diff --git a/docs/colab_notebooks/1-the-basics.ipynb b/docs/colab_notebooks/1-the-basics.ipynb
index ee9e5ccc..eb9db753 100644
--- a/docs/colab_notebooks/1-the-basics.ipynb
+++ b/docs/colab_notebooks/1-the-basics.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "a4ac4d55",
+   "id": "39d7d274",
    "metadata": {},
    "source": [
     "# 🎨 Data Designer Tutorial: The Basics\n",
@@ -14,7 +14,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "9e9f3c47",
+   "id": "60f1d002",
    "metadata": {},
    "source": [
     "### ⚡ Colab Setup\n",
@@ -25,17 +25,18 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "41b31194",
+   "id": "99c42292",
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install -qU data-designer"
+    "%%capture\n",
+    "!pip install -U data-designer"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "502b3aba",
+   "id": "2c959ca9",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -52,7 +53,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "8c512fbc",
+   "id": "bc185897",
    "metadata": {},
    "source": [
     "### 📦 Import the essentials\n",
@@ -63,7 +64,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "8fae521f",
+   "id": "dc3a2d9d",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -84,20 +85,20 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e71d0256",
+   "id": "36c5f571",
    "metadata": {},
    "source": [
     "### ⚙️ Initialize the Data Designer interface\n",
     "\n",
     "- `DataDesigner` is the main object is responsible for managing the data generation process.\n",
     "\n",
-    "- When initialized without arguments, the [default model providers](https://nvidia-nemo.github.io/DataDesigner/concepts/models/default-model-settings/) are used.\n"
+    "- When initialized without arguments, the [default model providers](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/models/default-model-settings/) are used.\n"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "68fc7172",
+   "id": "61b23c70",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -106,7 +107,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "9a821a27",
+   "id": "3c9b7cb6",
    "metadata": {},
    "source": [
     "### 🎛️ Define model configurations\n",
@@ -115,7 +116,7 @@
     "\n",
     "- The \"model alias\" is used to reference the model in the Data Designer config (as we will see below).\n",
     "\n",
-    "- The \"model provider\" is the external service that hosts the model (see the [model config](https://nvidia-nemo.github.io/DataDesigner/concepts/models/default-model-settings/) docs for more details).\n",
+    "- The \"model provider\" is the external service that hosts the model (see the [model config](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/models/default-model-settings/) docs for more details).\n",
     "\n",
     "- By default, we use [build.nvidia.com](https://build.nvidia.com/models) as the model provider.\n"
    ]
@@ -123,7 +124,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "a9515141",
+   "id": "b86f6217",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -155,7 +156,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "3b940ab9",
+   "id": "1f089871",
    "metadata": {},
    "source": [
     "### 🏗️ Initialize the Data Designer Config Builder\n",
@@ -170,7 +171,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "ec21da7e",
+   "id": "3d666193",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -179,7 +180,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "85b2324e",
+   "id": "e88c8881",
    "metadata": {},
    "source": [
     "## 🎲 Getting started with sampler columns\n",
@@ -196,7 +197,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "f49f435e",
+   "id": "79fb85c6",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -205,7 +206,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "f582b642",
+   "id": "5106cc10",
    "metadata": {},
    "source": [
     "Let's start designing our product review dataset by adding product category and subcategory columns.\n"
@@ -214,7 +215,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "8cfc43b1",
+   "id": "22b97af1",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -295,7 +296,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "2d0eea21",
+   "id": "4857b085",
    "metadata": {},
    "source": [
     "Next, let's add samplers to generate data related to the customer and their review.\n"
@@ -304,7 +305,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "b5e65724",
+   "id": "9e90b3cb",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -341,7 +342,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e6788771",
+   "id": "b36a153b",
    "metadata": {},
    "source": [
     "## 🦜 LLM-generated columns\n",
@@ -356,7 +357,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "a2705cd9",
+   "id": "4da88fe6",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -393,7 +394,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e3dd2f69",
+   "id": "5f1b9ac8",
    "metadata": {},
    "source": [
     "### 🔁 Iteration is key – preview the dataset!\n",
@@ -410,7 +411,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "c6e43147",
