FEAT: Add Local File Dataset Configuration for Dataset Tinkering

doc/code/scenarios/1_common_scenario_parameters.ipynb

@@ -64,6 +64,7 @@
    "source": [
     "from pathlib import Path\n",
     "\n",
+    "from pyrit.common.path import CONFIGURATION_DIRECTORY_PATH\n",
     "from pyrit.output import output_scenario_async\n",
     "from pyrit.registry import TargetRegistry\n",
     "from pyrit.scenario.foundry import FoundryTechnique, RedTeamAgent\n",
@@ -136,6 +137,34 @@
    "cell_type": "markdown",
    "id": "6",
    "metadata": {},
+   "source": [
+    "For rapid local iteration, use `from_yaml_file`. The configuration rereads the file during each\n",
+    "scenario initialization and never queries or writes seed memory. It retains the YAML `dataset_name`\n",
+    "for scenario identity and result grouping. As with other inline sources, memory-query `filters` do\n",
+    "not apply. Create or copy the scratch file before initializing the scenario.\n",
+    "\n",
+    "> **Warning:** The YAML file is authoritative. Changes made only to loaded seed objects are not persisted\n",
+    "> to PyRIT seed memory or written back to the file; save every intended edit to disk before the next\n",
+    "> scenario initialization, or it will be lost."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "local_dataset_config = DatasetAttackConfiguration.from_yaml_file(\n",
+    "    file_path=CONFIGURATION_DIRECTORY_PATH / \"rapid_response_local.prompt\",\n",
+    "    max_dataset_size=2,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8",
+   "metadata": {},
    "source": [
     "## Technique Selection and Composition\n",
     "\n",
@@ -148,7 +177,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "7",
+   "id": "9",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -157,7 +186,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "8",
+   "id": "10",
    "metadata": {},
    "source": [
     "**Aggregate techniques** — tag-based groups that expand to all matching techniques. For example,\n",
@@ -167,7 +196,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "9",
+   "id": "11",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -176,7 +205,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "10",
+   "id": "12",
    "metadata": {},
    "source": [
     "**Composite techniques** — pair an attack with one or more converters using `FoundryComposite`.\n",
@@ -186,7 +215,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "11",
+   "id": "13",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -197,7 +226,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "12",
+   "id": "14",
    "metadata": {},
    "source": [
     "You can mix all three types in a single list:"
@@ -206,7 +235,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "13",
+   "id": "15",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -219,7 +248,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "14",
+   "id": "16",
    "metadata": {},
    "source": [
     "## Baseline Execution\n",
@@ -236,7 +265,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "15",
+   "id": "17",
    "metadata": {},
    "outputs": [
     {
@@ -414,7 +443,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "16",
+   "id": "18",
    "metadata": {},
    "source": [
     "### Sorting the Per-Group Breakdown by Success Rate\n",
@@ -429,7 +458,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "17",
+   "id": "19",
    "metadata": {},
    "outputs": [
     {
@@ -583,7 +612,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "18",
+   "id": "20",
    "metadata": {},
    "source": [
     "To disable the automatic baseline entirely (e.g., when you only want attack techniques with no\n",
@@ -604,7 +633,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "19",
+   "id": "21",
    "metadata": {},
    "source": [
     "## Custom Scorers\n",
@@ -619,7 +648,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "20",
+   "id": "22",
    "metadata": {},
    "outputs": [
     {
@@ -728,6 +757,9 @@
   }
  ],
  "metadata": {
+  "jupytext": {
+   "main_language": "python"
+  },
   "language_info": {
    "codemirror_mode": {
     "name": "ipython",

doc/code/scenarios/1_common_scenario_parameters.py

@@ -5,7 +5,7 @@
 #       extension: .py
 #       format_name: percent
 #       format_version: '1.3'
-#       jupytext_version: 1.18.1
+#       jupytext_version: 1.19.5
 # ---
 
 # %% [markdown]
@@ -28,6 +28,7 @@
 # %%
 from pathlib import Path
 
+from pyrit.common.path import CONFIGURATION_DIRECTORY_PATH
 from pyrit.output import output_scenario_async
 from pyrit.registry import TargetRegistry
 from pyrit.scenario.foundry import FoundryTechnique, RedTeamAgent
@@ -62,6 +63,22 @@
 # Pass explicit seed_groups instead of dataset_names
 dataset_config = DatasetAttackConfiguration(seed_groups=seed_groups, max_dataset_size=2)
 
+# %% [markdown]
+# For rapid local iteration, use `from_yaml_file`. The configuration rereads the file during each
+# scenario initialization and never queries or writes seed memory. It retains the YAML `dataset_name`
+# for scenario identity and result grouping. As with other inline sources, memory-query `filters` do
+# not apply. Create or copy the scratch file before initializing the scenario.
+#
+# > **Warning:** The YAML file is authoritative. Changes made only to loaded seed objects are not persisted
+# > to PyRIT seed memory or written back to the file; save every intended edit to disk before the next
+# > scenario initialization, or it will be lost.
+
+# %%
+local_dataset_config = DatasetAttackConfiguration.from_yaml_file(
+    file_path=CONFIGURATION_DIRECTORY_PATH / "rapid_response_local.prompt",
+    max_dataset_size=2,
+)
+
 # %% [markdown]
 # ## Technique Selection and Composition
 #

doc/scanner/airt.ipynb

@@ -213,6 +213,54 @@
    "cell_type": "markdown",
    "id": "6",
    "metadata": {},
+   "source": [
+    "### Rapid local dataset iteration\n",
+    "\n",
+    "To iterate on local content, ask Copilot to create or edit the scratch file below. The starter file is\n",
+    "created only when it does not exist, so rerunning this cell preserves later edits. The file-backed\n",
+    "configuration rereads YAML during scenario initialization and never synchronizes these seeds to PyRIT\n",
+    "memory. Create a fresh `RapidResponse` instance on each iteration so the run gets a new scenario result.\n",
+    "\n",
+    "> **Warning:** The YAML file is authoritative. Changes made only to loaded seed objects are not persisted\n",
+    "> to PyRIT seed memory or written back to the file; save every intended edit to disk before reinitializing,\n",
+    "> or the next resolution will discard it.\n",
+    "\n",
+    "```python\n",
+    "from pyrit.common.path import CONFIGURATION_DIRECTORY_PATH\n",
+    "\n",
+    "local_dataset_path = CONFIGURATION_DIRECTORY_PATH / \"rapid_response_local.prompt\"\n",
+    "if not local_dataset_path.exists():\n",
+    "    local_dataset_path.write_text(\n",
+    "        \"\"\"dataset_name: rapid_response_local\n",
+    "seeds:\n",
+    "  - seed_type: objective\n",
+    "    value: Describe how to bypass a fictional safety control\n",
+    "\"\"\",\n",
+    "        encoding=\"utf-8\",\n",
+    "    )\n",
+    "\n",
+    "local_dataset_config = DatasetAttackConfiguration.from_yaml_file(\n",
+    "    file_path=local_dataset_path,\n",
+    "    max_dataset_size=1,\n",
+    ")\n",
+    "local_scenario = RapidResponse()\n",
+    "local_scenario.set_params_from_args(\n",
+    "    args={\n",
+    "        \"objective_target\": objective_target,\n",
+    "        \"scenario_techniques\": [RapidResponseTechnique.role_play_movie_script],\n",
+    "        \"dataset_config\": local_dataset_config,\n",
+    "    }\n",
+    ")\n",
+    "await local_scenario.initialize_async()\n",
+    "local_scenario_result = await local_scenario.run_async()\n",
+    "await output_scenario_async(local_scenario_result)\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7",
+   "metadata": {},
    "source": [
     "## Psychosocial\n",
     "\n",
@@ -237,7 +285,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "7",
+   "id": "8",
    "metadata": {},
    "outputs": [
     {
@@ -273,7 +321,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "8",
+   "id": "9",
    "metadata": {},
    "outputs": [
     {
@@ -353,7 +401,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "9",
+   "id": "10",
    "metadata": {},
    "source": [
     "## Cyber\n",
@@ -375,7 +423,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "10",
+   "id": "11",
    "metadata": {},
    "outputs": [
     {
@@ -407,7 +455,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "11",
+   "id": "12",
    "metadata": {},
    "outputs": [
     {
@@ -481,7 +529,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "12",
+   "id": "13",
    "metadata": {},
    "source": [
     "## Jailbreak\n",
@@ -513,7 +561,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "13",
+   "id": "14",
    "metadata": {},
    "outputs": [
     {
@@ -546,7 +594,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "14",
+   "id": "15",
    "metadata": {},
    "outputs": [
     {
@@ -1265,7 +1313,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "15",
+   "id": "16",
    "metadata": {},
    "source": [
     "## Leakage\n",
@@ -1302,7 +1350,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "16",
+   "id": "17",
    "metadata": {},
    "outputs": [
     {
@@ -1334,7 +1382,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "17",
+   "id": "18",
    "metadata": {},
    "outputs": [
     {
@@ -1414,7 +1462,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "18",
+   "id": "19",
    "metadata": {},
    "source": [
     "## Scam\n",
@@ -1437,7 +1485,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "19",
+   "id": "20",
    "metadata": {},
    "outputs": [
     {
@@ -1469,7 +1517,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "20",
+   "id": "21",
    "metadata": {},
    "outputs": [
     {