.") NzOllm_chain is none, either set either llm_chain or llm at generator constructionr0)rrrangerunrr.r/)rr0r1r2r3_resultrrrgeneratePs    zSyntheticDataGenerator.generate)r0r1extrar2r3rcsHdttttddfdd tjfddt|DIdHjS) aGenerate synthetic data using the given subject asynchronously. Note: Since the LLM calls run concurrently, you may have fewer duplicates by adding specific instructions to the "extra" keyword argument. Args: subject (str): The subject the synthetic data will be about. runs (int): Number of times to generate the data asynchronously. extra (str): Extra instructions for steerability in data generation. Returns: List[str]: List of generated synthetic data for the given subject. Usage Example: >>> results = await generator.agenerate(subject="climate change", runs=5, extra="Focus on env impacts.") r9N)r0r:r2r3rcs8jdur4jj|||d|IdH}j|dS)Nr0r:)rZarunrr.)r0r:r2r3r7)rrr run_chains  z3SyntheticDataGenerator.agenerate..run_chainc3s|]}dVqdS)r;Nr)r"r6)r:r<r0rr r&z3SyntheticDataGenerator.agenerate..)r9)r,rasynciogatherr4r)rr0r1r:r2r3r)r:r<rr0r ageneratejs  z SyntheticDataGenerator.agenerate)r9)__name__ __module__ __qualname____doc__r __annotations__rrr rlistrrrr,rZ model_configrrr staticmethodrr)rr rr/intrr8r@rrrrr s(   " r)r>typingrrrrrrZlangchain.chains.baserZlangchain.chains.llmr Zlangchain_core.language_modelsr Zlangchain_core.prompts.few_shotr Zlangchain_core.utils.pydanticr Zpydanticr rrZtyping_extensionsrrrrrrs