Skip to navigation
Tutorials

Structured Outputs, Jinja Expressions, and Conditional Generation

View as Markdown
Run in Google Colab

🎨 Data Designer Tutorial: Structured Outputs, Jinja Expressions, and Conditional Generation

📚 What you'll learn

In this notebook, we will continue our exploration of Data Designer, demonstrating more advanced data generation using structured outputs, Jinja expressions, and conditional generation with skip.when.

If this is your first time using Data Designer, we recommend starting with the first notebook in this tutorial series.

📦 Import Data Designer

  • data_designer.config provides access to the configuration API.

  • DataDesigner is the main interface for data generation.

Python
1import data_designer.config as dd
2from data_designer.interface import DataDesigner
3

⚙️ Initialize the Data Designer interface

  • DataDesigner is the main object that is used to interface with the library.

  • When initialized without arguments, the default model providers are used.

Python
1data_designer = DataDesigner()
2

🎛️ Define model configurations

  • Each ModelConfig defines a model that can be used during the generation process.

  • The "model alias" is used to reference the model in the Data Designer config (as we will see below).

  • The "model provider" is the external service that hosts the model (see the model config docs for more details).

  • By default, we use build.nvidia.com as the model provider.

Python
1# This name is set in the model provider configuration.
2MODEL_PROVIDER = "nvidia"
3 
4# The model ID is from build.nvidia.com.
5MODEL_ID = "nvidia/nemotron-3.5-lightning-30b-a3b"
6 
7# We choose this alias to be descriptive for our use case.
8MODEL_ALIAS = "nemotron-lightning"
9 
10model_configs = [
11    dd.ModelConfig(
12        alias=MODEL_ALIAS,
13        model=MODEL_ID,
14        provider=MODEL_PROVIDER,
15        inference_parameters=dd.ChatCompletionInferenceParams(
16            temperature=1.0,
17            top_p=0.95,
18            max_tokens=2048,
19            extra_body={"chat_template_kwargs": {"enable_thinking": False}},
20        ),
21    )
22]
23

🏗️ Initialize the Data Designer Config Builder

  • The Data Designer config defines the dataset schema and generation process.

  • The config builder provides an intuitive interface for building this configuration.

  • The list of model configs is provided to the builder at initialization.

Python
1config_builder = dd.DataDesignerConfigBuilder(model_configs=model_configs)
2

🧑‍🎨 Designing our data

  • We will again create a product review dataset, but this time we will use structured outputs and Jinja expressions.

  • Structured outputs let you specify the exact schema of the data you want to generate.

  • Data Designer supports schemas specified using either json schema or Pydantic data models (recommended).


We'll define our structured outputs using Pydantic data models

💡 Why Pydantic?

  • Pydantic models provide better IDE support and type validation.

  • They are more Pythonic than raw JSON schemas.

  • They integrate seamlessly with Data Designer's structured output system.

Python
1from decimal import Decimal
2from typing import Literal
3 
4from pydantic import BaseModel, Field
5 
6 
7# We define a Product schema so that the name, description, and price are generated
8# in one go, with the types and constraints specified.
9class Product(BaseModel):
10    name: str = Field(description="The name of the product")
11    description: str = Field(description="A description of the product")
12    price: Decimal = Field(description="The price of the product", ge=10, le=1000, decimal_places=2)
13 
14 
15class ProductReview(BaseModel):
16    rating: int = Field(description="The rating of the product", ge=1, le=5)
17    customer_mood: Literal["irritated", "mad", "happy", "neutral", "excited"] = Field(
18        description="The mood of the customer"
19    )
20    review: str = Field(description="A review of the product")
21

Next, let's design our product review dataset using a few more tricks compared to the previous notebook.

Python
1# Since we often only want a few attributes from Person objects, we can
2# set drop=True in the column config to drop the column from the final dataset.
3config_builder.add_column(
4    dd.SamplerColumnConfig(
5        name="customer",
6        sampler_type=dd.SamplerType.PERSON_FROM_FAKER,
7        params=dd.PersonFromFakerSamplerParams(),
8        drop=True,
9    )
10)
11 
12config_builder.add_column(
13    dd.SamplerColumnConfig(
14        name="product_category",
15        sampler_type=dd.SamplerType.CATEGORY,
16        params=dd.CategorySamplerParams(
17            values=[
18                "Electronics",
19                "Clothing",
20                "Home & Kitchen",
21                "Books",
22                "Home Office",
23            ],
24        ),
25    )
26)
27 
28config_builder.add_column(
29    dd.SamplerColumnConfig(
30        name="product_subcategory",
31        sampler_type=dd.SamplerType.SUBCATEGORY,
32        params=dd.SubcategorySamplerParams(
33            category="product_category",
34            values={
35                "Electronics": [
36                    "Smartphones",
37                    "Laptops",
38                    "Headphones",
39                    "Cameras",
40                    "Accessories",
41                ],
42                "Clothing": [
43                    "Men's Clothing",
44                    "Women's Clothing",
45                    "Winter Coats",
46                    "Activewear",
47                    "Accessories",
48                ],
49                "Home & Kitchen": [
50                    "Appliances",
51                    "Cookware",
52                    "Furniture",
53                    "Decor",
54                    "Organization",
55                ],
56                "Books": [
57                    "Fiction",
58                    "Non-Fiction",
59                    "Self-Help",
60                    "Textbooks",
61                    "Classics",
62                ],
63                "Home Office": [
64                    "Desks",
65                    "Chairs",
66                    "Storage",
67                    "Office Supplies",
68                    "Lighting",
69                ],
70            },
71        ),
72    )
73)
74 
75config_builder.add_column(
76    dd.SamplerColumnConfig(
77        name="target_age_range",
78        sampler_type=dd.SamplerType.CATEGORY,
79        params=dd.CategorySamplerParams(values=["18-25", "25-35", "35-50", "50-65", "65+"]),
80    )
81)
82 
83# Sampler columns support conditional params, which are used if the condition is met.
84# In this example, we set the review style to rambling if the target age range is 18-25.
85# Note conditional parameters are only supported for Sampler column types.
86config_builder.add_column(
87    dd.SamplerColumnConfig(
88        name="review_style",
89        sampler_type=dd.SamplerType.CATEGORY,
90        params=dd.CategorySamplerParams(
91            values=["rambling", "brief", "detailed", "structured with bullet points"],
92            weights=[1, 2, 2, 1],
93        ),
94        conditional_params={
95            "target_age_range == '18-25'": dd.CategorySamplerParams(values=["rambling"]),
96        },
97    )
98)
99 
100# Optionally validate that the columns are configured correctly.
101data_designer.validate(config_builder)
102
Output
[19:55:38] [INFO] ✅ Validation passed

