data-designer 0.3.2__tar.gz → 0.3.4__tar.gz

data_designer-0.3.4/.github/ISSUE_TEMPLATE/bug-report.yml

@@ -0,0 +1,51 @@
+name: 🐛 Bug Report
+description: Report a bug
+labels: ["bug"]
+body:
+  - type: dropdown
+    id: priority
+    attributes:
+      label: Priority Level
+      description: How urgent is this issue?
+      default: 2
+      options:
+        - Critical (Total blocker)
+        - High (Major functionality broken)
+        - Medium (Annoying but has workaround)
+        - Low (Cosmetic / Minor)
+    validations:
+      required: true
+  - type: textarea
+    id: description
+    attributes:
+      label: Describe the bug
+      placeholder: A clear and concise description of what the bug is.
+    validations:
+      required: true
+  - type: textarea
+    id: reproduction
+    attributes:
+      label: Steps/Code to reproduce bug
+      description: |
+        Please list *minimal* steps or code snippet for us to be able to reproduce the bug.
+        A helpful guide on how to craft a minimal bug report: http://matthewrocklin.com/blog/work/2018/02/28/minimal-bug-reports
+      placeholder: |
+        Please include:
+          - Minimal code example that reproduces the issue
+          - Configuration used (if applicable)
+          - Commands run (if applicable)
+          - Error traceback
+    validations:
+      required: true
+  - type: textarea
+    id: expected
+    attributes:
+      label: Expected behavior
+      placeholder: A clear and concise description of what you expected to happen.
+    validations:
+      required: true
+  - type: textarea
+    id: context
+    attributes:
+      label: Additional context
+      placeholder: Add any other context about the problem here (e.g., screenshots, logs, browser version).

data_designer-0.3.4/.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,5 @@
+blank_issues_enabled: false
+contact_links:
+  - name: 💬 Ask a Question
+    url: https://github.com/NVIDIA-NeMo/DataDesigner/discussions
+    about: Please use GitHub Discussions for general questions.

data_designer-0.3.4/.github/ISSUE_TEMPLATE/development-task.yml

@@ -0,0 +1,32 @@
+name: 🛠️ Development Task
+description: Track internal development work, refactoring, or infrastructure
+labels: ["task"]
+body:
+  - type: dropdown
+    id: priority
+    attributes:
+      label: Priority Level
+      default: 1
+      options:
+        - High
+        - Medium
+        - Low
+    validations:
+      required: true
+  - type: textarea
+    id: summary
+    attributes:
+      label: Task Summary
+      placeholder: What is the core objective of this task?
+    validations:
+      required: true
+  - type: textarea
+    id: technical-details
+    attributes:
+      label: Technical Details & Implementation Plan
+      placeholder: Describe the technical approach, files affected, or logic changes.
+  - type: input
+    id: dependencies
+    attributes:
+      label: Dependencies
+      placeholder: "e.g., Blocked by issue #123"

data_designer-0.3.4/.github/ISSUE_TEMPLATE/feature-request.yml

@@ -0,0 +1,45 @@
+name: ✨ Feature Request
+description: Put in a request for a new feature
+labels: ["enhancement"]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Please use this form to suggest new features or improvements.
+  - type: dropdown
+    id: priority
+    attributes:
+      label: Priority Level
+      description: How important is this feature to your workflow?
+      default: 2
+      options:
+        - Critical (Essential for use)
+        - High (Major improvement)
+        - Medium (Nice to have)
+        - Low (Minor tweak)
+    validations:
+      required: true
+  - type: textarea
+    id: problem
+    attributes:
+      label: Is your feature request related to a problem? Please describe.
+      placeholder: A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
+    validations:
+      required: true
+  - type: textarea
+    id: solution
+    attributes:
+      label: Describe the solution you'd like
+      placeholder: A clear and concise description of what you want to happen.
+    validations:
+      required: true
+  - type: textarea
+    id: alternatives
+    attributes:
+      label: Describe alternatives you've considered
+      placeholder: A clear and concise description of any alternative solutions or features you've considered.
+  - type: textarea
+    id: context
+    attributes:
+      label: Additional context
+      placeholder: Add any other context or screenshots about the feature request here.

