data-designer 0.3.2__tar.gz → 0.3.3__tar.gz

data_designer-0.3.3/.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-0.3.3/.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-0.3.3/.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-0.3.3/.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-0.3.3}/.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-0.3.3}/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"
@@ -91,6 +95,33 @@ test-e2e:
 	@echo "🧪 Running e2e tests..."
 	uv run --no-cache --refresh --directory e2e_tests 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 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 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..."
 	@mkdir -p docs/notebooks
@@ -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-0.3.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-designer
-Version: 0.3.2
+Version: 0.3.3
 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

{data_designer-0.3.2 → data_designer-0.3.3}/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-0.3.3}/pyproject.toml

@@ -42,7 +42,7 @@ dependencies = [
   "python-json-logger>=3,<4",
   "pyyaml>=6.0.1,<7",
   "requests<3,>=2.32.2",
-  "rich>=13.7.1,<14",
+  "rich>=13.7.1,<15",
   "ruff>=0.14.10,<1",
   "scipy>=1.11.0,<2",
   "sqlfluff>=3.2.0,<4",

{data_designer-0.3.2 → data_designer-0.3.3}/src/data_designer/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.3.2'
-__version_tuple__ = version_tuple = (0, 3, 2)
+__version__ = version = '0.3.3'
+__version_tuple__ = version_tuple = (0, 3, 3)
 
 __commit_id__ = commit_id = None

{data_designer-0.3.2 → data_designer-0.3.3}/src/data_designer/engine/dataset_builders/utils/concurrency.py

@@ -108,6 +108,26 @@ class ConcurrentThreadExecutor:
         self._shutdown_window_size = shutdown_error_window
         self._results = ExecutorResults(failure_threshold=shutdown_error_rate)
 
+    @property
+    def results(self) -> ExecutorResults:
+        return self._results
+
+    @property
+    def max_workers(self) -> int:
+        return self._max_workers
+
+    @property
+    def shutdown_error_rate(self) -> float:
+        return self._shutdown_error_rate
+
+    @property
+    def shutdown_window_size(self) -> int:
+        return self._shutdown_window_size
+
+    @property
+    def semaphore(self) -> Semaphore:
+        return self._semaphore
+
     def __enter__(self) -> ConcurrentThreadExecutor:
         self._executor = ThreadPoolExecutor(
             max_workers=self._max_workers,
@@ -145,14 +165,16 @@ class ConcurrentThreadExecutor:
             self._raise_task_error()
 
         def _handle_future(future: Future) -> None:
-            self._results.completed_count += 1
             try:
                 result = future.result()
                 if self._result_callback is not None:
                     self._result_callback(result, context=context)
-                self._results.success_count += 1
+                with self._lock:
+                    self._results.completed_count += 1
+                    self._results.success_count += 1
             except Exception as err:
                 with self._lock:
+                    self._results.completed_count += 1
                     self._results.error_trap.handle_error(err)
                     if self._results.is_error_rate_exceeded(self._shutdown_window_size):
                         # Signal to shutdown early on the next submission (if received).

{data_designer-0.3.2 → data_designer-0.3.3}/tests/engine/dataset_builders/utils/test_concurrency.py

@@ -71,7 +71,7 @@ def test_executor_results_error_rate_exceeded(
 
 def test_concurrent_thread_executor_creation():
     executor = ConcurrentThreadExecutor(max_workers=2, column_name="test_column")
-    assert executor._max_workers == 2
+    assert executor.max_workers == 2
 
 
 @pytest.mark.parametrize(
@@ -129,7 +129,7 @@ def test_concurrent_thread_executor_early_shutdown_behavior(
             for _ in range(5):
                 executor.submit(failing_func)
             time.sleep(0.1)
-            assert executor._results.early_shutdown is False
+            assert executor.results.early_shutdown is False
 
 
 def test_concurrent_thread_executor_result_callback():
@@ -211,9 +211,9 @@ def test_concurrent_thread_executor_custom_shutdown_parameters():
         max_workers=2, column_name="test_column", shutdown_error_rate=0.3, shutdown_error_window=5
     )
 
-    assert executor._shutdown_error_rate == 0.3
-    assert executor._shutdown_window_size == 5
-    assert executor._results.failure_threshold == 0.3
+    assert executor.shutdown_error_rate == 0.3
+    assert executor.shutdown_window_size == 5
+    assert executor.results.failure_threshold == 0.3
 
 
 def test_context_variables_context_variable_propagation():
@@ -263,7 +263,7 @@ def test_edge_cases_zero_error_window():
             executor.submit(failing_func)
             time.sleep(0.1)  # Wait for task to complete
 
-            assert executor._results.completed_count == 1
+            assert executor.results.completed_count == 1
 
 
 def test_edge_cases_concurrent_submit_calls():
@@ -324,7 +324,7 @@ def test_edge_cases_semaphore_release_on_exception():
     executor = ConcurrentThreadExecutor(max_workers=1, column_name="test_column")
 
     with executor:
-        original_release = executor._semaphore.release
+        original_release = executor.semaphore.release
         release_count = 0
 
         def counting_release():
@@ -332,7 +332,7 @@ def test_edge_cases_semaphore_release_on_exception():
             release_count += 1
             original_release()
 