Next, we will use more advanced Jinja expressions to create new columns.

Jinja expressions let you:

  • Access nested attributes: {{ customer.first_name }}

  • Combine values: {{ customer.first_name }} {{ customer.last_name }}

  • Use conditional logic: {% if condition %}...{% endif %}

Python
1# We can create new columns using Jinja expressions that reference
2# existing columns, including attributes of nested objects.
3config_builder.add_column(
4    dd.ExpressionColumnConfig(name="customer_name", expr="{{ customer.first_name }} {{ customer.last_name }}")
5)
6 
7config_builder.add_column(dd.ExpressionColumnConfig(name="customer_age", expr="{{ customer.age }}"))
8 
9config_builder.add_column(
10    dd.LLMStructuredColumnConfig(
11        name="product",
12        prompt=(
13            "Create a product in the '{{ product_category }}' category, focusing on products  "
14            "related to '{{ product_subcategory }}'. The target age range of the ideal customer is "
15            "{{ target_age_range }} years old. The product should be priced between $10 and $1000."
16        ),
17        output_format=Product,
18        model_alias=MODEL_ALIAS,
19    )
20)
21 
22# We can even use if/else logic in our Jinja expressions to create more complex prompt patterns.
23config_builder.add_column(
24    dd.LLMStructuredColumnConfig(
25        name="customer_review",
26        prompt=(
27            "Your task is to write a review for the following product:\n\n"
28            "Product Name: {{ product.name }}\n"
29            "Product Description: {{ product.description }}\n"
30            "Price: {{ product.price }}\n\n"
31            "Imagine your name is {{ customer_name }} and you are from {{ customer.city }}, {{ customer.state }}. "
32            "Write the review in a style that is '{{ review_style }}'."
33            "{% if target_age_range == '18-25' %}"
34            "Make sure the review is more informal and conversational.\n"
35            "{% else %}"
36            "Make sure the review is more formal and structured.\n"
37            "{% endif %}"
38            "The review field should contain only the review, no other text."
39        ),
40        output_format=ProductReview,
41        model_alias=MODEL_ALIAS,
42    )
43)
44 
45data_designer.validate(config_builder)
46
Output
[19:55:38] [INFO] ✅ Validation passed

🚦 Conditional generation with skip.when

So far, every column is generated for every row. But sometimes an expensive LLM column only makes sense for a subset of rows — for example, a detailed complaint analysis is only useful when the review is negative.

Data Designer lets you skip column generation on a per-row basis using SkipConfig. Skipped rows receive None by default, but you can provide a sentinel value with skip=dd.SkipConfig(when="...", value="N/A") to write a specific value instead.

There are three patterns to know:

Pattern How Effect
Expression gate skip=dd.SkipConfig(when="...") Skip this column when the Jinja2 expression is truthy
Skip propagation (default) Downstream column depends on a skipped column Automatically skipped too (propagate_skip=True by default)
Propagation opt-out propagate_skip=False on the downstream column Always generates, even if an upstream was skipped

Pattern 1 — Expression gate. Only generate a detailed complaint analysis when the customer gave a low rating (1 or 2 stars). Rows where the rating is 3 or higher will get None for this column.

Python
1config_builder.add_column(
2    dd.LLMTextColumnConfig(
3        name="complaint_analysis",
4        model_alias=MODEL_ALIAS,
5        prompt=(
6            "A customer reviewed '{{ product.name }}' ({{ product_category }} / {{ product_subcategory }}).\n\n"
7            "Review: {{ customer_review.review }}\n"
8            "Rating: {{ customer_review.rating }}/5\n"
9            "Mood: {{ customer_review.customer_mood }}\n\n"
10            "Write a short root-cause analysis of why this customer is unhappy "
11            "and suggest one concrete improvement the product team could make."
12        ),
13        skip=dd.SkipConfig(when="{{ customer_review.rating > 2 }}"),
14    )
15)
16
Output
DataDesignerConfigBuilder(
    sampler_columns: [
        "customer",
        "product_category",
        "product_subcategory",
        "target_age_range",
        "review_style"
    ]
    llm_text_columns: ['complaint_analysis']
    llm_structured_columns: ['product', 'customer_review']
    expression_columns: ['customer_name', 'customer_age']
)

Pattern 2 — Skip propagation. action_items depends on complaint_analysis. When complaint_analysis is skipped, action_items auto-skips too because propagate_skip defaults to True.

