如何构建合规的 AI 模型蒸馏合成数据工作流

pip install data-designer==0.4.0

import data_designer.config as dd
from data_designer.interface import DataDesigner

# We set trainable text to true here 
model_provider = dd.ModelProvider(
    name = "deepinfra",
    endpoint = "https://openrouter.ai/api/v1/",
    provider_type = "openai",
    api_key = Open_Router_Api_Key,
    extra_body={
        "provider": {
            "enforce_distillable_text": True,
            # optionally, prefer DeepInfra endpoints
            "only": ["deepinfra"]
        }
    }
)

data_designer_client = DataDesigner(model_providers=[model_provider])

model_alias="nemotron-3-nano-30b-a3b"

inference_parameters = dd.ChatCompletionInferenceParams(
    temperature=0.5,
    top_p=0.9,
    max_tokens=10000,
    max_parallel_requests=10,  # Number of concurrent workers
    extra_body={
        "reasoning": {"enabled": False}
    },
)

model_configs = [
    dd.ModelConfig(
        alias=model_alias,
        model="nvidia/nemotron-3-nano-30b-a3b",
        provider="deepinfra",
        inference_parameters=inference_parameters
        )
]

config_builder = dd.DataDesignerConfigBuilder(model_configs=model_configs)

import string
from pydantic import BaseModel
from pydantic import Field

# Define product category options
config_builder.add_column(
    dd.SamplerColumnConfig(
        name="category",
        sampler_type=dd.SamplerType.CATEGORY,
        params=dd.CategorySamplerParams(
            values=[
                "Electronics",
                "Clothing",
                "Home Appliances",
                "Groceries",
                "Toiletries",
                "Sports Equipment",
                "Toys",
                "Books",
                "Pet Supplies",
                "Tools & Home Improvement",
                "Beauty",
                "Health & Wellness",
                "Outdoor Gear",
                "Automotive",
                "Jewelry",
                "Watches",
                "Office Supplies",
                "Gifts",
                "Arts & Crafts",
                "Baby & Kids",
                "Music",
                "Video Games",
                "Movies",
                "Software",
                "Tech Devices",
            ]
        ),
    )
)

# Define price range to seed realistic product types
config_builder.add_column(
    dd.SamplerColumnConfig(
        name="price_tens_of_dollars",
        sampler_type=dd.SamplerType.UNIFORM,
        params=dd.UniformSamplerParams(low=1, high=200),
    )
)

config_builder.add_column(
    dd.ExpressionColumnConfig(
        name="product_price",
        expr="{{ (price_tens_of_dollars * 10) - 0.01 | round(2) }}",
        dtype="float",
    )
)

# Generate first letter for product name to ensure diversity
config_builder.add_column(
    dd.SamplerColumnConfig(
        name="first_letter",
        sampler_type=dd.SamplerType.CATEGORY,
        params=dd.CategorySamplerParams(values=list(string.ascii_uppercase)),
    )
)

# Determine if this example will include hallucination
config_builder.add_column(
    dd.SamplerColumnConfig(
        name="is_hallucination",
        sampler_type=dd.SamplerType.BERNOULLI,
        params=dd.BernoulliSamplerParams(p=0.5),
    )
)          

# Define product information structure
class ProductInfo(BaseModel):
    product_name: str = Field(
        ..., description="A realistic product name for the market."
    )
    key_features: list[str] = Field(
        ..., min_length=1, max_length=3, description="Key product features."
    )
    description: str = Field(
        ...,
        description="A short, engaging description of what the product does, highlighting a unique but believable feature.",
    )
    price_usd: float = Field(..., description="The stated price in USD.")


# Generate product information
config_builder.add_column(
    dd.LLMStructuredColumnConfig(
        name="product_info",
        model_alias=model_alias,
        prompt=(
            "Generate a realistic product description for a product in the {{ category }} "
            "category that costs {{ product_price }}.\n"
            "The name of the product MUST start with the letter {{ first_letter }}.\n"
        ),
        output_format=ProductInfo,
    )
)

# Generate user questions about the product
config_builder.add_column(
    dd.LLMTextColumnConfig(
        name="question",
        model_alias=model_alias,
        prompt=("Ask a question about the following product:\n\n {{ product_info }}"),
    )
)


# Generate answers to the questions
config_builder.add_column(
    dd.LLMTextColumnConfig(
        name="answer",
        model_alias=model_alias,
        prompt=(
            "{%- if is_hallucination == 0 -%}\n"
            "<product_info>\n"
            "{{ product_info }}\n"
            "</product_info>\n"
            "{%- endif -%}\n"
            "User Question: {{ question }}\n"
            "Directly and succinctly answer the user's question.\n"
            "{%- if is_hallucination == 1 -%}\n"
            "Make up whatever information you need to in order to answer the user's request.\n"
            "{%- endif -%}"
        ),
    )
)

# Define evaluation rubrics for answer quality
CompletenessRubric = dd.Score(
    name="Completeness",
    description="Evaluation of AI assistant's thoroughness in addressing all aspects of the user's query.",
    options={
        "Complete": "The response thoroughly covers all key points requested in the question, providing sufficient detail to satisfy the user's information needs.",
        "PartiallyComplete": "The response addresses the core question but omits certain important details or fails to elaborate on relevant aspects that were requested.",
        "Incomplete": "The response significantly lacks necessary information, missing major components of what was asked and leaving the query largely unanswered.",
    },
)

AccuracyRubric = dd.Score(
    name="Accuracy",
    description="Evaluation of how factually correct the AI assistant's response is relative to the product information.",
    options={
        "Accurate": "The information provided aligns perfectly with the product specifications without introducing any misleading or incorrect details.",
        "PartiallyAccurate": "While some information is correctly stated, the response contains minor factual errors or potentially misleading statements about the product.",
        "Inaccurate": "The response presents significantly wrong information about the product, with claims that contradict the actual product details.",
    },
)


# Evaluate answer quality
config_builder.add_column(
    dd.LLMJudgeColumnConfig(
        name="llm_answer_metrics",
        model_alias=model_alias,
        prompt=(
            "<product_info>\n"
            "{{ product_info }}\n"
            "</product_info>\n"
            "User Question: {{question }}\n"
            "AI Assistant Answer: {{ answer }}\n"
            "Judge the AI assistant's response to the user's question about the product described in <product_info>."
        ),
        scores=[CompletenessRubric, AccuracyRubric],
    )
)


# Extract metric scores for easier analysis
config_builder.add_column(
    dd.ExpressionColumnConfig(
        name="completeness_result",
        expr="{{ llm_answer_metrics.Completeness.score }}",
    )
)

config_builder.add_column(
    dd.ExpressionColumnConfig(
        name="accuracy_result",
        expr="{{ llm_answer_metrics.Accuracy.score }}",
    )
)

preview = data_designer_client.preview(config_builder)

# Display one record
preview.display_sample_record()

job_results = data_designer_client.create(config_builder, num_records=100)
dataset = job_results.load_dataset()

from pathlib import Path

Folder_Name = "data-designer-tutorial-output"
File_Name = "dataset_OR.csv"

TUTORIAL_OUTPUT_PATH = Path(Folder_Name)
TUTORIAL_OUTPUT_PATH.mkdir(parents=True, exist_ok=True)

dataset.to_csv(TUTORIAL_OUTPUT_PATH / File_Name, index=False)