{data_designer-0.3.2 → data_designer-0.3.4}/.github/workflows/ci.yml

@@ -54,7 +54,7 @@ jobs:
         with:
           version: "latest"
           python-version: ${{ matrix.python-version }}
-          enable-cache: true
+          enable-cache: false
 
       - name: Run e2e tests
         run: |

{data_designer-0.3.2 → data_designer-0.3.4}/.gitignore

@@ -92,4 +92,4 @@ docs/notebook_source/*.ipynb
 docs/notebook_source/*.csv
 docs/**/artifacts/
 
-e2e_tests/uv.lock
+tests_e2e/uv.lock

{data_designer-0.3.2 → data_designer-0.3.4}/Makefile

@@ -22,6 +22,10 @@ help:
 	@echo "🧪 Testing:"
 	@echo "  test                      - Run all unit tests"
 	@echo "  coverage                  - Run tests with coverage report"
+	@echo "  test-e2e                  - Run e2e plugin tests"
+	@echo "  test-run-tutorials        - Run tutorial notebooks as e2e tests"
+	@echo "  test-run-recipes          - Run recipe scripts as e2e tests"
+	@echo "  test-run-all-examples     - Run all tutorials and recipes as e2e tests"
 	@echo ""
 	@echo "✨ Code Quality:"
 	@echo "  format                    - Format code with ruff"
@@ -63,22 +67,22 @@ check-all-fix: format lint-fix
 
 format:
 	@echo "📐 Formatting code with ruff..."
-	uv run ruff format src/ tests/ scripts/ e2e_tests/ --exclude '**/src/data_designer/_version.py'
+	uv run ruff format src/ tests/ scripts/ tests_e2e/ --exclude '**/src/data_designer/_version.py'
 	@echo "✅ Formatting complete!"
 
 format-check:
 	@echo "📐 Checking code formatting with ruff..."
-	uv run ruff format --check src/ tests/ scripts/ e2e_tests/ --exclude '**/src/data_designer/_version.py'
+	uv run ruff format --check src/ tests/ scripts/ tests_e2e/ --exclude '**/src/data_designer/_version.py'
 	@echo "✅ Formatting check complete! Run 'make format' to auto-fix issues."
 
 lint:
 	@echo "🔍 Linting code with ruff..."
-	uv run ruff check --output-format=full src/ tests/ scripts/ e2e_tests/ --exclude '**/src/data_designer/_version.py'
+	uv run ruff check --output-format=full src/ tests/ scripts/ tests_e2e/ --exclude '**/src/data_designer/_version.py'
 	@echo "✅ Linting complete! Run 'make lint-fix' to auto-fix issues."
 
 lint-fix:
 	@echo "🔍 Fixing linting issues with ruff..."
-	uv run ruff check --fix src/ tests/ scripts/ e2e_tests/ --exclude '**/src/data_designer/_version.py'
+	uv run ruff check --fix src/ tests/ scripts/ tests_e2e/ --exclude '**/src/data_designer/_version.py'
 	@echo "✅ Linting with autofix complete!"
 
 test:
@@ -87,9 +91,36 @@ test:
 
 test-e2e:
 	@echo "🧹 Cleaning e2e test environment..."
-	rm -rf e2e_tests/uv.lock e2e_tests/.pycache e2e_tests/.venv
+	rm -rf tests_e2e/uv.lock tests_e2e/.pycache tests_e2e/.venv
 	@echo "🧪 Running e2e tests..."
-	uv run --no-cache --refresh --directory e2e_tests pytest -s
+	uv run --no-cache --refresh --directory tests_e2e pytest -s
+
+test-run-tutorials:
+	@echo "🧪 Running tutorials as e2e tests..."
+	@TUTORIAL_WORKDIR=$$(mktemp -d); \
+	trap "rm -rf $$TUTORIAL_WORKDIR" EXIT; \
+	for f in docs/notebook_source/*.py; do \
+		echo "  📓 Running $$f..."; \
+		(cd "$$TUTORIAL_WORKDIR" && uv run --project "$(REPO_PATH)" --group notebooks python "$(REPO_PATH)/$$f") || exit 1; \
+	done; \
+	echo "🧹 Cleaning up tutorial artifacts..."; \
+	rm -rf "$$TUTORIAL_WORKDIR"; \
+	echo "✅ All tutorials completed successfully!"
+
+test-run-recipes:
+	@echo "🧪 Running recipes as e2e tests..."
+	@RECIPE_WORKDIR=$$(mktemp -d); \
+	trap "rm -rf $$RECIPE_WORKDIR" EXIT; \
+	for f in docs/assets/recipes/**/*.py; do \
+		echo "  📜 Running $$f..."; \
+		(cd "$$RECIPE_WORKDIR" && uv run --project "$(REPO_PATH)" --group notebooks python "$(REPO_PATH)/$$f" --model-alias nvidia-text --artifact-path "$$RECIPE_WORKDIR" --num-records 5) || exit 1; \
+	done; \
+	echo "🧹 Cleaning up recipe artifacts..."; \
+	rm -rf "$$RECIPE_WORKDIR"; \
+	echo "✅ All recipes completed successfully!"
+
+test-run-all-examples: test-run-tutorials test-run-recipes
+	@echo "✅ All examples (tutorials + recipes) completed successfully!"
 
 convert-execute-notebooks:
 	@echo "📓 Converting Python tutorials to notebooks and executing..."
@@ -137,4 +168,4 @@ install-dev-notebooks:
 	$(call install-pre-commit-hooks)
 	@echo "✅ Dev + notebooks installation complete!"
 
-.PHONY: clean coverage format format-check lint lint-fix test check-license-headers update-license-headers check-all check-all-fix install install-dev install-dev-notebooks generate-colab-notebooks
+.PHONY: clean coverage format format-check lint lint-fix test test-e2e test-run-tutorials test-run-recipes test-run-all-examples check-license-headers update-license-headers check-all check-all-fix install install-dev install-dev-notebooks generate-colab-notebooks

{data_designer-0.3.2 → data_designer-0.3.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-designer
-Version: 0.3.2
+Version: 0.3.4
 Summary: General framework for synthetic data generation
 License-Expression: Apache-2.0
 License-File: LICENSE
@@ -37,7 +37,7 @@ Requires-Dist: pygments<3,>=2.19.2
 Requires-Dist: python-json-logger<4,>=3
 Requires-Dist: pyyaml<7,>=6.0.1
 Requires-Dist: requests<3,>=2.32.2
-Requires-Dist: rich<14,>=13.7.1
+Requires-Dist: rich<15,>=13.7.1
 Requires-Dist: ruff<1,>=0.14.10
 Requires-Dist: scipy<2,>=1.11.0
 Requires-Dist: sqlfluff<4,>=3.2.0
@@ -193,6 +193,14 @@ The value `openai/gpt-oss-20b` would be collected.
 
 To disable telemetry capture, set `NEMO_TELEMETRY_ENABLED=false`.
 
+### Top Models
+
+This chart represents the breakdown of models used for Data Designer across all synthetic data generation jobs from 12/18/2025 to 1/14/2026. 
+
+![Top models used for synthetic data generation](docs/images/top-models.png)
+
+_Last updated on 1/14/2026_
+
 ---
 
 ## License

{data_designer-0.3.2 → data_designer-0.3.4}/README.md

@@ -146,6 +146,14 @@ The value `openai/gpt-oss-20b` would be collected.
 
 To disable telemetry capture, set `NEMO_TELEMETRY_ENABLED=false`.
 
+### Top Models
+
+This chart represents the breakdown of models used for Data Designer across all synthetic data generation jobs from 12/18/2025 to 1/14/2026. 
+
+![Top models used for synthetic data generation](docs/images/top-models.png)
+
+_Last updated on 1/14/2026_
+
 ---
 
 ## License

{data_designer-0.3.2 → data_designer-0.3.4}/docs/assets/recipes/qa_and_chat/product_info_qa.py

@@ -150,14 +150,14 @@ def build_config(model_alias: str) -> DataDesignerConfigBuilder:
     config_builder.add_column(
         ExpressionColumnConfig(
             name="completeness_result",
-            expr="{{ llm_answer_metrics.completeness.score }}",
+            expr="{{ llm_answer_metrics.Completeness.score }}",
         )
     )
 
     config_builder.add_column(
         ExpressionColumnConfig(
             name="accuracy_result",
-            expr="{{ llm_answer_metrics.accuracy.score }}",
+            expr="{{ llm_answer_metrics.Accuracy.score }}",
         )
     )
 

{data_designer-0.3.2 → data_designer-0.3.4}/docs/colab_notebooks/1-the-basics.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "adb0c3cd",
+   "id": "fcbfacc7",
    "metadata": {},
    "source": [
     "# 🎨 Data Designer Tutorial: The Basics\n",
@@ -14,7 +14,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "73d42bda",
+   "id": "e25b987d",
    "metadata": {},
    "source": [
     "### ⚡ Colab Setup\n",
@@ -25,7 +25,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "c6675487",
+   "id": "d8194911",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -36,7 +36,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "b98ebeee",
+   "id": "00ffb95b",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -53,7 +53,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "6e2355bb",
+   "id": "2c5c31e2",
    "metadata": {},
    "source": [
     "### 📦 Import the essentials\n",
@@ -64,7 +64,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "95bf5ae3",
+   "id": "a7a9489f",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -85,7 +85,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "ee906a92",
+   "id": "141b77e2",
    "metadata": {},
    "source": [
     "### ⚙️ Initialize the Data Designer interface\n",
@@ -98,7 +98,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "15b35cb8",
+   "id": "2bca9124",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -107,7 +107,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "999ce38a",
+   "id": "d4142887",
    "metadata": {},
    "source": [
     "### 🎛️ Define model configurations\n",
@@ -124,7 +124,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "f5ab65d5",
+   "id": "b3762937",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -154,7 +154,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "912d7954",
+   "id": "fec3a11f",
    "metadata": {},
    "source": [
     "### 🏗️ Initialize the Data Designer Config Builder\n",
@@ -169,7 +169,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "0ba83688",
+   "id": "5324dbec",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -178,7 +178,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "ee2de21d",
+   "id": "9acab1b8",
    "metadata": {},
    "source": [
     "## 🎲 Getting started with sampler columns\n",
@@ -195,7 +195,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "3009cfa5",
+   "id": "9916a82e",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -204,7 +204,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "c42c890f",
+   "id": "8452819f",
    "metadata": {},
    "source": [
     "Let's start designing our product review dataset by adding product category and subcategory columns.\n"
@@ -213,7 +213,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "16251687",
+   "id": "3c99a9fe",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -294,7 +294,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "ff41c919",
+   "id": "9028e845",
    "metadata": {},
    "source": [
     "Next, let's add samplers to generate data related to the customer and their review.\n"
@@ -303,7 +303,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "78ec15fc",
+   "id": "b64910fc",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -340,7 +340,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "8ac2131e",
+   "id": "3c56ff50",
    "metadata": {},
    "source": [
     "## 🦜 LLM-generated columns\n",
@@ -355,7 +355,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "d8232495",
+   "id": "db03dbae",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -391,7 +391,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "9105ddf2",
+   "id": "ee137104",
    "metadata": {},
    "source": [
     "### 🔁 Iteration is key – preview the dataset!\n",
@@ -408,7 +408,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "a6b02b74",
+   "id": "d318e88f",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -418,7 +418,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "74a4a386",
+   "id": "a6327bd4",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -429,7 +429,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "b1be4d95",
+   "id": "9d9f8ba0",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -439,7 +439,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "c2871df4",
+   "id": "5b1df1d7",
    "metadata": {},
    "source": [
     "### 📊 Analyze the generated data\n",
@@ -452,7 +452,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "b2beb476",
+   "id": "0c19da33",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -462,7 +462,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "765fb038",
+   "id": "0e35f0f5",
    "metadata": {},
    "source": [
     "### 🆙 Scale up!\n",
@@ -475,7 +475,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "f4fc625e",
+   "id": "07bdf600",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -485,7 +485,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "58989731",
+   "id": "27959f17",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -498,7 +498,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "80351a24",
+   "id": "953b6749",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -510,7 +510,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "cc79ae74",
+   "id": "471fb9a5",
    "metadata": {},
    "source": [
     "## ⏭️ Next Steps\n",