Python
1config_builder.add_column(
2    dd.LLMTextColumnConfig(
3        name="action_items",
4        model_alias=MODEL_ALIAS,
5        prompt=(
6            "Based on this complaint analysis:\n"
7            "{{ complaint_analysis }}\n\n"
8            "List 2-3 concrete action items for the product team."
9        ),
10    )
11)
12
Output
DataDesignerConfigBuilder(
    sampler_columns: [
        "customer",
        "product_category",
        "product_subcategory",
        "target_age_range",
        "review_style"
    ]
    llm_text_columns: ['complaint_analysis', 'action_items']
    llm_structured_columns: ['product', 'customer_review']
    expression_columns: ['customer_name', 'customer_age']
)

Pattern 3 — Propagation opt-out. review_summary also depends on complaint_analysis, but sets propagate_skip=False so it always generates. The prompt uses a Jinja conditional to handle the case where complaint_analysis is None.

Python
1config_builder.add_column(
2    dd.LLMTextColumnConfig(
3        name="review_summary",
4        model_alias=MODEL_ALIAS,
5        propagate_skip=False,
6        prompt=(
7            "Summarize this product review in one sentence:\n"
8            "Product: {{ product.name }}\n"
9            "Rating: {{ customer_review.rating }}/5\n"
10            "Review: {{ customer_review.review }}\n"
11            "{% if complaint_analysis %}"
12            "Complaint analysis: {{ complaint_analysis }}\n"
13            "{% endif %}"
14        ),
15    )
16)
17 
18data_designer.validate(config_builder)
19
Output
[19:55:38] [INFO] ✅ Validation passed

🔁 Iteration is key – preview the dataset!

