{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "e568e8cc",
   "metadata": {},
   "source": [
    "# Synthetic Data Generator\n",
    "\n",
    "Tool for generating sample synthetic data using a local Llama model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "4191b928",
   "metadata": {},
   "outputs": [],
   "source": [
    "# imports \n",
    "\n",
    "from openai import OpenAI\n",
    "import json\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "93d63879",
   "metadata": {},
   "outputs": [],
   "source": [
    "openai = OpenAI(base_url='http://localhost:11434/v1', api_key='ollama')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "0b9821dc",
   "metadata": {},
   "outputs": [],
   "source": [
    "# model\n",
    "\n",
    "MODEL = \"llama3.2\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "5fe77aa5",
   "metadata": {},
   "outputs": [],
   "source": [
    "def generate_synthetic_data(user_prompt = (\n",
    "      \"Generate 5 realistic customer reviews for a product. \"\n",
    "      \"The review should be 1-2 sentences long and contain a mix of positive and negative comments. \"\n",
    "      \"The review should be formatted as a JSON object with the following fields: \"\n",
    "      \"review: a string containing the review text\"\n",
    "    )):\n",
    "  \n",
    "  system_message = (\n",
    "    \"You are a helpful assistant that generates synthetic data.\"\n",
    "  )\n",
    "  response = openai.chat.completions.create(\n",
    "    model=MODEL,\n",
    "    messages=[\n",
    "      {\"role\": \"system\", \"content\": system_message},\n",
    "      {\"role\": \"user\", \"content\": user_prompt}\n",
    "    ],\n",
    "    response_format={\"type\": \"json_object\"}\n",
    "  )\n",
    "  result = json.loads(response.choices[0].message.content)\n",
    "  return result\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "047309d4",
   "metadata": {},
   "outputs": [],
   "source": [
    "result = generate_synthetic_data()\n",
    "\n",
    "formatted_json_result = json.dumps(result, indent=4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "07124b11",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{\n",
      "    \"review1\": \"I'm really impressed with how easy the setup was for this product! It only took me about 10 minutes to get everything up and running.\",\n",
      "    \"review2\": \"The quality of the material is top-notch, but I've noticed a few scratches after using it for a week.\",\n",
      "    \"review3\": \"I was skeptical at first, but this product has truly exceeded my expectations - it's even more functional than I thought it would be!\",\n",
      "    \"review4\": \"Unfortunately, the battery life could be longer. It's fine for occasional use, but it doesn't hold up as well during extended periods.\",\n",
      "    \"review5\": \"I love how compact and lightweight this product is - perfect for my morning commute! The only reason I'm giving 4 stars instead of 5 is because the charging port can get a bit finicky.\"\n",
      "}\n"
     ]
    }
   ],
   "source": [
    "print(formatted_json_result)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "a937ac81",
   "metadata": {},
   "outputs": [],
   "source": [
    "user_prompt = \"\"\"\n",
    "Generate a dataset of 5 employees with name, department, salary, and years of experience.\n",
    "\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "2cef4545",
   "metadata": {},
   "outputs": [],
   "source": [
    "result = generate_synthetic_data(user_prompt)\n",
    "\n",
    "formatted_json_result = json.dumps(result, indent=4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "f7d64ed3",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{\n",
      "    \"employees\": [\n",
      "        {\n",
      "            \"name\": \"John Doe\",\n",
      "            \"department\": \"Marketing\",\n",
      "            \"salary\": 60000,\n",
      "            \"years_of_experience\": 8\n",
      "        },\n",
      "        {\n",
      "            \"name\": \"Jane Smith\",\n",
      "            \"department\": \"IT\",\n",
      "            \"salary\": 70000,\n",
      "            \"years_of_experience\": 5\n",
      "        },\n",
      "        {\n",
      "            \"name\": \"Bob Johnson\",\n",
      "            \"department\": \"Sales\",\n",
      "            \"salary\": 55000,\n",
      "            \"years_of_experience\": 10\n",
      "        },\n",
      "        {\n",
      "            \"name\": \"Emily Chen\",\n",
      "            \"department\": \"Marketing\",\n",
      "            \"salary\": 65000,\n",
      "            \"years_of_experience\": 6\n",
      "        },\n",
      "        {\n",
      "            \"name\": \"Michael Davis\",\n",
      "            \"department\": \"IT\",\n",
      "            \"salary\": 75000,\n",
      "            \"years_of_experience\": 7\n",
      "        }\n",
      "    ]\n",
      "}\n"
     ]
    }
   ],
   "source": [
    "print(formatted_json_result)"
   ]
  }
 ],
 "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": "3.12.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}