data-designer 0.2.0__tar.gz → 0.2.2__tar.gz

{data_designer-0.2.0 → data_designer-0.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-designer
-Version: 0.2.0
+Version: 0.2.2
 Summary: General framework for synthetic data generation
 License-Expression: Apache-2.0
 License-File: LICENSE
@@ -15,36 +15,34 @@ Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Software Development
 Requires-Python: >=3.10
-Requires-Dist: anyascii<1.0,>=0.3.3
-Requires-Dist: datasets>=4.0.0
-Requires-Dist: duckdb==1.1.3
-Requires-Dist: faker==20.1.0
-Requires-Dist: httpx-retries>=0.4.2
-Requires-Dist: httpx>=0.27.2
-Requires-Dist: huggingface-hub>=0.34.4
+Requires-Dist: anyascii<1,>=0.3.3
+Requires-Dist: duckdb<2,>=1.1.3
+Requires-Dist: faker<21,>=20.1.0
+Requires-Dist: httpx-retries<1,>=0.4.2
+Requires-Dist: httpx<1,>=0.27.2
+Requires-Dist: huggingface-hub<2,>=1.0.1
 Requires-Dist: jinja2<4,>=3.1.6
-Requires-Dist: json-repair==0.48.0
-Requires-Dist: jsonpath-rust-bindings>=1.0
-Requires-Dist: litellm==1.73.6
-Requires-Dist: lxml>=6.0.2
-Requires-Dist: marko==2.1.2
-Requires-Dist: networkx==3.0
-Requires-Dist: numpy>=1.23.5
-Requires-Dist: pandas>=1.5.3
-Requires-Dist: prompt-toolkit>=3.0.0
-Requires-Dist: pyarrow>=19.0.1
-Requires-Dist: pydantic>=2.9.2
-Requires-Dist: pydantic[email]>=2.9.2
-Requires-Dist: pygments>=2.19.2
-Requires-Dist: python-json-logger==2.0.7
-Requires-Dist: pyyaml>=6.0.1
+Requires-Dist: json-repair<1,>=0.48.0
+Requires-Dist: jsonpath-rust-bindings<2,>=1.0
+Requires-Dist: litellm<2,>=1.73.6
+Requires-Dist: lxml<7,>=6.0.2
+Requires-Dist: marko<3,>=2.1.2
+Requires-Dist: networkx<4,>=3.0
+Requires-Dist: numpy<3,>=1.23.5
+Requires-Dist: pandas<3,>=2.3.3
+Requires-Dist: prompt-toolkit<4,>=3.0.0
+Requires-Dist: pyarrow<20,>=19.0.1
+Requires-Dist: pydantic[email]<3,>=2.9.2
+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>=13.7.1
-Requires-Dist: ruff==0.12.3
-Requires-Dist: scipy>=1.11.0
-Requires-Dist: sqlfluff==3.2.0
-Requires-Dist: tiktoken>=0.8.0
-Requires-Dist: typer>=0.12.0
+Requires-Dist: rich<14,>=13.7.1
+Requires-Dist: ruff<1,>=0.14.10
+Requires-Dist: scipy<2,>=1.11.0
+Requires-Dist: sqlfluff<4,>=3.2.0
+Requires-Dist: tiktoken<1,>=0.8.0
+Requires-Dist: typer<1,>=0.12.0
 Description-Content-Type: text/markdown
 
 # 🎨 NeMo Data Designer
@@ -166,6 +164,37 @@ data-designer config list      # View current settings
 
 ---
 
+## Telemetry
+
+Data Designer collects telemetry to help us improve the library for developers. We collect:
+
+* The names of models used
+* The count of input tokens
+* The count of output tokens
+
+**No user or device information is collected.** This data is not used to track any individual user behavior. It is used to see an aggregation of which models are the most popular for SDG. We will share this usage data with the community.
+
+Specifically, a model name that is defined a `ModelConfig` object, is what will be collected. In the below example config:
+
+```python
+ModelConfig(
+    alias="nv-reasoning",
+    model="openai/gpt-oss-20b",
+    provider="nvidia",
+    inference_parameters=InferenceParameters(
+        temperature=0.3,
+        top_p=0.9,
+        max_tokens=4096,
+    ),
+    )
+```
+
+The value `openai/gpt-oss-20b` would be collected.
+
+To disable telemetry capture, set `NEMO_TELEMETRY_ENABLED=false`.
+
+---
+
 ## License
 
 Apache License 2.0 – see [LICENSE](LICENSE) for details.