  1. Use the preview method to generate a sample of records quickly.

  2. Inspect the results for quality and format issues.

  3. Adjust column configurations, prompts, or parameters as needed.

  4. Re-run the preview until satisfied.

Python
1preview = data_designer.preview(config_builder, num_records=2)
2
Output
[19:55:38] [INFO] 🔭 Preview generation in progress
[19:55:38] [INFO]   |-- 🔒 Jinja rendering engine: secure
[19:55:38] [INFO] ✅ Validation passed
[19:55:38] [INFO] ⛓️ Sorting column configs into a Directed Acyclic Graph
[19:55:38] [INFO] Skipping model health checks because DATA_DESIGNER_SKIP_MODEL_HEALTH_CHECKS=1
[19:55:38] [INFO] ⚡ Using async task-queue preview
[19:55:38] [INFO] 🗂️ llm-structured model config for column 'product'
[19:55:38] [INFO]   |-- model: 'nvidia/nemotron-3.5-lightning-30b-a3b'
[19:55:38] [INFO]   |-- model alias: 'nemotron-lightning'
[19:55:38] [INFO]   |-- model provider: 'nvidia'
[19:55:38] [INFO]   |-- inference parameters:
[19:55:38] [INFO]   |  |-- generation_type=chat-completion
[19:55:38] [INFO]   |  |-- max_parallel_requests=4
[19:55:38] [INFO]   |  |-- extra_body={'chat_template_kwargs': {'enable_thinking': False}}
[19:55:38] [INFO]   |  |-- temperature=1.00
[19:55:38] [INFO]   |  |-- top_p=0.95
[19:55:38] [INFO]   |  |-- max_tokens=2048
[19:55:38] [INFO] 🗂️ llm-structured model config for column 'customer_review'
[19:55:38] [INFO]   |-- model: 'nvidia/nemotron-3.5-lightning-30b-a3b'
[19:55:38] [INFO]   |-- model alias: 'nemotron-lightning'
[19:55:38] [INFO]   |-- model provider: 'nvidia'
[19:55:38] [INFO]   |-- inference parameters:
[19:55:38] [INFO]   |  |-- generation_type=chat-completion
[19:55:38] [INFO]   |  |-- max_parallel_requests=4
[19:55:38] [INFO]   |  |-- extra_body={'chat_template_kwargs': {'enable_thinking': False}}
[19:55:38] [INFO]   |  |-- temperature=1.00
[19:55:38] [INFO]   |  |-- top_p=0.95
[19:55:38] [INFO]   |  |-- max_tokens=2048
[19:55:38] [INFO] 📝 llm-text model config for column 'complaint_analysis'
[19:55:38] [INFO]   |-- model: 'nvidia/nemotron-3.5-lightning-30b-a3b'
[19:55:38] [INFO]   |-- model alias: 'nemotron-lightning'
[19:55:38] [INFO]   |-- model provider: 'nvidia'
[19:55:38] [INFO]   |-- inference parameters:
[19:55:38] [INFO]   |  |-- generation_type=chat-completion
[19:55:38] [INFO]   |  |-- max_parallel_requests=4
[19:55:38] [INFO]   |  |-- extra_body={'chat_template_kwargs': {'enable_thinking': False}}
[19:55:38] [INFO]   |  |-- temperature=1.00
[19:55:38] [INFO]   |  |-- top_p=0.95
[19:55:38] [INFO]   |  |-- max_tokens=2048
[19:55:38] [INFO] 📝 llm-text model config for column 'review_summary'
[19:55:38] [INFO]   |-- model: 'nvidia/nemotron-3.5-lightning-30b-a3b'
[19:55:38] [INFO]   |-- model alias: 'nemotron-lightning'
[19:55:38] [INFO]   |-- model provider: 'nvidia'
[19:55:38] [INFO]   |-- inference parameters:
[19:55:38] [INFO]   |  |-- generation_type=chat-completion
[19:55:38] [INFO]   |  |-- max_parallel_requests=4
[19:55:38] [INFO]   |  |-- extra_body={'chat_template_kwargs': {'enable_thinking': False}}
[19:55:38] [INFO]   |  |-- temperature=1.00
[19:55:38] [INFO]   |  |-- top_p=0.95
[19:55:38] [INFO]   |  |-- max_tokens=2048
[19:55:38] [INFO] 📝 llm-text model config for column 'action_items'
[19:55:38] [INFO]   |-- model: 'nvidia/nemotron-3.5-lightning-30b-a3b'
[19:55:38] [INFO]   |-- model alias: 'nemotron-lightning'
[19:55:38] [INFO]   |-- model provider: 'nvidia'
[19:55:38] [INFO]   |-- inference parameters:
[19:55:38] [INFO]   |  |-- generation_type=chat-completion
[19:55:38] [INFO]   |  |-- max_parallel_requests=4
[19:55:38] [INFO]   |  |-- extra_body={'chat_template_kwargs': {'enable_thinking': False}}
[19:55:38] [INFO]   |  |-- temperature=1.00
[19:55:38] [INFO]   |  |-- top_p=0.95
[19:55:38] [INFO]   |  |-- max_tokens=2048
[19:55:38] [INFO] ⚡️ Async generation: 5 column(s) (column 'product', column 'customer_review', column 'complaint_analysis', column 'review_summary', column 'action_items'), 10 tasks across 1 row group(s)
[19:55:38] [INFO] 🚀 (1/1) Dispatching with 2 records
[19:55:38] [INFO] 🎲 (1/1) Preparing samplers to generate 2 records across 5 columns
[19:55:39] [INFO] 🧩 (1/1) Generating column `customer_age` from expression
[19:55:39] [INFO] 🧩 (1/1) Generating column `customer_name` from expression
[19:55:44] [INFO] 📊 Progress [5.6s]:
[19:55:44] [INFO]   |-- 🤩 column 'product': 2/2 (100%) 0.4 rec/s
[19:55:44] [INFO]   |-- ⛅ column 'customer_review': 1/2 (50%) 0.2 rec/s
[19:55:44] [INFO]   |-- 🌗 column 'complaint_analysis': 1/2 (50%) 0.2 rec/s, 1 skipped
[19:55:44] [INFO]   |-- 🐥 column 'review_summary': 1/2 (50%) 0.2 rec/s
[19:55:44] [INFO]   |-- ⛅ column 'action_items': 1/2 (50%) 0.2 rec/s, 1 skipped
[19:55:48] [INFO] 📊 Progress [9.4s]:
[19:55:48] [INFO]   |-- 🤩 column 'product': 2/2 (100%) 0.2 rec/s
[19:55:48] [INFO]   |-- ☀️ column 'customer_review': 2/2 (100%) 0.2 rec/s
[19:55:48] [INFO]   |-- 🌕 column 'complaint_analysis': 2/2 (100%) 0.2 rec/s, 2 skipped
[19:55:48] [INFO]   |-- 🐔 column 'review_summary': 2/2 (100%) 0.2 rec/s
[19:55:48] [INFO]   |-- ☀️ column 'action_items': 2/2 (100%) 0.2 rec/s, 2 skipped
[19:55:48] [INFO] ✅ Async generation complete [9.4s]: 6 ok, 0 failed, 4 skipped across 5 column(s)
[19:55:48] [INFO] 📊 Model usage summary:
[19:55:48] [INFO]   |-- model: nvidia/nemotron-3.5-lightning-30b-a3b
[19:55:48] [INFO]   |-- tokens: input=1731, output=677, reasoning=0, total=2408, tps=255
[19:55:48] [INFO]   |-- requests: success=6, failed=0, total=6, rpm=38
[19:55:48] [INFO] 🙈 Dropping columns: ['customer']
[19:55:48] [INFO] 📐 Measuring dataset column statistics:
[19:55:48] [INFO]   |-- 🎲 column: 'product_category'
[19:55:48] [INFO]   |-- 🎲 column: 'product_subcategory'
[19:55:48] [INFO]   |-- 🎲 column: 'target_age_range'
[19:55:48] [INFO]   |-- 🎲 column: 'review_style'
[19:55:48] [INFO]   |-- 🧩 column: 'customer_name'
[19:55:48] [INFO]   |-- 🧩 column: 'customer_age'
[19:55:48] [INFO]   |-- 🗂️ column: 'product'
[19:55:48] [INFO]   |-- 🗂️ column: 'customer_review'
[19:55:48] [INFO]   |-- 📝 column: 'complaint_analysis'
[19:55:48] [INFO]   |-- 📝 column: 'action_items'
[19:55:48] [INFO]   |-- 📝 column: 'review_summary'
[19:55:48] [INFO] 👏 Preview complete!
Python
1# Run this cell multiple times to cycle through the 2 preview records.
2# Look for rows where complaint_analysis and action_items are None (skipped)
3# vs rows where they were generated (low-rated reviews).
4preview.display_sample_record()
5
Output
[index: 0]
                                                                                                              