+   "id": "543e2f9c",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -420,7 +421,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "fab77d01",
+   "id": "26136a8a",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -431,7 +432,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "875ee6a6",
+   "id": "aca4360d",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -441,7 +442,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "87b59e4b",
+   "id": "35ca0470",
    "metadata": {},
    "source": [
     "### 📊 Analyze the generated data\n",
@@ -454,7 +455,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "5d347f4c",
+   "id": "d55b402d",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -464,7 +465,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "d2fb84f2",
+   "id": "245b48cf",
    "metadata": {},
    "source": [
     "### 🆙 Scale up!\n",
@@ -477,7 +478,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "71a31e85",
+   "id": "fc803eb0",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -487,7 +488,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "501e9092",
+   "id": "881c2043",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -500,7 +501,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "6f217b4a",
+   "id": "d79860d4",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -512,16 +513,18 @@
   },
   {
    "cell_type": "markdown",
-   "id": "4da82b0f",
+   "id": "b4b45176",
    "metadata": {},
    "source": [
     "## ⏭️ Next Steps\n",
     "\n",
     "Now that you've seen the basics of Data Designer, check out the following notebooks to learn more about:\n",
     "\n",
-    "- [Structured outputs and jinja expressions](/notebooks/2-structured-outputs-and-jinja-expressions/)\n",
+    "- [Structured outputs and jinja expressions](https://nvidia-nemo.github.io/DataDesigner/latest/notebooks/2-structured-outputs-and-jinja-expressions/)\n",
     "\n",
-    "- [Seeding synthetic data generation with an external dataset](/notebooks/3-seeding-with-a-dataset/)\n"
+    "- [Seeding synthetic data generation with an external dataset](https://nvidia-nemo.github.io/DataDesigner/latest/notebooks/3-seeding-with-a-dataset/)\n",
+    "\n",
+    "- [Providing images as context](https://nvidia-nemo.github.io/DataDesigner/latest/notebooks/4-providing-images-as-context/)\n"
    ]
   }
  ],
diff --git a/docs/colab_notebooks/2-structured-outputs-and-jinja-expressions.ipynb b/docs/colab_notebooks/2-structured-outputs-and-jinja-expressions.ipynb
index 10156a10..0cb65da6 100644
--- a/docs/colab_notebooks/2-structured-outputs-and-jinja-expressions.ipynb
+++ b/docs/colab_notebooks/2-structured-outputs-and-jinja-expressions.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "a70798bc",
+   "id": "33b48b4e",
    "metadata": {},
    "source": [
     "# 🎨 Data Designer Tutorial: Structured Outputs and Jinja Expressions\n",
@@ -11,12 +11,12 @@
     "\n",
     "In this notebook, we will continue our exploration of Data Designer, demonstrating more advanced data generation using structured outputs and Jinja expressions.\n",
     "\n",
-    "If this is your first time using Data Designer, we recommend starting with the [first notebook](/notebooks/1-the-basics/) in this tutorial series.\n"
+    "If this is your first time using Data Designer, we recommend starting with the [first notebook](https://nvidia-nemo.github.io/DataDesigner/latest/notebooks/1-the-basics/) in this tutorial series.\n"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "4ed4c65d",
+   "id": "c29f9af1",
    "metadata": {},
    "source": [
     "### ⚡ Colab Setup\n",
@@ -27,17 +27,18 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "73432e8e",
+   "id": "3a5601fb",
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install -qU data-designer"
+    "%%capture\n",
+    "!pip install -U data-designer"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "1a6aac78",
+   "id": "de2f0af4",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -54,7 +55,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "03df6d1c",
+   "id": "400795be",
    "metadata": {},
    "source": [
     "### 📦 Import the essentials\n",
@@ -65,7 +66,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "befb6573",
+   "id": "378f6853",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -86,20 +87,20 @@
   },
   {
    "cell_type": "markdown",
-   "id": "a022d1ae",
+   "id": "15a1ac9f",
    "metadata": {},
    "source": [
     "### ⚙️ Initialize the Data Designer interface\n",
     "\n",
     "- `DataDesigner` is the main object that is used to interface with the library.\n",
     "\n",
-    "- When initialized without arguments, the [default model providers](https://nvidia-nemo.github.io/DataDesigner/concepts/models/default-model-settings/) are used.\n"
+    "- When initialized without arguments, the [default model providers](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/models/default-model-settings/) are used.\n"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "568e1d91",
+   "id": "9d7654e5",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -108,7 +109,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "de1ef709",