{data_designer-0.2.0 → data_designer-0.2.2}/README.md

@@ -117,6 +117,37 @@ data-designer config list      # View current settings
 
 ---
 
+## Telemetry
+
+Data Designer collects telemetry to help us improve the library for developers. We collect:
+
+* The names of models used
+* The count of input tokens
+* The count of output tokens
+
+**No user or device information is collected.** This data is not used to track any individual user behavior. It is used to see an aggregation of which models are the most popular for SDG. We will share this usage data with the community.
+
+Specifically, a model name that is defined a `ModelConfig` object, is what will be collected. In the below example config:
+
+```python
+ModelConfig(
+    alias="nv-reasoning",
+    model="openai/gpt-oss-20b",
+    provider="nvidia",
+    inference_parameters=InferenceParameters(
+        temperature=0.3,
+        top_p=0.9,
+        max_tokens=4096,
+    ),
+    )
+```
+
+The value `openai/gpt-oss-20b` would be collected.
+
+To disable telemetry capture, set `NEMO_TELEMETRY_ENABLED=false`.
+
+---
+
 ## License
 
 Apache License 2.0 – see [LICENSE](LICENSE) for details.

{data_designer-0.2.0 → data_designer-0.2.2}/docs/colab_notebooks/1-the-basics.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "9f804f90",
+   "id": "2e6331ad",
    "metadata": {},
    "source": [
     "# 🎨 Data Designer Tutorial: The Basics\n",
@@ -14,7 +14,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "9cb786eb",
+   "id": "af3aad47",
    "metadata": {},
    "source": [
     "### ⚡ Colab Setup\n",
@@ -25,7 +25,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "7f45ea56",
+   "id": "4c39e2a5",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -36,7 +36,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "ea86e81e",
+   "id": "d8652e5e",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -53,7 +53,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "16611c7b",
+   "id": "c51e6323",
    "metadata": {},
    "source": [
     "### 📦 Import the essentials\n",
@@ -64,7 +64,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "875342bb",
+   "id": "2de6b279",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -85,7 +85,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "b58ac676",
+   "id": "6a484a8d",
    "metadata": {},
    "source": [
     "### ⚙️ Initialize the Data Designer interface\n",
@@ -98,7 +98,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "3ce805ad",
+   "id": "7554bd1a",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -107,7 +107,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "50e961ed",
+   "id": "dc1d9f84",
    "metadata": {},
    "source": [
     "### 🎛️ Define model configurations\n",
@@ -124,7 +124,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "1b07a6a5",
+   "id": "76d22674",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -135,10 +135,7 @@
     "MODEL_ID = \"nvidia/nemotron-3-nano-30b-a3b\"\n",
     "\n",
     "# We choose this alias to be descriptive for our use case.\n",
-    "MODEL_ALIAS = \"nemotron-nano-v2\"\n",
-    "\n",
-    "# This sets reasoning to False for the nemotron-nano-v2 model.\n",
-    "SYSTEM_PROMPT = \"/no_think\"\n",
+    "MODEL_ALIAS = \"nemotron-nano-v3\"\n",
     "\n",
     "model_configs = [\n",
     "    ModelConfig(\n",
@@ -146,9 +143,10 @@
     "        model=MODEL_ID,\n",
     "        provider=MODEL_PROVIDER,\n",
     "        inference_parameters=ChatCompletionInferenceParams(\n",
-    "            temperature=0.5,\n",
+    "            temperature=1.0,\n",
     "            top_p=1.0,\n",
-    "            max_tokens=1024,\n",
+    "            max_tokens=2048,\n",
+    "            extra_body={\"chat_template_kwargs\": {\"enable_thinking\": False}},\n",
     "        ),\n",
     "    )\n",
     "]"
@@ -156,7 +154,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "6d873251",
+   "id": "187da050",
    "metadata": {},
    "source": [
     "### 🏗️ Initialize the Data Designer Config Builder\n",
@@ -171,7 +169,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "d45fac13",
+   "id": "977497d1",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -180,7 +178,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "c35b0274",
+   "id": "92c51ea0",
    "metadata": {},
    "source": [
     "## 🎲 Getting started with sampler columns\n",