                                              Generated Columns                                               
┏━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ Name                ┃ Value                                                                                ┃
┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩
│ product_category    │ Books                                                                                │
├─────────────────────┼──────────────────────────────────────────────────────────────────────────────────────┤
│ product_subcategory │ Textbooks                                                                            │
├─────────────────────┼──────────────────────────────────────────────────────────────────────────────────────┤
│ target_age_range    │ 25-35                                                                                │
├─────────────────────┼──────────────────────────────────────────────────────────────────────────────────────┤
│ review_style        │ brief                                                                                │
├─────────────────────┼──────────────────────────────────────────────────────────────────────────────────────┤
│ complaint_analysis  │ None                                                                                 │
├─────────────────────┼──────────────────────────────────────────────────────────────────────────────────────┤
│ action_items        │ None                                                                                 │
├─────────────────────┼──────────────────────────────────────────────────────────────────────────────────────┤
│ review_summary      │ This review praises the book as a rigorous yet accessible guide that effectively     │
│                     │ bridges theory and practice, particularly commending its clear explanations of       │
│                     │ complex topics like balanced trees and graph algorithms along with practical Python  │
│                     │ and Java implementations, making it an essential resource for intermediate to        │
│                     │ advanced learners and interview preparation.                                         │
├─────────────────────┼──────────────────────────────────────────────────────────────────────────────────────┤
│ product             │ {                                                                                    │
│                     │     'name': 'Advanced Data Structures and Algorithms: A Modern Approach',            │
│                     │     'description': 'A comprehensive textbook designed for intermediate to advanced   │
│                     │ computer science students and professionals. This book bridges the gap between       │
│                     │ theoretical concepts and practical implementation, covering topics such as balanced  │
│                     │ trees, hash tables, graph algorithms, and dynamic programming. It features clear     │
│                     │ explanations, real-world code examples in Python and Java, and practice problems     │
│                     │ with solutions. Perfect for readers aged 25-35 looking to advance their technical    │
│                     │ skills or prepare for technical interviews.',                                        │
│                     │     'price': 89.99                                                                   │
│                     │ }                                                                                    │
├─────────────────────┼──────────────────────────────────────────────────────────────────────────────────────┤
│ customer_review     │ {                                                                                    │
│                     │     'rating': 5,                                                                     │
│                     │     'customer_mood': 'happy',                                                        │
│                     │     'review': 'Advanced Data Structures and Algorithms: A Modern Approach provides a │
│                     │ rigorous yet accessible bridge between theory and practice. The text excels in its   │
│                     │ clear explanations of complex topics like balanced trees and graph algorithms,       │
│                     │ complemented by practical Python and Java implementations. An essential resource for │
│                     │ intermediate to advanced learners and technical interview preparation.'              │
│                     │ }                                                                                    │
├─────────────────────┼──────────────────────────────────────────────────────────────────────────────────────┤
│ customer_name       │ Charles Mullins                                                                      │
├─────────────────────┼──────────────────────────────────────────────────────────────────────────────────────┤
│ customer_age        │ 57                                                                                   │
└─────────────────────┴──────────────────────────────────────────────────────────────────────────────────────┘
Python
1# The preview dataset is available as a pandas DataFrame.
2# Notice that complaint_analysis, action_items, and review_summary columns
3# reflect the skip behavior: None for skipped rows, generated text otherwise.
4preview.dataset
5
Output
product_category product_subcategory target_age_range review_style customer_name customer_age product customer_review complaint_analysis action_items review_summary
0 Books Textbooks 25-35 brief Charles Mullins 57 {'name': 'Advanced Data Structures and Algorit... {'rating': 5, 'customer_mood': 'happy', 'revie... None None This review praises the book as a rigorous yet...
1 Books Non-Fiction 65+ detailed Thomas Bradley 25 {'name': 'The Golden Years Guide: A Non-Fictio... {'rating': 5, 'customer_mood': 'happy', 'revie... None None The Golden Years Guide is a meticulously curat...

📊 Analyze the generated data

  • Data Designer automatically generates a basic statistical analysis of the generated data.

  • This analysis is available via the analysis property of generation result objects.

Python
1# Print the analysis as a table.
2preview.analysis.to_report()
3
Output
──────────────────────────────────────── 🎨 Data Designer Dataset Profile ─────────────────────────────────────────

                                                                                                                   
                                                 Dataset Overview                                                  
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ number of records               ┃ number of columns               ┃ percent complete records                    ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩
│ 2                               │ 11                              │ 100.0%                                      │
└─────────────────────────────────┴─────────────────────────────────┴─────────────────────────────────────────────┘
                                                                                                                   
                                                                                                                   
                                                🎲 Sampler Columns                                                 
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━┓
┃ column name                      ┃        data type ┃               number unique values ┃         sampler type ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━┩
│ product_category                 │           string │                          1 (50.0%) │             category │
├──────────────────────────────────┼──────────────────┼────────────────────────────────────┼──────────────────────┤
│ product_subcategory              │           string │                         2 (100.0%) │          subcategory │
├──────────────────────────────────┼──────────────────┼────────────────────────────────────┼──────────────────────┤
│ target_age_range                 │           string │                         2 (100.0%) │             category │
├──────────────────────────────────┼──────────────────┼────────────────────────────────────┼──────────────────────┤
│ review_style                     │           string │                         2 (100.0%) │             category │
└──────────────────────────────────┴──────────────────┴────────────────────────────────────┴──────────────────────┘
                                                                                                                   
                                                                                                                   
                                                📝 LLM-Text Columns                                                
┏━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━┓
┃                         ┃              ┃                            ┃      prompt tokens ┃    completion tokens ┃
┃ column name             ┃    data type ┃       number unique values ┃         per record ┃           per record ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━┩
│ complaint_analysis      │         None │                   0 (0.0%) │     197.0 +/- 78.0 │          1.0 +/- 0.0 │
├─────────────────────────┼──────────────┼────────────────────────────┼────────────────────┼──────────────────────┤
│ action_items            │         None │                   0 (0.0%) │       22.0 +/- 0.0 │          1.0 +/- 0.0 │
├─────────────────────────┼──────────────┼────────────────────────────┼────────────────────┼──────────────────────┤
│ review_summary          │       string │                 2 (100.0%) │     169.5 +/- 77.5 │        45.5 +/- 13.4 │
└─────────────────────────┴──────────────┴────────────────────────────┴────────────────────┴──────────────────────┘
                                                                                                                   
                                                                                                                   
                                             🗂️ LLM-Structured Columns                                             
┏━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┓
┃                       ┃               ┃                            ┃     prompt tokens ┃      completion tokens ┃
┃ column name           ┃     data type ┃       number unique values ┃        per record ┃             per record ┃
┡━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━┩
│ product               │          dict │                 2 (100.0%) │     264.0 +/- 0.0 │          111.5 +/- 3.5 │
├───────────────────────┼───────────────┼────────────────────────────┼───────────────────┼────────────────────────┤
│ customer_review       │          dict │                 2 (100.0%) │     365.5 +/- 2.5 │        153.0 +/- 104.7 │
└───────────────────────┴───────────────┴────────────────────────────┴───────────────────┴────────────────────────┘
                                                                                                                   
