feat: add notebook example

.pre-commit-config.yaml

@@ -79,3 +79,7 @@ repos:
         args: [--fix]
       # Run the formatter.
       - id: ruff-format
+  - repo: https://github.com/kynan/nbstripout
+    rev: 0.5.0 # use the latest version
+    hooks:
+      - id: nbstripout

notebooks/demo.ipynb

@@ -0,0 +1,77 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pprint\n",
+    "import random"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llmdataparser import ParserRegistry\n",
+    "ParserRegistry.list_parsers()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mmlu_parser = ParserRegistry.get_parser('mmlu')\n",
+    "mmlu_parser.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mmlu_parser.parse(split_names=['dev', 'test'])\n",
+    "parsed_data = mmlu_parser.get_parsed_data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "index = random.randint(0, len(parsed_data))\n",
+    "print(f\"Question: \\n-------------------\\n {parsed_data[index].prompt}\")\n",
+    "print(\"-------------------\")\n",
+    "print(f\"Answer: \\n-------------------\\n{parsed_data[index].answer_letter}\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llmdata",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}