update

example.ipynb

@@ -0,0 +1,217 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/ubuntu/jsonllm/.venv/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Loading model and tokenizer...\n",
+      "Loaded model and tokenizer\n"
+     ]
+    }
+   ],
+   "source": [
+    "from transformers import AutoModelForCausalLM, AutoTokenizer\n",
+    "\n",
+    "print(\"Loading model and tokenizer...\")\n",
+    "model_name = \"databricks/dolly-v2-12b\"\n",
+    "model = AutoModelForCausalLM.from_pretrained(model_name, use_cache=True)\n",
+    "tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True, use_cache=True)\n",
+    "print(\"Loaded model and tokenizer\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Generating...\n",
+      "{\n",
+      "  temperature: \u001b[32m2.2225\u001b[0m,\n",
+      "  humidity: \u001b[32m1.0\u001b[0m,\n",
+      "  wind_speed: {\n",
+      "    value: \u001b[32m0.0\u001b[0m,\n",
+      "    unit: \u001b[32m\"value\"\u001b[0m\n",
+      "  }\n",
+      "}\n"
+     ]
+    }
+   ],
+   "source": [
+    "from jsonformer.format import highlight_values\n",
+    "from jsonformer.main import Jsonformer\n",
+    "\n",
+    "weather_schema = {\n",
+    "    \"type\": \"object\",\n",
+    "    \"properties\": {\n",
+    "        \"temperature\": {\"type\": \"number\"},\n",
+    "        \"humidity\": {\n",
+    "            \"type\": \"number\",\n",
+    "        },\n",
+    "        \"wind_speed\": {\n",
+    "            \"type\": \"object\",\n",
+    "            \"properties\": {\n",
+    "                \"value\": {\"type\": \"number\"},\n",
+    "                \"unit\": {\"type\": \"string\"},\n",
+    "            },\n",
+    "        },\n",
+    "    },\n",
+    "}\n",
+    "\n",
+    "builder = Jsonformer(\n",
+    "    model=model,\n",
+    "    tokenizer=tokenizer,\n",
+    "    json_schema=weather_schema,\n",
+    "    prompt=\"generate the weather\",\n",
+    ")\n",
+    "\n",
+    "print(\"Generating...\")\n",
+    "output = builder()\n",
+    "\n",
+    "highlight_values(output)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Generating...\n",
+      "{\n",
+      "  make: \u001b[32m\"Ford\"\u001b[0m,\n",
+      "  model: \u001b[32m\"Mustang\"\u001b[0m,\n",
+      "  year: \u001b[32m10.0\u001b[0m,\n",
+      "  colors: [\n",
+      "    \u001b[32m\"red\"\u001b[0m,\n",
+      "    \u001b[32m\"white\"\u001b[0m,\n",
+      "    \u001b[32m\"blue\"\u001b[0m,\n",
+      "    \u001b[32m\"black\"\u001b[0m,\n",
+      "    \u001b[32m\"yellow\"\u001b[0m,\n",
+      "    \u001b[32m\"orange\"\u001b[0m,\n",
+      "    \u001b[32m\"green\"\u001b[0m,\n",
+      "    \u001b[32m\"pink\"\u001b[0m,\n",
+      "    \u001b[32m\"purple\"\u001b[0m,\n",
+      "    \u001b[32m\"violet\"\u001b[0m\n",
+      "  ]\n",
+      "}\n"
+     ]
+    }
+   ],
+   "source": [
+    "car = {\n",
+    "    \"type\": \"object\",\n",
+    "    \"properties\": {\n",
+    "        \"make\": {\"type\": \"string\"},\n",
+    "        \"model\": {\"type\": \"string\"},\n",
+    "        \"year\": {\"type\": \"number\"},\n",
+    "        \"colors\": {\n",
+    "            \"type\": \"array\",\n",
+    "            \"items\": {\"type\": \"string\"},\n",
+    "        }\n",
+    "    },\n",
+    "}\n",
+    "\n",
+    "builder = Jsonformer(\n",
+    "    model=model,\n",
+    "    tokenizer=tokenizer,\n",
+    "    json_schema=car,\n",
+    "    prompt=\"generate an example car\",\n",
+    ")\n",
+    "\n",
+    "print(\"Generating...\")\n",
+    "output = builder()\n",
+    "\n",
+    "highlight_values(output)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{\n",
+      "  temperature: \u001b[32m24\u001b[0m,\n",
+      "  humidity: \u001b[32m48.0\u001b[0m,\n",
+      "  wind_speed: {\n",
+      "    value: \u001b[32m12\u001b[0m,\n",
+      "    unit: \u001b[32m\"mph\"\u001b[0m\n",
+      "  }\n",
+      "}\n"
+     ]
+    }
+   ],
+   "source": [
+    "test = {\n",
+    "  \"temperature\": 24,\n",
+    "  \"humidity\": 48.0,\n",
+    "  \"wind_speed\": {\n",
+    "    \"value\": 12,\n",
+    "    \"unit\": \"mph\"\n",
+    "  }\n",
+    "}\n",
+    "\n",
+    "highlight_values(test)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "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": "3.10.11"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}