                                                                                                                   
                                               🧩 Expression Columns                                               
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ column name                       ┃                data type ┃                             number unique values ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩
│ customer_name                     │                   string │                                       2 (100.0%) │
├───────────────────────────────────┼──────────────────────────┼──────────────────────────────────────────────────┤
│ customer_age                      │                   string │                                       2 (100.0%) │
└───────────────────────────────────┴──────────────────────────┴──────────────────────────────────────────────────┘
                                                                                                                   
                                                                                                                   
╭────────────────────────────────────────────────── Table Notes ──────────────────────────────────────────────────╮
│                                                                                                                 │
│  1. All token statistics are based on a sample of max(1000, len(dataset)) records.                              │
│  2. Tokens are calculated using tiktoken's cl100k_base tokenizer.                                               │
│                                                                                                                 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
                                                                                                                   
───────────────────────────────────────────────────────────────────────────────────────────────────────────────────

🆙 Scale up!

  • Happy with your preview data?

  • Use the create method to submit larger Data Designer generation jobs.

Python
1results = data_designer.create(config_builder, num_records=10, dataset_name="tutorial-2")
2
Output
[19:55:48] [INFO] OpenTelemetry metrics available at http://127.0.0.1:9464/metrics
[19:55:48] [INFO] 🎨 Creating Data Designer dataset
[19:55:48] [INFO]   |-- 🔒 Jinja rendering engine: secure
[19:55:48] [INFO] ✅ Validation passed
[19:55:48] [INFO] ⛓️ Sorting column configs into a Directed Acyclic Graph
[19:55:48] [INFO] Skipping model health checks because DATA_DESIGNER_SKIP_MODEL_HEALTH_CHECKS=1
[19:55:48] [INFO] ⚡ Using async task-queue builder
[19:55:48] [INFO] 🗂️ llm-structured model config for column 'product'
[19:55:48] [INFO]   |-- model: 'nvidia/nemotron-3.5-lightning-30b-a3b'
[19:55:48] [INFO]   |-- model alias: 'nemotron-lightning'
[19:55:48] [INFO]   |-- model provider: 'nvidia'
[19:55:48] [INFO]   |-- inference parameters:
[19:55:48] [INFO]   |  |-- generation_type=chat-completion
[19:55:48] [INFO]   |  |-- max_parallel_requests=4
[19:55:48] [INFO]   |  |-- extra_body={'chat_template_kwargs': {'enable_thinking': False}}
[19:55:48] [INFO]   |  |-- temperature=1.00
[19:55:48] [INFO]   |  |-- top_p=0.95
[19:55:48] [INFO]   |  |-- max_tokens=2048
[19:55:48] [INFO] 🗂️ llm-structured model config for column 'customer_review'
[19:55:48] [INFO]   |-- model: 'nvidia/nemotron-3.5-lightning-30b-a3b'
[19:55:48] [INFO]   |-- model alias: 'nemotron-lightning'
[19:55:48] [INFO]   |-- model provider: 'nvidia'
[19:55:48] [INFO]   |-- inference parameters:
[19:55:48] [INFO]   |  |-- generation_type=chat-completion
[19:55:48] [INFO]   |  |-- max_parallel_requests=4
[19:55:48] [INFO]   |  |-- extra_body={'chat_template_kwargs': {'enable_thinking': False}}
[19:55:48] [INFO]   |  |-- temperature=1.00
[19:55:48] [INFO]   |  |-- top_p=0.95
[19:55:48] [INFO]   |  |-- max_tokens=2048
[19:55:48] [INFO] 📝 llm-text model config for column 'complaint_analysis'
[19:55:48] [INFO]   |-- model: 'nvidia/nemotron-3.5-lightning-30b-a3b'
[19:55:48] [INFO]   |-- model alias: 'nemotron-lightning'
[19:55:48] [INFO]   |-- model provider: 'nvidia'
[19:55:48] [INFO]   |-- inference parameters:
[19:55:48] [INFO]   |  |-- generation_type=chat-completion
[19:55:48] [INFO]   |  |-- max_parallel_requests=4
[19:55:48] [INFO]   |  |-- extra_body={'chat_template_kwargs': {'enable_thinking': False}}
[19:55:48] [INFO]   |  |-- temperature=1.00
[19:55:48] [INFO]   |  |-- top_p=0.95
[19:55:48] [INFO]   |  |-- max_tokens=2048
[19:55:48] [INFO] 📝 llm-text model config for column 'review_summary'
[19:55:48] [INFO]   |-- model: 'nvidia/nemotron-3.5-lightning-30b-a3b'
[19:55:48] [INFO]   |-- model alias: 'nemotron-lightning'
[19:55:48] [INFO]   |-- model provider: 'nvidia'
[19:55:48] [INFO]   |-- inference parameters:
[19:55:48] [INFO]   |  |-- generation_type=chat-completion
[19:55:48] [INFO]   |  |-- max_parallel_requests=4
[19:55:48] [INFO]   |  |-- extra_body={'chat_template_kwargs': {'enable_thinking': False}}
[19:55:48] [INFO]   |  |-- temperature=1.00
[19:55:48] [INFO]   |  |-- top_p=0.95
[19:55:48] [INFO]   |  |-- max_tokens=2048
[19:55:48] [INFO] 📝 llm-text model config for column 'action_items'
[19:55:48] [INFO]   |-- model: 'nvidia/nemotron-3.5-lightning-30b-a3b'
[19:55:48] [INFO]   |-- model alias: 'nemotron-lightning'