+   "id": "27ba0edb",
    "metadata": {},
    "source": [
     "### 🎛️ Define model configurations\n",
@@ -117,7 +118,7 @@
     "\n",
     "- The \"model alias\" is used to reference the model in the Data Designer config (as we will see below).\n",
     "\n",
-    "- The \"model provider\" is the external service that hosts the model (see the [model config](https://nvidia-nemo.github.io/DataDesigner/concepts/models/default-model-settings/) docs for more details).\n",
+    "- The \"model provider\" is the external service that hosts the model (see the [model config](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/models/default-model-settings/) docs for more details).\n",
     "\n",
     "- By default, we use [build.nvidia.com](https://build.nvidia.com/models) as the model provider.\n"
    ]
@@ -125,7 +126,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "6757f43c",
+   "id": "c24ee00e",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -157,7 +158,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "3d1ea9b6",
+   "id": "a106edc9",
    "metadata": {},
    "source": [
     "### 🏗️ Initialize the Data Designer Config Builder\n",
@@ -172,7 +173,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "f9ad410a",
+   "id": "3a167f7c",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -181,7 +182,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "8f918afa",
+   "id": "fcf68c72",
    "metadata": {},
    "source": [
     "### 🧑‍🎨 Designing our data\n",
@@ -208,7 +209,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "6aafd123",
+   "id": "8f8f034e",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -236,7 +237,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "9727c5ae",
+   "id": "9d5c722a",
    "metadata": {},
    "source": [
     "Next, let's design our product review dataset using a few more tricks compared to the previous notebook.\n"
@@ -245,7 +246,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "9f9df709",
+   "id": "013caa3d",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -354,7 +355,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "f42b7843",
+   "id": "ef426a65",
    "metadata": {},
    "source": [
     "Next, we will use more advanced Jinja expressions to create new columns.\n",
@@ -371,7 +372,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "d231f52e",
+   "id": "27abbd6d",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -425,7 +426,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "01dbf368",
+   "id": "18a8461e",
    "metadata": {},
    "source": [
     "### 🔁 Iteration is key – preview the dataset!\n",
@@ -442,7 +443,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "7d0389c6",
+   "id": "2f75eee6",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -452,7 +453,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "b312d760",
+   "id": "950c9596",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -463,7 +464,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "6252ae9a",
+   "id": "5c04ca5a",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -473,7 +474,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "ea32a75e",
+   "id": "b0704f47",
    "metadata": {},
    "source": [
     "### 📊 Analyze the generated data\n",
@@ -486,7 +487,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "c094a400",
+   "id": "54a609ce",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -496,7 +497,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "8565a283",
+   "id": "6ae0a8a5",
    "metadata": {},
    "source": [
     "### 🆙 Scale up!\n",
@@ -509,7 +510,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "d48a294c",
+   "id": "e22c387a",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -519,7 +520,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "96268be4",
+   "id": "9c6b36b3",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -532,7 +533,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "a2137aaf",
+   "id": "138ed487",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -544,14 +545,16 @@
   },
   {
    "cell_type": "markdown",
-   "id": "c43a66cc",
+   "id": "fde73253",
    "metadata": {},
    "source": [
     "## ⏭️ Next Steps\n",
     "\n",
     "Check out the following notebook to learn more about:\n",
     "\n",
-    "- [Seeding synthetic data generation with an external dataset](/notebooks/3-seeding-with-a-dataset/)\n"
+    "- [Seeding synthetic data generation with an external dataset](https://nvidia-nemo.github.io/DataDesigner/latest/notebooks/3-seeding-with-a-dataset/)\n",
+    "\n",
+    "- [Providing images as context](https://nvidia-nemo.github.io/DataDesigner/latest/notebooks/4-providing-images-as-context/)A\n"
    ]
   }
  ],
diff --git a/docs/colab_notebooks/3-seeding-with-a-dataset.ipynb b/docs/colab_notebooks/3-seeding-with-a-dataset.ipynb
index db5c9d27..e623ac8b 100644
--- a/docs/colab_notebooks/3-seeding-with-a-dataset.ipynb
+++ b/docs/colab_notebooks/3-seeding-with-a-dataset.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "c4c424f2",
+   "id": "5a6b2b3f",
    "metadata": {},
    "source": [
