data-designer 0.3.3__tar.gz → 0.3.4__tar.gz

{data_designer-0.3.3 → 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-0.3.3 → data_designer-0.3.4}/Makefile

@@ -67,22 +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:
@@ -91,9 +91,9 @@ 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..."
@@ -101,7 +101,7 @@ test-run-tutorials:
 	trap "rm -rf $$TUTORIAL_WORKDIR" EXIT; \
 	for f in docs/notebook_source/*.py; do \
 		echo "  📓 Running $$f..."; \
-		(cd "$$TUTORIAL_WORKDIR" && uv run python "$(REPO_PATH)/$$f") || exit 1; \
+		(cd "$$TUTORIAL_WORKDIR" && uv run --project "$(REPO_PATH)" --group notebooks python "$(REPO_PATH)/$$f") || exit 1; \
 	done; \
 	echo "🧹 Cleaning up tutorial artifacts..."; \
 	rm -rf "$$TUTORIAL_WORKDIR"; \
@@ -113,7 +113,7 @@ test-run-recipes:
 	trap "rm -rf $$RECIPE_WORKDIR" EXIT; \
 	for f in docs/assets/recipes/**/*.py; do \
 		echo "  📜 Running $$f..."; \
-		(cd "$$RECIPE_WORKDIR" && uv run python "$(REPO_PATH)/$$f" --model-alias nvidia-text --artifact-path "$$RECIPE_WORKDIR" --num-records 5) || exit 1; \
+		(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"; \

{data_designer-0.3.3 → data_designer-0.3.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-designer
-Version: 0.3.3
+Version: 0.3.4
 Summary: General framework for synthetic data generation
 License-Expression: Apache-2.0
 License-File: LICENSE
@@ -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-0.3.3 → 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-0.3.3 → 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",

{data_designer-0.3.3 → data_designer-0.3.4}/docs/colab_notebooks/2-structured-outputs-and-jinja-expressions.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "166f4a41",
+   "id": "079d58ee",
    "metadata": {},
    "source": [
     "# 🎨 Data Designer Tutorial: Structured Outputs and Jinja Expressions\n",
@@ -16,7 +16,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "00a139eb",
+   "id": "ecff521c",
    "metadata": {},
    "source": [
     "### ⚡ Colab Setup\n",
@@ -27,7 +27,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "a60a4a4e",
+   "id": "fd576d9d",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -38,7 +38,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "14fc001f",
+   "id": "ce54e602",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -55,7 +55,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "22c4fe6b",
+   "id": "1b105464",
    "metadata": {},
    "source": [
     "### 📦 Import the essentials\n",
@@ -66,7 +66,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "b2f8e13d",
+   "id": "961c83c0",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -87,7 +87,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e644b2a8",
+   "id": "953dbcc6",
    "metadata": {},
    "source": [
     "### ⚙️ Initialize the Data Designer interface\n",
@@ -100,7 +100,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "74b146e7",
+   "id": "72d80b48",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -109,7 +109,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "7471f914",
+   "id": "f15d6f2f",
    "metadata": {},
    "source": [
     "### 🎛️ Define model configurations\n",
@@ -126,7 +126,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "ea1fcee5",
+   "id": "d60c4f65",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -156,7 +156,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "53855c58",
+   "id": "63b77ae7",
    "metadata": {},
    "source": [
     "### 🏗️ Initialize the Data Designer Config Builder\n",
@@ -171,7 +171,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "74064875",
+   "id": "9b7c73e2",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -180,7 +180,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "808534e9",
+   "id": "754134fe",
    "metadata": {},
    "source": [
     "### 🧑‍🎨 Designing our data\n",
@@ -207,7 +207,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "26d84a29",
+   "id": "d8c02a86",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -235,7 +235,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "624111a6",
+   "id": "4f5a5a27",
    "metadata": {},
    "source": [
     "Next, let's design our product review dataset using a few more tricks compared to the previous notebook.\n"
@@ -244,7 +244,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "c63fbc58",
+   "id": "99db5612",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -353,7 +353,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "60832414",
+   "id": "f9d62fa0",
    "metadata": {},
    "source": [
     "Next, we will use more advanced Jinja expressions to create new columns.\n",
@@ -370,7 +370,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "0964aff9",
+   "id": "7c784693",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -423,7 +423,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "a818e85f",
+   "id": "710b9527",
    "metadata": {},
    "source": [
     "### 🔁 Iteration is key – preview the dataset!\n",
@@ -440,7 +440,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "4af25c1e",
+   "id": "1ff3b750",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -450,7 +450,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "2594a896",
+   "id": "9086a983",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -461,7 +461,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "bfffec10",
+   "id": "cd9d7618",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -471,7 +471,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "54ce7f5d",
+   "id": "9324b008",
    "metadata": {},
    "source": [
     "### 📊 Analyze the generated data\n",
@@ -484,7 +484,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "841f74c7",
+   "id": "62240760",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -494,7 +494,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "14573ebb",
+   "id": "fb01f9be",
    "metadata": {},
    "source": [
     "### 🆙 Scale up!\n",
@@ -507,7 +507,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "49b43121",
+   "id": "9da730cf",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -517,7 +517,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "d74648e8",
+   "id": "5e356874",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -530,7 +530,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "c811b234",
+   "id": "71c7045c",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -542,7 +542,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "56509580",
+   "id": "f9ecce31",
    "metadata": {},
    "source": [
     "## ⏭️ Next Steps\n",