[19:55:48] [INFO]   |-- model provider: 'nvidia'
[19:55:48] [INFO]   |-- inference parameters:
[19:55:48] [INFO]   |  |-- generation_type=chat-completion
[19:55:48] [INFO]   |  |-- max_parallel_requests=4
[19:55:48] [INFO]   |  |-- extra_body={'chat_template_kwargs': {'enable_thinking': False}}
[19:55:48] [INFO]   |  |-- temperature=1.00
[19:55:48] [INFO]   |  |-- top_p=0.95
[19:55:48] [INFO]   |  |-- max_tokens=2048
[19:55:48] [INFO] ⚡️ Async generation: 5 column(s) (column 'product', column 'customer_review', column 'complaint_analysis', column 'review_summary', column 'action_items'), 50 tasks across 1 row group(s)
[19:55:48] [INFO] 🚀 (1/1) Dispatching with 10 records
[19:55:48] [INFO] 🎲 (1/1) Preparing samplers to generate 10 records across 5 columns
[19:55:48] [INFO] 🧩 (1/1) Generating column `customer_age` from expression
[19:55:48] [INFO] 🧩 (1/1) Generating column `customer_name` from expression
[19:55:53] [INFO] 📊 Progress [5.3s]:
[19:55:53] [INFO]   |-- 🌖 column 'product': 8/10 (80%) 1.5 rec/s
[19:55:53] [INFO]   |-- 🌑 column 'customer_review': 2/10 (20%) 0.4 rec/s
[19:55:53] [INFO]   |-- 😴 column 'complaint_analysis': 2/10 (20%) 0.4 rec/s, 2 skipped
[19:55:53] [INFO]   |-- 😴 column 'review_summary': 2/10 (20%) 0.4 rec/s
[19:55:53] [INFO]   |-- 😴 column 'action_items': 2/10 (20%) 0.4 rec/s, 2 skipped
[19:55:56] [INFO] Unspecified property removed from data object: product_name.
[19:55:56] [INFO] 1 unspecified properties removed from data object.
[19:55:59] [INFO] 📊 Progress [11.2s]:
[19:55:59] [INFO]   |-- 🌕 column 'product': 10/10 (100%) 0.9 rec/s
[19:55:59] [INFO]   |-- 🌗 column 'customer_review': 6/10 (60%) 0.5 rec/s
[19:55:59] [INFO]   |-- 😐 column 'complaint_analysis': 5/10 (50%) 0.4 rec/s, 5 skipped
[19:55:59] [INFO]   |-- 😐 column 'review_summary': 5/10 (50%) 0.4 rec/s
[19:55:59] [INFO]   |-- 😐 column 'action_items': 5/10 (50%) 0.4 rec/s, 5 skipped
[19:56:06] [INFO] 📊 Progress [18.2s]:
[19:56:06] [INFO]   |-- 🌕 column 'product': 10/10 (100%) 0.5 rec/s
[19:56:06] [INFO]   |-- 🌕 column 'customer_review': 10/10 (100%) 0.5 rec/s
[19:56:06] [INFO]   |-- 😊 column 'complaint_analysis': 9/10 (90%) 0.5 rec/s, 9 skipped
[19:56:06] [INFO]   |-- 😊 column 'review_summary': 9/10 (90%) 0.5 rec/s
[19:56:06] [INFO]   |-- 😊 column 'action_items': 9/10 (90%) 0.5 rec/s, 9 skipped
[19:56:07] [INFO] 🙈 Dropping columns: ['customer']
[19:56:07] [INFO] 📊 Progress [19.2s]:
[19:56:07] [INFO]   |-- 🌕 column 'product': 10/10 (100%) 0.5 rec/s
[19:56:07] [INFO]   |-- 🌕 column 'customer_review': 10/10 (100%) 0.5 rec/s
[19:56:07] [INFO]   |-- 🤩 column 'complaint_analysis': 10/10 (100%) 0.5 rec/s, 10 skipped
[19:56:07] [INFO]   |-- 🤩 column 'review_summary': 10/10 (100%) 0.5 rec/s
[19:56:07] [INFO]   |-- 🤩 column 'action_items': 10/10 (100%) 0.5 rec/s, 10 skipped
[19:56:07] [INFO] ✅ Async generation complete [19.2s]: 30 ok, 0 failed, 20 skipped across 5 column(s)
[19:56:08] [INFO] 📊 Model usage summary:
[19:56:08] [INFO]   |-- model: nvidia/nemotron-3.5-lightning-30b-a3b
[19:56:08] [INFO]   |-- tokens: input=9606, output=4196, reasoning=0, total=13802, tps=706
[19:56:08] [INFO]   |-- requests: success=31, failed=0, total=31, rpm=95
[19:56:08] [INFO] 📐 Measuring dataset column statistics:
[19:56:08] [INFO]   |-- 🎲 column: 'product_category'
[19:56:08] [INFO]   |-- 🎲 column: 'product_subcategory'
[19:56:08] [INFO]   |-- 🎲 column: 'target_age_range'
[19:56:08] [INFO]   |-- 🎲 column: 'review_style'
[19:56:08] [INFO]   |-- 🧩 column: 'customer_name'
[19:56:08] [INFO]   |-- 🧩 column: 'customer_age'
[19:56:08] [INFO]   |-- 🗂️ column: 'product'
[19:56:08] [INFO]   |-- 🗂️ column: 'customer_review'
[19:56:08] [INFO]   |-- 📝 column: 'complaint_analysis'
[19:56:08] [INFO]   |-- 📝 column: 'action_items'
[19:56:08] [INFO]   |-- 📝 column: 'review_summary'
Python
1# Load the generated dataset as a pandas DataFrame.
2dataset = results.load_dataset()
3 
4dataset.head()
5
Output
product_category product_subcategory target_age_range review_style customer_age customer_name product customer_review complaint_analysis action_items review_summary
0 Clothing Men's Clothing 65+ detailed 100 James Rodriguez {'name': 'Classic Soft-Care Flannel Shirt', 'd... {'rating': 5, 'customer_mood': 'happy', 'revie... None None The reviewer, a retired Pennsylvania construct...
1 Clothing Winter Coats 25-35 structured with bullet points 52 Tanya Martinez {'name': 'Urban Insulated Parka', 'description... {'rating': 5, 'customer_mood': 'happy', 'revie... None None The Urban Insulated Parka is a highly recommen...
2 Clothing Winter Coats 50-65 brief 112 Sherry Bird {'name': 'Premium Wool Blend Pea Coat', 'descr... {'rating': 4, 'customer_mood': 'happy', 'revie... None None A high-quality, warm, and versatile pea coat t...
3 Home & Kitchen Appliances 35-50 brief 46 Christina Bond {'name': 'Smart Digital Air Fryer', 'descripti... {'rating': 4, 'customer_mood': 'happy', 'revie... None None The Smart Digital Air Fryer delivers crispy, h...
4 Books Classics 35-50 brief 89 Theresa Gonzalez {'name': 'The Complete Hardcover Classics Coll... {'rating': 5, 'customer_mood': 'happy', 'revie... None None This exquisite collection of hardcover classic...
Python
1# Load the analysis results into memory.
2analysis = results.load_analysis()
3 
4analysis.to_report()
5
Output
──────────────────────────────────────── 🎨 Data Designer Dataset Profile ─────────────────────────────────────────