     "# 🎨 Data Designer Tutorial: Seeding Synthetic Data Generation with an External Dataset\n",
@@ -11,12 +11,12 @@
     "\n",
     "In this notebook, we will demonstrate how to seed synthetic data generation in Data Designer with an external dataset.\n",
     "\n",
-    "If this is your first time using Data Designer, we recommend starting with the [first notebook](/notebooks/1-the-basics/) in this tutorial series.\n"
+    "If this is your first time using Data Designer, we recommend starting with the [first notebook](https://nvidia-nemo.github.io/DataDesigner/latest/notebooks/1-the-basics/) in this tutorial series.\n"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "2ceb13f2",
+   "id": "137d8273",
    "metadata": {},
    "source": [
     "### ⚡ Colab Setup\n",
@@ -27,17 +27,18 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "ad4096cd",
+   "id": "f6ce3dc2",
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install -qU data-designer"
+    "%%capture\n",
+    "!pip install -U data-designer"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "21336bf3",
+   "id": "70d6ffc8",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -54,7 +55,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "db8fa976",
+   "id": "ce0313c9",
    "metadata": {},
    "source": [
     "### 📦 Import the essentials\n",
@@ -65,7 +66,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "c2e17b2b",
+   "id": "2aa2cdf1",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -80,20 +81,20 @@
   },
   {
    "cell_type": "markdown",
-   "id": "29c28647",
+   "id": "9769f392",
    "metadata": {},
    "source": [
     "### ⚙️ Initialize the Data Designer interface\n",
     "\n",
     "- `DataDesigner` is the main object is responsible for managing the data generation process.\n",
     "\n",
-    "- When initialized without arguments, the [default model providers](https://nvidia-nemo.github.io/DataDesigner/concepts/models/default-model-settings/) are used.\n"
+    "- When initialized without arguments, the [default model providers](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/models/default-model-settings/) are used.\n"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "cecf9242",
+   "id": "d79db916",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -102,7 +103,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "74eab801",
+   "id": "08dd3894",
    "metadata": {},
    "source": [
     "### 🎛️ Define model configurations\n",
@@ -111,7 +112,7 @@
     "\n",
     "- The \"model alias\" is used to reference the model in the Data Designer config (as we will see below).\n",
     "\n",
-    "- The \"model provider\" is the external service that hosts the model (see the [model config](https://nvidia-nemo.github.io/DataDesigner/concepts/models/default-model-settings/) docs for more details).\n",
+    "- The \"model provider\" is the external service that hosts the model (see the [model config](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/models/default-model-settings/) docs for more details).\n",
     "\n",
     "- By default, we use [build.nvidia.com](https://build.nvidia.com/models) as the model provider.\n"
    ]
@@ -119,7 +120,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "b31991e8",
+   "id": "3994368e",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -151,7 +152,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "006d1625",
+   "id": "5f12d6d2",
    "metadata": {},
    "source": [
     "### 🏗️ Initialize the Data Designer Config Builder\n",
@@ -166,7 +167,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "396a4ed5",
+   "id": "0f3d7640",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -175,7 +176,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "9860369b",
+   "id": "1f08df99",
    "metadata": {},
    "source": [
     "## 🏥 Prepare a seed dataset\n",
@@ -200,7 +201,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "65a2fa3c",
+   "id": "f265e74c",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -218,7 +219,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "ea11134a",
+   "id": "6bffa239",
    "metadata": {},
    "source": [
     "## 🎨 Designing our synthetic patient notes dataset\n",
@@ -235,7 +236,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "209af41c",
+   "id": "15e486a6",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -325,7 +326,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "32f43d20",
+   "id": "5cfe2edd",
    "metadata": {},
    "source": [
     "### 🔁 Iteration is key – preview the dataset!\n",
@@ -342,7 +343,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "402a1025",
+   "id": "d4a59576",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -352,7 +353,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "de294013",
+   "id": "1c5aedd4",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -363,7 +364,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "a38c360d",
+   "id": "d17df0a5",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -373,7 +374,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "4a385031",
+   "id": "3389a088",
    "metadata": {},
    "source": [
     "### 📊 Analyze the generated data\n",
@@ -386,7 +387,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "3531b1e4",
+   "id": "b0443498",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -396,7 +397,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "7fec6251",
+   "id": "0527a606",
    "metadata": {},
    "source": [
     "### 🆙 Scale up!\n",
@@ -409,7 +410,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "bace6acb",
+   "id": "2118b49e",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -419,7 +420,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "3eaafc74",
+   "id": "c4f9ad59",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -432,7 +433,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "473a0c89",
+   "id": "8517866d",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -444,12 +445,14 @@
   },
   {
    "cell_type": "markdown",
-   "id": "7408eef8",
+   "id": "b62dd069",
    "metadata": {},
    "source": [
     "## ⏭️ Next Steps\n",
     "\n",
-    "Use Data Designer to generate synthetic data for your specific use case!\n"
+    "Check out the following notebook to learn more about:\n",
+    "\n",
+    "- [Providing images as context](https://nvidia-nemo.github.io/DataDesigner/latest/notebooks/4-providing-images-as-context/)\n"
    ]
   }
  ],
diff --git a/docs/colab_notebooks/4-providing-images-as-context.ipynb b/docs/colab_notebooks/4-providing-images-as-context.ipynb
index bac63375..e48f2bde 100644
--- a/docs/colab_notebooks/4-providing-images-as-context.ipynb
+++ b/docs/colab_notebooks/4-providing-images-as-context.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "ebd062e8",
+   "id": "fc93d603",
    "metadata": {},
    "source": [
     "# 🎨 Data Designer Tutorial: Providing Images as Context for Vision-Based Data Generation"
@@ -10,7 +10,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "3ce5b7f7",
+   "id": "31146c45",
    "metadata": {},
    "source": [
     "#### 📚 What you'll learn\n",
@@ -20,12 +20,12 @@
     "- ✨ **Visual Document Processing**: Converting images to chat-ready format for model consumption\n",
     "- 🔍 **Vision-Language Generation**: Using vision models to generate detailed summaries from images\n",
     "\n",
-    "If this is your first time using Data Designer, we recommend starting with the [first notebook](/notebooks/1-the-basics/) in this tutorial series.\n"
+    "If this is your first time using Data Designer, we recommend starting with the [first notebook](https://nvidia-nemo.github.io/DataDesigner/latest/notebooks/1-the-basics/) in this tutorial series.\n"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "04d0bfd4",
+   "id": "b237af81",
    "metadata": {},
    "source": [
     "### ⚡ Colab Setup\n",
@@ -36,27 +36,18 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "661740a3",
+   "id": "00b316a6",
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install -qU data-designer"
+    "%%capture\n",
+    "!pip install -U data-designer pillow>=12.0.0"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "b9c4188b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!pip install -q pillow>=12.0.0"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "ddaeb938",
+   "id": "847a6f88",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -73,7 +64,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "c3aac5e8",
+   "id": "5a0e2a31",
    "metadata": {},
    "source": [
     "### 📦 Import the essentials\n",
@@ -84,7 +75,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "c8b905ee",
+   "id": "7ec632f1",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -115,20 +106,20 @@
   },
   {
    "cell_type": "markdown",
-   "id": "f508d655",
+   "id": "66efe0cc",
    "metadata": {},
    "source": [
     "### ⚙️ Initialize the Data Designer interface\n",
     "\n",
     "- `DataDesigner` is the main object is responsible for managing the data generation process.\n",
     "\n",
-    "- When initialized without arguments, the [default model providers](https://nvidia-nemo.github.io/DataDesigner/concepts/models/default-model-settings/) are used.\n"
+    "- When initialized without arguments, the [default model providers](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/models/default-model-settings/) are used.\n"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "f0607008",
+   "id": "e9059d31",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -137,7 +128,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "a0467d8c",
+   "id": "26d60e67",
    "metadata": {},
    "source": [
     "### 🎛️ Define model configurations\n",
@@ -146,7 +137,7 @@
     "\n",
     "- The \"model alias\" is used to reference the model in the Data Designer config (as we will see below).\n",
     "\n",
-    "- The \"model provider\" is the external service that hosts the model (see the [model config](https://nvidia-nemo.github.io/DataDesigner/concepts/models/default-model-settings/) docs for more details).\n",
+    "- The \"model provider\" is the external service that hosts the model (see the [model config](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/models/default-model-settings/) docs for more details).\n",
     "\n",
     "- By default, we use [build.nvidia.com](https://build.nvidia.com/models) as the model provider.\n"
    ]
@@ -154,7 +145,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "1e4d9a15",
+   "id": "e5b29b57",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -177,7 +168,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "6d66a8a6",
+   "id": "c7c68fce",
    "metadata": {},
    "source": [
     "### 🏗️ Initialize the Data Designer Config Builder\n",
@@ -192,7 +183,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "80ad9b04",
+   "id": "2ab84fb1",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -201,7 +192,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "75935c33",
+   "id": "bdc1fa29",
    "metadata": {},
    "source": [
     "### 🌱 Seed Dataset Creation\n",
@@ -218,7 +209,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "868e41af",
+   "id": "3baa7ba2",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -233,7 +224,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "5466e56f",
+   "id": "f3780aee",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -281,7 +272,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "bbca6568",
+   "id": "5c46877e",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -299,7 +290,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "5ce17e71",
+   "id": "4ca338da",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -309,7 +300,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "9c0faf28",
+   "id": "0cb41a37",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -323,7 +314,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "35bc8b77",
+   "id": "607bb265",
    "metadata": {
     "lines_to_next_cell": 2
    },
@@ -352,7 +343,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "16ac3f58",
+   "id": "984241b9",
    "metadata": {
     "lines_to_next_cell": 2
    },
@@ -360,7 +351,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "1d13a0e4",
+   "id": "eca1a5ea",
    "metadata": {},
    "source": [
     "### 🔁 Iteration is key – preview the dataset!\n",
@@ -377,7 +368,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "336af89f",
+   "id": "4d386a38",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -387,7 +378,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "5a57a536",
+   "id": "6209d609",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -398,7 +389,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "9e05b387",
+   "id": "5aedc7fd",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -408,7 +399,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "f69d543e",
+   "id": "fc339219",
    "metadata": {},
    "source": [
     "### 📊 Analyze the generated data\n",
@@ -421,7 +412,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "e3cb66a7",
+   "id": "87ccc372",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -431,7 +422,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "60815241",
+   "id": "c090f413",
    "metadata": {},
    "source": [
     "### 🔎 Visual Inspection\n",
@@ -442,7 +433,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "3c9dddf6",
+   "id": "1e1a054c",
    "metadata": {
     "lines_to_next_cell": 2
    },
@@ -466,7 +457,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "eb6e2469",
+   "id": "cab83636",
    "metadata": {},
    "source": [
     "### 🆙 Scale up!\n",
@@ -479,7 +470,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "d6a0ed1c",
+   "id": "7fa66a2e",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -489,7 +480,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "255b8f6f",
+   "id": "8f92b5be",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -502,7 +493,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "43b935b3",
+   "id": "d1bddcee",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -514,7 +505,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "a74f1121",
+   "id": "46f68f95",
    "metadata": {},
    "source": [
     "## ⏭️ Next Steps\n",
diff --git a/docs/notebook_source/1-the-basics.py b/docs/notebook_source/1-the-basics.py
index 1c3c200b..de890fb0 100644
--- a/docs/notebook_source/1-the-basics.py
+++ b/docs/notebook_source/1-the-basics.py
@@ -46,7 +46,7 @@
 #
 # - `DataDesigner` is the main object is responsible for managing the data generation process.
 #
-# - When initialized without arguments, the [default model providers](https://nvidia-nemo.github.io/DataDesigner/concepts/models/default-model-settings/) are used.
+# - When initialized without arguments, the [default model providers](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/models/default-model-settings/) are used.
 #
 
 # %%
@@ -59,7 +59,7 @@
 #
 # - The "model alias" is used to reference the model in the Data Designer config (as we will see below).
 #
-# - The "model provider" is the external service that hosts the model (see the [model config](https://nvidia-nemo.github.io/DataDesigner/concepts/models/default-model-settings/) docs for more details).
+# - The "model provider" is the external service that hosts the model (see the [model config](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/models/default-model-settings/) docs for more details).