@@ -197,7 +195,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "14cb9967",
+   "id": "68d7a4e6",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -206,7 +204,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "40945aea",
+   "id": "314c4719",
    "metadata": {},
    "source": [
     "Let's start designing our product review dataset by adding product category and subcategory columns.\n"
@@ -215,7 +213,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "a7d87e00",
+   "id": "1bcad060",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -296,7 +294,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "48699878",
+   "id": "aab7414d",
    "metadata": {},
    "source": [
     "Next, let's add samplers to generate data related to the customer and their review.\n"
@@ -305,7 +303,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "df84faf3",
+   "id": "f191f5bf",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -342,7 +340,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "8288352d",
+   "id": "5d893b3d",
    "metadata": {},
    "source": [
     "## 🦜 LLM-generated columns\n",
@@ -357,7 +355,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "157919b4",
+   "id": "2abadac9",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -370,7 +368,6 @@
     "            \"on products related to '{{ product_subcategory }}'. The target age range of the ideal customer is \"\n",
     "            \"{{ target_age_range }} years old. Respond with only the product name, no other text.\"\n",
     "        ),\n",
-    "        system_prompt=SYSTEM_PROMPT,\n",
     "        model_alias=MODEL_ALIAS,\n",
     "    )\n",
     ")\n",
@@ -382,9 +379,9 @@
     "            \"You are a customer named {{ customer.first_name }} from {{ customer.city }}, {{ customer.state }}. \"\n",
     "            \"You are {{ customer.age }} years old and recently purchased a product called {{ product_name }}. \"\n",
     "            \"Write a review of this product, which you gave a rating of {{ number_of_stars }} stars. \"\n",
-    "            \"The style of the review should be '{{ review_style }}'.\"\n",
+    "            \"The style of the review should be '{{ review_style }}'. \"\n",
+    "            \"Respond with only the review, no other text.\"\n",
     "        ),\n",
-    "        system_prompt=SYSTEM_PROMPT,\n",
     "        model_alias=MODEL_ALIAS,\n",
     "    )\n",
     ")\n",
@@ -394,7 +391,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "009646e4",
+   "id": "2c9cb423",
    "metadata": {},
    "source": [
     "### 🔁 Iteration is key – preview the dataset!\n",
@@ -411,7 +408,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "a9c90236",
+   "id": "71e3a022",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -421,7 +418,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "3cfe180e",
+   "id": "28f7913d",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -432,7 +429,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "65b2f595",
+   "id": "6621c80f",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -442,7 +439,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "2134fa0f",
+   "id": "2b451ded",
    "metadata": {},
    "source": [
     "### 📊 Analyze the generated data\n",
@@ -455,7 +452,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "8a37dd61",
+   "id": "0f7cb6cc",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -465,7 +462,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "b715bc3a",
+   "id": "721b3c7d",
    "metadata": {},
    "source": [
     "### 🆙 Scale up!\n",
@@ -478,17 +475,17 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "565f03a1",
+   "id": "1ad777d1",
    "metadata": {},
    "outputs": [],
    "source": [
-    "results = data_designer.create(config_builder, num_records=10)"
+    "results = data_designer.create(config_builder, num_records=10, dataset_name=\"tutorial-1\")"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "9d4c91ad",
+   "id": "df089509",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -501,7 +498,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "93c5a082",
+   "id": "e37fa65b",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -513,7 +510,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "13f7c942",
+   "id": "84d1802b",
    "metadata": {},
    "source": [
     "## ⏭️ Next Steps\n",