-        executor._semaphore.release = counting_release
+        executor.semaphore.release = counting_release
 
         def failing_func():
             raise ValueError("Test error")
@@ -364,3 +364,170 @@ def test_edge_cases_multiple_early_shutdown_attempts():
             time.sleep(0.1)  # Wait for tasks to complete
 
             executor.submit(failing_func)
+
+
+@pytest.mark.parametrize(
+    "shutdown_error_rate,num_errors,num_successes,expected_early_shutdown",
+    [
+        # Threshold 0%: Only succeeds when NO errors
+        (0.0, 0, 100, False),  # 0% errors, 0% threshold → No shutdown
+        # Threshold below error rate: Should NOT shutdown
+        (0.5, 40, 60, False),  # 40% errors, 50% threshold → No shutdown
+        (0.3, 20, 80, False),  # 20% errors, 30% threshold → No shutdown
+        # Threshold 100%: Only shuts down at exactly 100% errors
+        (1.0, 90, 10, False),  # 90% errors, 100% threshold → No shutdown
+        (1.0, 50, 50, False),  # 50% errors, 100% threshold → No shutdown
+    ],
+)
+def test_no_early_shutdown_when_below_threshold(
+    shutdown_error_rate: float, num_errors: int, num_successes: int, expected_early_shutdown: bool
+):
+    """Test that early shutdown does NOT occur when error rate is below or at threshold."""
+    total_tasks = num_errors + num_successes
+    executor = ConcurrentThreadExecutor(
+        max_workers=20,
+        column_name="test_column",
+        shutdown_error_rate=shutdown_error_rate,
+        shutdown_error_window=20,
+    )
+
+    with executor:
+
+        def success_task(x: int) -> int:
+            return x * 2
+
+        def error_task(x: int) -> None:
+            raise ValueError(f"Error {x}")
+
+        # Interleave tasks to maintain consistent error rate throughout execution
+        # Calculate how many tasks per error to distribute evenly
+        if num_errors > 0:
+            tasks_per_error = total_tasks / num_errors
+        else:
+            tasks_per_error = float("inf")
+
+        error_index = 0
+        success_index = 0
+        for i in range(total_tasks):
+            # Determine if this position should be an error based on even distribution
+            if num_errors > 0 and error_index < num_errors and i >= int(error_index * tasks_per_error):
+                executor.submit(error_task, error_index)
+                error_index += 1
+            elif success_index < num_successes:
+                executor.submit(success_task, success_index)
+                success_index += 1
+
+        time.sleep(0.5)  # Wait for all tasks to complete
+
+    # Verify no early shutdown occurred
+    assert executor.results.early_shutdown == expected_early_shutdown
+    assert executor.results.completed_count == total_tasks
+    assert executor.results.success_count == num_successes
+    assert executor.results.error_trap.error_count == num_errors
+
+
+@pytest.mark.parametrize(
+    "shutdown_error_rate,num_errors,num_successes,shutdown_window",
+    [
+        # Threshold 0%: ANY error triggers shutdown
+        (0.0, 10, 0, 10),  # 100% errors, 0% threshold → Shutdown
+        (0.0, 5, 5, 10),  # 50% errors, 0% threshold → Shutdown
+        # Threshold exceeded: Should shutdown
+        (0.5, 60, 40, 20),  # 60% errors, 50% threshold → Shutdown
+        (0.3, 40, 60, 20),  # 40% errors, 30% threshold → Shutdown
+        # Threshold 100%: Shuts down when ALL tasks fail
+        (1.0, 20, 0, 10),  # 100% errors, 100% threshold → Shutdown
+    ],
+)
+def test_early_shutdown_when_threshold_exceeded(
+    shutdown_error_rate: float, num_errors: int, num_successes: int, shutdown_window: int
+):
+    """Test that early shutdown DOES occur when error rate exceeds threshold."""
+    executor = ConcurrentThreadExecutor(
+        max_workers=10,
+        column_name="test_column",
+        shutdown_error_rate=shutdown_error_rate,
+        shutdown_error_window=shutdown_window,
+    )
+
+    with pytest.raises(DataDesignerRuntimeError, match="Data generation was terminated early"):
+        with executor:
+
+            def success_task(x: int) -> int:
+                return x * 2
+
+            def error_task(x: int) -> None:
+                raise ValueError(f"Error {x}")
+
+            # Interleave tasks to maintain the specified error rate
+            total_tasks = num_errors + num_successes
+
+            # Calculate how many tasks per error to distribute evenly
+            if num_errors > 0:
+                tasks_per_error = total_tasks / num_errors
+            else:
+                tasks_per_error = float("inf")
+
+            error_index = 0
+            success_index = 0
+            for i in range(total_tasks):
+                # Determine if this position should be an error based on even distribution
+                if num_errors > 0 and error_index < num_errors and i >= int(error_index * tasks_per_error):
+                    executor.submit(error_task, error_index)
+                    error_index += 1
+                elif success_index < num_successes:
+                    executor.submit(success_task, success_index)
+                    success_index += 1
+
+            time.sleep(0.3)
+
+            # Try to submit more tasks - should raise because early_shutdown is True
+            executor.submit(success_task, 999)
+
+
+def test_thread_safety_with_high_concurrency():
+    """Stress test to verify thread-safe counter updates under high concurrency."""
+    num_tasks = 500
+    max_workers = 20
+    results_list = []
+    errors_list = []
+
+    def result_callback(result: int, *, context: dict | None = None) -> None:
+        results_list.append(result)
+
+    def error_callback(exc: Exception, *, context: dict | None = None) -> None:
+        errors_list.append(exc)
+
+    with ConcurrentThreadExecutor(
+        max_workers=max_workers,
+        column_name="test_column",
+        result_callback=result_callback,
+        error_callback=error_callback,
+        shutdown_error_rate=0.9,  # High threshold to avoid shutdown
+        shutdown_error_window=50,
+    ) as executor:
+
+        def variable_task(x: int) -> int:
+            # Some tasks succeed, some fail, some take longer
+            if x % 7 == 0:
+                raise ValueError(f"Error {x}")
+            if x % 3 == 0:
+                time.sleep(0.001)
+            return x * 2
+
+        for i in range(num_tasks):
+            executor.submit(variable_task, i)
+
+        time.sleep(1.0)  # Wait for all tasks to complete
+
+    # Calculate expected counts
+    expected_errors = sum(1 for i in range(num_tasks) if i % 7 == 0)
+    expected_successes = num_tasks - expected_errors
+
+    # Verify all counts are accurate (no race conditions)
+    assert executor.results.completed_count == num_tasks
+    assert executor.results.success_count == expected_successes
+    assert executor.results.error_trap.error_count == expected_errors
+    assert len(results_list) == expected_successes
+    assert len(errors_list) == expected_errors
+    assert executor.results.early_shutdown is False

{data_designer-0.3.2 → data_designer-0.3.3}/uv.lock

@@ -1,5 +1,5 @@
 version = 1
-revision = 2
+revision = 3
 requires-python = ">=3.10"
 resolution-markers = [
     "python_full_version >= '3.14'",
@@ -763,7 +763,7 @@ requires-dist = [
     { name = "python-json-logger", specifier = ">=3,<4" },
     { name = "pyyaml", specifier = ">=6.0.1,<7" },
     { name = "requests", specifier = ">=2.32.2,<3" },
-    { name = "rich", specifier = ">=13.7.1,<14" },
+    { name = "rich", specifier = ">=14.0.0,<15" },
     { name = "ruff", specifier = ">=0.14.10,<1" },
     { name = "scipy", specifier = ">=1.11.0,<2" },
     { name = "sqlfluff", specifier = ">=3.2.0,<4" },
@@ -4216,16 +4216,15 @@ wheels = [
 
 [[package]]
 name = "rich"
-version = "13.9.4"
+version = "14.2.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "markdown-it-py" },
     { name = "pygments" },
-    { name = "typing-extensions", marker = "python_full_version < '3.11'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/ab/3a/0316b28d0761c6734d6bc14e770d85506c986c85ffb239e688eeaab2c2bc/rich-13.9.4.tar.gz", hash = "sha256:439594978a49a09530cff7ebc4b5c7103ef57baf48d5ea3184f21d9a2befa098", size = 223149, upload-time = "2024-11-01T16:43:57.873Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/fb/d2/8920e102050a0de7bfabeb4c4614a49248cf8d5d7a8d01885fbb24dc767a/rich-14.2.0.tar.gz", hash = "sha256:73ff50c7c0c1c77c8243079283f4edb376f0f6442433aecb8ce7e6d0b92d1fe4", size = 219990, upload-time = "2025-10-09T14:16:53.064Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/19/71/39c7c0d87f8d4e6c020a393182060eaefeeae6c01dab6a84ec346f2567df/rich-13.9.4-py3-none-any.whl", hash = "sha256:6049d5e6ec054bf2779ab3358186963bac2ea89175919d699e378b99738c2a90", size = 242424, upload-time = "2024-11-01T16:43:55.817Z" },
+    { url = "https://files.pythonhosted.org/packages/25/7a/b0178788f8dc6cafce37a212c99565fa1fe7872c70c6c9c1e1a372d9d88f/rich-14.2.0-py3-none-any.whl", hash = "sha256:76bc51fe2e57d2b1be1f96c524b890b816e334ab4c1e45888799bfaab0021edd", size = 243393, upload-time = "2025-10-09T14:16:51.245Z" },
 ]
 
 [[package]]