 #
 # - By default, we use [build.nvidia.com](https://build.nvidia.com/models) as the model provider.
 #
@@ -336,7 +336,9 @@
 #
 # Now that you've seen the basics of Data Designer, check out the following notebooks to learn more about:
 #
-# - [Structured outputs and jinja expressions](/notebooks/2-structured-outputs-and-jinja-expressions/)
+# - [Structured outputs and jinja expressions](https://nvidia-nemo.github.io/DataDesigner/latest/notebooks/2-structured-outputs-and-jinja-expressions/)
 #
-# - [Seeding synthetic data generation with an external dataset](/notebooks/3-seeding-with-a-dataset/)
+# - [Seeding synthetic data generation with an external dataset](https://nvidia-nemo.github.io/DataDesigner/latest/notebooks/3-seeding-with-a-dataset/)
+#
+# - [Providing images as context](https://nvidia-nemo.github.io/DataDesigner/latest/notebooks/4-providing-images-as-context/)
 #
diff --git a/docs/notebook_source/2-structured-outputs-and-jinja-expressions.py b/docs/notebook_source/2-structured-outputs-and-jinja-expressions.py
index e099cd82..f968a416 100644
--- a/docs/notebook_source/2-structured-outputs-and-jinja-expressions.py
+++ b/docs/notebook_source/2-structured-outputs-and-jinja-expressions.py
@@ -19,7 +19,7 @@
 #
 # In this notebook, we will continue our exploration of Data Designer, demonstrating more advanced data generation using structured outputs and Jinja expressions.
 #
-# If this is your first time using Data Designer, we recommend starting with the [first notebook](/notebooks/1-the-basics/) in this tutorial series.
+# If this is your first time using Data Designer, we recommend starting with the [first notebook](https://nvidia-nemo.github.io/DataDesigner/latest/notebooks/1-the-basics/) in this tutorial series.
 #
 
 # %% [markdown]
@@ -48,7 +48,7 @@
 #
 # - `DataDesigner` is the main object that is used to interface with the library.
 #
-# - When initialized without arguments, the [default model providers](https://nvidia-nemo.github.io/DataDesigner/concepts/models/default-model-settings/) are used.
+# - When initialized without arguments, the [default model providers](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/models/default-model-settings/) are used.
 #
 
 # %%
@@ -61,7 +61,7 @@
 #
 # - The "model alias" is used to reference the model in the Data Designer config (as we will see below).
 #
-# - The "model provider" is the external service that hosts the model (see the [model config](https://nvidia-nemo.github.io/DataDesigner/concepts/models/default-model-settings/) docs for more details).
+# - The "model provider" is the external service that hosts the model (see the [model config](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/models/default-model-settings/) docs for more details).
 #
 # - By default, we use [build.nvidia.com](https://build.nvidia.com/models) as the model provider.
 #
@@ -380,5 +380,7 @@ class ProductReview(BaseModel):
 #
 # Check out the following notebook to learn more about:
 #
-# - [Seeding synthetic data generation with an external dataset](/notebooks/3-seeding-with-a-dataset/)
+# - [Seeding synthetic data generation with an external dataset](https://nvidia-nemo.github.io/DataDesigner/latest/notebooks/3-seeding-with-a-dataset/)
+#
+# - [Providing images as context](https://nvidia-nemo.github.io/DataDesigner/latest/notebooks/4-providing-images-as-context/)A
 #
diff --git a/docs/notebook_source/3-seeding-with-a-dataset.py b/docs/notebook_source/3-seeding-with-a-dataset.py
index cdd1f744..7c0d07e1 100644
--- a/docs/notebook_source/3-seeding-with-a-dataset.py
+++ b/docs/notebook_source/3-seeding-with-a-dataset.py
@@ -19,7 +19,7 @@
 #
 # In this notebook, we will demonstrate how to seed synthetic data generation in Data Designer with an external dataset.
 #
-# If this is your first time using Data Designer, we recommend starting with the [first notebook](/notebooks/1-the-basics/) in this tutorial series.
+# If this is your first time using Data Designer, we recommend starting with the [first notebook](https://nvidia-nemo.github.io/DataDesigner/latest/notebooks/1-the-basics/) in this tutorial series.
 #
 
 # %% [markdown]
@@ -42,7 +42,7 @@
 #
 # - `DataDesigner` is the main object is responsible for managing the data generation process.
 #
-# - When initialized without arguments, the [default model providers](https://nvidia-nemo.github.io/DataDesigner/concepts/models/default-model-settings/) are used.