                                                                                                                   
                                                 Dataset Overview                                                  
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ number of records               ┃ number of columns               ┃ percent complete records                    ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩
│ 10                              │ 11                              │ 100.0%                                      │
└─────────────────────────────────┴─────────────────────────────────┴─────────────────────────────────────────────┘
                                                                                                                   
                                                                                                                   
                                                🎲 Sampler Columns                                                 
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━┓
┃ column name                      ┃        data type ┃               number unique values ┃         sampler type ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━┩
│ product_category                 │           string │                          5 (50.0%) │             category │
├──────────────────────────────────┼──────────────────┼────────────────────────────────────┼──────────────────────┤
│ product_subcategory              │           string │                          8 (80.0%) │          subcategory │
├──────────────────────────────────┼──────────────────┼────────────────────────────────────┼──────────────────────┤
│ target_age_range                 │           string │                          5 (50.0%) │             category │
├──────────────────────────────────┼──────────────────┼────────────────────────────────────┼──────────────────────┤
│ review_style                     │           string │                          4 (40.0%) │             category │
└──────────────────────────────────┴──────────────────┴────────────────────────────────────┴──────────────────────┘
                                                                                                                   
                                                                                                                   
                                                📝 LLM-Text Columns                                                
┏━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━┓
┃                         ┃              ┃                           ┃       prompt tokens ┃    completion tokens ┃
┃ column name             ┃    data type ┃      number unique values ┃          per record ┃           per record ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━┩
│ complaint_analysis      │         None │                  0 (0.0%) │     321.0 +/- 125.6 │          1.0 +/- 0.0 │
├─────────────────────────┼──────────────┼───────────────────────────┼─────────────────────┼──────────────────────┤
│ action_items            │         None │                  0 (0.0%) │        22.0 +/- 0.0 │          1.0 +/- 0.0 │
├─────────────────────────┼──────────────┼───────────────────────────┼─────────────────────┼──────────────────────┤
│ review_summary          │       string │               10 (100.0%) │     292.0 +/- 125.1 │        39.5 +/- 13.0 │
└─────────────────────────┴──────────────┴───────────────────────────┴─────────────────────┴──────────────────────┘
                                                                                                                   
                                                                                                                   
                                             🗂️ LLM-Structured Columns                                             
┏━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━┓
┃                      ┃               ┃                            ┃       prompt tokens ┃     completion tokens ┃
┃ column name          ┃     data type ┃       number unique values ┃          per record ┃            per record ┃
┡━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━┩
│ product              │          dict │                10 (100.0%) │       265.0 +/- 0.9 │        103.0 +/- 12.5 │
├──────────────────────┼───────────────┼────────────────────────────┼─────────────────────┼───────────────────────┤
│ customer_review      │          dict │                10 (100.0%) │      358.0 +/- 12.5 │       283.0 +/- 133.1 │
└──────────────────────┴───────────────┴────────────────────────────┴─────────────────────┴───────────────────────┘
                                                                                                                   
                                                                                                                   
                                               🧩 Expression Columns                                               
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ column name                       ┃                data type ┃                             number unique values ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩
│ customer_name                     │                   string │                                      10 (100.0%) │
├───────────────────────────────────┼──────────────────────────┼──────────────────────────────────────────────────┤
│ customer_age                      │                   string │                                      10 (100.0%) │
└───────────────────────────────────┴──────────────────────────┴──────────────────────────────────────────────────┘
                                                                                                                   
                                                                                                                   
╭────────────────────────────────────────────────── Table Notes ──────────────────────────────────────────────────╮
│                                                                                                                 │
│  1. All token statistics are based on a sample of max(1000, len(dataset)) records.                              │
│  2. Tokens are calculated using tiktoken's cl100k_base tokenizer.                                               │
│                                                                                                                 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
                                                                                                                   
───────────────────────────────────────────────────────────────────────────────────────────────────────────────────

⏭️ Next Steps

Check out the following notebook to learn more about: