data-designer 0.2.2__tar.gz → 0.3.0__tar.gz

{data_designer-0.2.2 → data_designer-0.3.0}/.github/workflows/build-docs.yml

@@ -22,7 +22,7 @@ jobs:
         with:
           version: "0.9.5"
       - name: Set up Python
-        run: uv python install
+        run: uv python install 3.11
       - name: Install dependencies for docs
         run: uv sync --group docs
       - name: Download artifact from previous step

{data_designer-0.2.2 → data_designer-0.3.0}/Makefile

@@ -98,7 +98,7 @@ convert-execute-notebooks:
 
 generate-colab-notebooks:
 	@echo "📓 Generating Colab-compatible notebooks..."
-	uv run --group notebooks python docs/scripts/generate_colab_notebooks.py
+	uv run --group docs python docs/scripts/generate_colab_notebooks.py
 	@echo "✅ Colab notebooks created in docs/colab_notebooks/"
 
 serve-docs-locally:

{data_designer-0.2.2 → data_designer-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-designer
-Version: 0.2.2
+Version: 0.3.0
 Summary: General framework for synthetic data generation
 License-Expression: Apache-2.0
 License-File: LICENSE
@@ -24,7 +24,7 @@ Requires-Dist: huggingface-hub<2,>=1.0.1
 Requires-Dist: jinja2<4,>=3.1.6
 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: litellm<1.80.12,>=1.73.6
 Requires-Dist: lxml<7,>=6.0.2
 Requires-Dist: marko<3,>=2.1.2
 Requires-Dist: networkx<4,>=3.0
@@ -181,7 +181,7 @@ ModelConfig(
     alias="nv-reasoning",
     model="openai/gpt-oss-20b",
     provider="nvidia",
-    inference_parameters=InferenceParameters(
+    inference_parameters=ChatCompletionInferenceParams(
         temperature=0.3,
         top_p=0.9,
         max_tokens=4096,

{data_designer-0.2.2 → data_designer-0.3.0}/README.md

@@ -134,7 +134,7 @@ ModelConfig(
     alias="nv-reasoning",
     model="openai/gpt-oss-20b",
     provider="nvidia",
-    inference_parameters=InferenceParameters(
+    inference_parameters=ChatCompletionInferenceParams(
         temperature=0.3,
         top_p=0.9,
         max_tokens=4096,

{data_designer-0.2.2 → data_designer-0.3.0}/docs/code_reference/models.md

@@ -1,6 +1,6 @@
 # Models
 
-The `models` module defines configuration objects for model-based generation. [ModelProvider](#data_designer.config.models.ModelProvider), specifies connection and authentication details for custom providers. [ModelConfig](#data_designer.config.models.ModelConfig) encapsulates model details including the model alias, identifier, and inference parameters. [InferenceParameters](#data_designer.config.models.InferenceParameters) controls model behavior through settings like `temperature`, `top_p`, and `max_tokens`, with support for both fixed values and distribution-based sampling. The module includes [ImageContext](#data_designer.config.models.ImageContext) for providing image inputs to multimodal models.
+The `models` module defines configuration objects for model-based generation. [ModelProvider](#data_designer.config.models.ModelProvider), specifies connection and authentication details for custom providers. [ModelConfig](#data_designer.config.models.ModelConfig) encapsulates model details including the model alias, identifier, and inference parameters. [Inference Parameters](../concepts/models/inference-parameters.md) controls model behavior through settings like `temperature`, `top_p`, and `max_tokens`, with support for both fixed values and distribution-based sampling. The module includes [ImageContext](#data_designer.config.models.ImageContext) for providing image inputs to multimodal models.
 
 For more information on how they are used, see below:
 

{data_designer-0.2.2 → data_designer-0.3.0}/docs/colab_notebooks/1-the-basics.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "2e6331ad",
+   "id": "32827bda",
    "metadata": {},
    "source": [
     "# 🎨 Data Designer Tutorial: The Basics\n",
@@ -14,7 +14,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "af3aad47",
+   "id": "cbe6b81e",
    "metadata": {},
    "source": [
     "### ⚡ Colab Setup\n",
@@ -25,7 +25,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "4c39e2a5",
+   "id": "5b007eed",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -36,7 +36,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "d8652e5e",
+   "id": "58dfdb07",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -53,7 +53,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "c51e6323",
+   "id": "03d07dff",
    "metadata": {},
    "source": [
     "### 📦 Import the essentials\n",
@@ -64,7 +64,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "2de6b279",
+   "id": "749a1536",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -85,7 +85,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "6a484a8d",
+   "id": "5c31d723",
    "metadata": {},
    "source": [
     "### ⚙️ Initialize the Data Designer interface\n",
@@ -98,7 +98,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "7554bd1a",
+   "id": "826f2421",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -107,7 +107,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "dc1d9f84",
+   "id": "b6bfc01a",
    "metadata": {},
    "source": [
     "### 🎛️ Define model configurations\n",
@@ -124,7 +124,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "76d22674",
+   "id": "11aa0146",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -154,7 +154,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "187da050",
+   "id": "c10b93a6",
    "metadata": {},
    "source": [
     "### 🏗️ Initialize the Data Designer Config Builder\n",
@@ -169,7 +169,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "977497d1",
+   "id": "02ae97ca",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -178,7 +178,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "92c51ea0",
+   "id": "c4c780c8",
    "metadata": {},
    "source": [
     "## 🎲 Getting started with sampler columns\n",
@@ -195,7 +195,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "68d7a4e6",
+   "id": "685417ab",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -204,7 +204,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "314c4719",
+   "id": "6bae388c",
    "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": "1bcad060",
+   "id": "6122711b",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -289,12 +289,12 @@
     ")\n",
     "\n",
     "# Optionally validate that the columns are configured correctly.\n",
-    "config_builder.validate()"
+    "data_designer.validate(config_builder)"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "aab7414d",
+   "id": "12d8c063",
    "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": "f191f5bf",
+   "id": "c4c21fa0",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -340,7 +340,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "5d893b3d",
+   "id": "be6bd3c8",
    "metadata": {},
    "source": [
     "## 🦜 LLM-generated columns\n",
@@ -355,7 +355,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "2abadac9",
+   "id": "99e953d8",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -391,7 +391,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "2c9cb423",
+   "id": "ec30007b",
    "metadata": {},
    "source": [
     "### 🔁 Iteration is key – preview the dataset!\n",
@@ -408,7 +408,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "71e3a022",
+   "id": "7ac1f25b",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -418,7 +418,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "28f7913d",
+   "id": "67d8dff4",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -429,7 +429,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "6621c80f",
+   "id": "f78e4d9f",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -439,7 +439,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "2b451ded",
+   "id": "ee838ed6",
    "metadata": {},
    "source": [
     "### 📊 Analyze the generated data\n",
@@ -452,7 +452,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "0f7cb6cc",
+   "id": "4bea0fca",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -462,7 +462,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "721b3c7d",
+   "id": "da9875d4",
    "metadata": {},
    "source": [
     "### 🆙 Scale up!\n",
@@ -475,7 +475,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "1ad777d1",
+   "id": "8c7f20b4",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -485,7 +485,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "df089509",
+   "id": "2f5fdaa8",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -498,7 +498,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "e37fa65b",
+   "id": "5c2d935f",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -510,7 +510,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "84d1802b",
+   "id": "a80515b7",
    "metadata": {},
    "source": [
     "## ⏭️ Next Steps\n",

{data_designer-0.2.2 → data_designer-0.3.0}/docs/colab_notebooks/2-structured-outputs-and-jinja-expressions.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "fabaacf3",
+   "id": "ba3eb53c",
    "metadata": {},
    "source": [
     "# 🎨 Data Designer Tutorial: Structured Outputs and Jinja Expressions\n",
@@ -16,7 +16,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "9c43b45f",
+   "id": "71e3de28",
    "metadata": {},
    "source": [
     "### ⚡ Colab Setup\n",
@@ -27,7 +27,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "b8ec517f",
+   "id": "f12bda54",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -38,7 +38,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "9cda5d44",
+   "id": "c8e1f477",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -55,7 +55,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "5cd6ad06",
+   "id": "efc5ac26",
    "metadata": {},
    "source": [
     "### 📦 Import the essentials\n",
@@ -66,7 +66,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "3b68f1ed",
+   "id": "3ffd67ca",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -87,7 +87,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "2ccb4a3e",
+   "id": "782aaacd",
    "metadata": {},
    "source": [
     "### ⚙️ Initialize the Data Designer interface\n",
@@ -100,7 +100,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "bc9a754a",
+   "id": "1b092ccc",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -109,7 +109,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "4a1335a7",
+   "id": "cf4e19e2",
    "metadata": {},
    "source": [
     "### 🎛️ Define model configurations\n",
@@ -126,7 +126,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "6ae7a51e",
+   "id": "ff05156e",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -156,7 +156,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "891d5040",
+   "id": "bfbac905",
    "metadata": {},
    "source": [
     "### 🏗️ Initialize the Data Designer Config Builder\n",
@@ -171,7 +171,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "d3a95b64",
+   "id": "d2c7a5d7",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -180,7 +180,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "7d67b2b1",
+   "id": "6fb54697",
    "metadata": {},
    "source": [
     "### 🧑‍🎨 Designing our data\n",
@@ -207,7 +207,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "78fbeae4",
+   "id": "0ea9bb0f",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -235,7 +235,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "69463e64",
+   "id": "987fbf33",
    "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": "a5da9004",
+   "id": "9960d332",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -348,12 +348,12 @@
     ")\n",
     "\n",
     "# Optionally validate that the columns are configured correctly.\n",
-    "config_builder.validate()"
+    "data_designer.validate(config_builder)"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "63196378",
+   "id": "81f8d04a",
    "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": "36fe581f",
+   "id": "e9583bf7",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -423,7 +423,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "998e907e",
+   "id": "c79829f3",
    "metadata": {},
    "source": [
     "### 🔁 Iteration is key – preview the dataset!\n",
@@ -440,7 +440,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "d2ec151e",
+   "id": "cceb2346",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -450,7 +450,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "231e4b2d",
+   "id": "4c35a66e",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -461,7 +461,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "4e9b1ecd",
+   "id": "c5cd23a7",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -471,7 +471,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "47a8e374",
+   "id": "2486fc8b",
    "metadata": {},
    "source": [
     "### 📊 Analyze the generated data\n",
@@ -484,7 +484,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "1cb581f6",
+   "id": "ef90239f",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -494,7 +494,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "aff26604",
+   "id": "d9cbd2f6",
    "metadata": {},
    "source": [
     "### 🆙 Scale up!\n",
@@ -507,7 +507,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "2804c0bb",
+   "id": "f0dcf922",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -517,7 +517,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "e44d4940",
+   "id": "aac62046",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -530,7 +530,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "1da63b8c",
+   "id": "33875a50",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -542,7 +542,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "ec74a797",
+   "id": "4d532955",
    "metadata": {},
    "source": [
     "## ⏭️ Next Steps\n",