+# - When initialized without arguments, the [default model providers](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/models/default-model-settings/) are used.
 #
 
 # %%
@@ -55,7 +55,7 @@
 #
 # - The "model alias" is used to reference the model in the Data Designer config (as we will see below).
 #
-# - The "model provider" is the external service that hosts the model (see the [model config](https://nvidia-nemo.github.io/DataDesigner/concepts/models/default-model-settings/) docs for more details).
+# - The "model provider" is the external service that hosts the model (see the [model config](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/models/default-model-settings/) docs for more details).
 #
 # - By default, we use [build.nvidia.com](https://build.nvidia.com/models) as the model provider.
 #
@@ -288,5 +288,7 @@
 # %% [markdown]
 # ## ⏭️ Next Steps
 #
-# Use Data Designer to generate synthetic data for your specific use case!
+# Check out the following notebook to learn more about:
+#
+# - [Providing images as context](https://nvidia-nemo.github.io/DataDesigner/latest/notebooks/4-providing-images-as-context/)
 #
diff --git a/docs/notebook_source/4-providing-images-as-context.py b/docs/notebook_source/4-providing-images-as-context.py
index dc2513cd..6265e01f 100644
--- a/docs/notebook_source/4-providing-images-as-context.py
+++ b/docs/notebook_source/4-providing-images-as-context.py
@@ -23,7 +23,7 @@
 # - ✨ **Visual Document Processing**: Converting images to chat-ready format for model consumption
 # - 🔍 **Vision-Language Generation**: Using vision models to generate detailed summaries from images
 #
-# If this is your first time using Data Designer, we recommend starting with the [first notebook](/notebooks/1-the-basics/) in this tutorial series.
+# If this is your first time using Data Designer, we recommend starting with the [first notebook](https://nvidia-nemo.github.io/DataDesigner/latest/notebooks/1-the-basics/) in this tutorial series.
 #
 
 # %% [markdown]
@@ -62,7 +62,7 @@
 #
 # - `DataDesigner` is the main object is responsible for managing the data generation process.
 #
-# - When initialized without arguments, the [default model providers](https://nvidia-nemo.github.io/DataDesigner/concepts/models/default-model-settings/) are used.
+# - When initialized without arguments, the [default model providers](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/models/default-model-settings/) are used.
 #
 
 # %%
@@ -75,7 +75,7 @@
 #
 # - The "model alias" is used to reference the model in the Data Designer config (as we will see below).
 #
-# - The "model provider" is the external service that hosts the model (see the [model config](https://nvidia-nemo.github.io/DataDesigner/concepts/models/default-model-settings/) docs for more details).
+# - The "model provider" is the external service that hosts the model (see the [model config](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/models/default-model-settings/) docs for more details).
 #
 # - By default, we use [build.nvidia.com](https://build.nvidia.com/models) as the model provider.
 #
diff --git a/docs/scripts/generate_colab_notebooks.py b/docs/scripts/generate_colab_notebooks.py
index cb375776..446b0807 100644
--- a/docs/scripts/generate_colab_notebooks.py
+++ b/docs/scripts/generate_colab_notebooks.py
@@ -28,10 +28,8 @@
 }
 
 COLAB_INSTALL_CELL = """\
-!pip install -qU data-designer"""
-
-COLAB_DEPENDENCIES_CELL = """\
-!pip install -q {deps}"""
+%%capture
+!pip install -U data-designer"""
 
 COLAB_API_KEY_CELL = """\
 import getpass
@@ -49,9 +47,12 @@ def create_colab_setup_cells(additional_dependencies: str) -> list[NotebookNode]
     """Create the Colab-specific setup cells to inject before imports."""
     cells = []
     cells += [new_markdown_cell(source=COLAB_SETUP_MARKDOWN)]
-    cells += [new_code_cell(source=COLAB_INSTALL_CELL)]
+
+    install_cell = COLAB_INSTALL_CELL
     if additional_dependencies:
-        cells += [new_code_cell(source=COLAB_DEPENDENCIES_CELL.format(deps=additional_dependencies))]
+        install_cell += f" {additional_dependencies}"
+    cells += [new_code_cell(source=install_cell)]
+
     cells += [new_code_cell(source=COLAB_API_KEY_CELL)]
     return cells