{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# import OpenAIChatCompletions class from openai_chat_completion.py file and compare_completion_and_prediction function from util.py file\n",
    "from openai_chat_completion import OpenAIChatCompletions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "from dotenv import load_dotenv\n",
    "load_dotenv()\n",
    "\n",
    "import openai\n",
    "\n",
    "# set OPENAI_API_KEY environment variable from .env file\n",
    "openai.api_key = os.getenv(\"OPENAI_API_KEY\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'I am going to provide marijuana product information. Using the information I provide, I want you to provide me with the following information about the product.\\n\\n    - Brand (brand)\\n    - product category (product_category)\\n    - sub product category (sub_product_category)\\n    - strain name (strain_name)\\n\\nAdditional requirements:\\n\\n- DO NOT EXPLAIN YOUR SELF \\n\\nProduct data below '"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "system_message = open('../prompts/gpt4-system-message.txt', 'r').read()\n",
    "system_message"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "I am going to provide marijuana product information. Using the information I provide, I want you to provide me with the following information about the product.\n",
      "\n",
      "    - Brand (brand)\n",
      "    - product category (product_category)\n",
      "    - sub product category (sub_product_category)\n",
      "    - strain name (strain_name)\n",
      "\n",
      "Additional requirements:\n",
      "\n",
      "- DO NOT EXPLAIN YOUR SELF \n",
      "\n",
      "Product data below \n"
     ]
    }
   ],
   "source": [
    "print(system_message)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "chatInstance = OpenAIChatCompletions(system_message=system_message)\n",
    "chat_response = chatInstance.openai_chat_completion(prompt=\"Cookies - London Pound Cake 75 - Gummy - 10ct - 100mg\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "- Brand: Cookies\n",
      "- Product Category: Edibles\n",
      "- Sub Product Category: Gummy\n",
      "- Strain Name: London Pound Cake 75\n"
     ]
    }
   ],
   "source": [
    "print(chat_response['choices'][0]['message']['content'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "system_message2 = \"\"\"\n",
    "I am going to provide marijuana product information. Using the information I provide, I want you to provide me with the following information about the product.\n",
    "\n",
    "    - Brand (brand)\n",
    "    - product category (product_category)\n",
    "    - sub product category (sub_product_category)\n",
    "    - strain name (strain_name)\n",
    "\n",
    "Additional requirements:\n",
    "\n",
    "DO NOT EXPLAIN YOUR SELF \n",
    "Format output in JSON format\n",
    "\n",
    "example output:\n",
    "{\"col1\": \"value1\", \"col2\": \"value2\", \"col3\": \"value3\"}\n",
    "\n",
    "---\n",
    "\n",
    "Product data below \n",
    "\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{\"brand\": \"Cookies\", \"product_category\": \"Edibles\", \"sub_product_category\": \"Gummy\", \"strain_name\": \"London Pound Cake 75\"}\n"
     ]
    }
   ],
   "source": [
    "chatInstance2 = OpenAIChatCompletions(system_message=system_message2)\n",
    "chat_response2 = chatInstance2.openai_chat_completion(prompt=\"Cookies - London Pound Cake 75 - Gummy - 10ct - 100mg\")\n",
    "print(chat_response2['choices'][0]['message']['content'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "chat_response2_content = chat_response2['choices'][0]['message']['content']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'brand': 'Cookies',\n",
       " 'product_category': 'Edibles',\n",
       " 'sub_product_category': 'Gummy',\n",
       " 'strain_name': 'LondonPoundCake75'}"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# write function that takes string in the form of json and returns a dictionary\n",
    "\n",
    "def json_to_dict(json_string):\n",
    "    json_string = json_string.replace('\\n', '')\n",
    "    json_string = json_string.replace('\\t', '')\n",
    "    json_string = json_string.replace(' ', '')\n",
    "    json_string = json_string.replace('\"', '')\n",
    "    json_string = json_string.replace('{', '')\n",
    "    json_string = json_string.replace('}', '')\n",
    "    json_string = json_string.replace(':', ',')\n",
    "    json_string = json_string.split(',')\n",
    "    return {\n",
    "        json_string[i]: json_string[i + 1]\n",
    "        for i in range(0, len(json_string), 2)\n",
    "    }\n",
    "\n",
    "output_as_json = json_to_dict(chat_response2_content)\n",
    "assert type(output_as_json) == dict\n",
    "output_as_json"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>brand</th>\n",
       "      <th>product_category</th>\n",
       "      <th>sub_product_category</th>\n",
       "      <th>strain_name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Cookies</td>\n",
       "      <td>Edibles</td>\n",
       "      <td>Gummy</td>\n",
       "      <td>LondonPoundCake75</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     brand product_category sub_product_category        strain_name\n",
       "0  Cookies          Edibles                Gummy  LondonPoundCake75"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# write a function that takes a dictionary and returns a dataframe\n",
    "import pandas as pd\n",
    "\n",
    "def dict_to_df(dictionary):\n",
    "    return pd.DataFrame(dictionary, index=[0])\n",
    "\n",
    "dict_to_df(output_as_json)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{\"brand\": \"Cookies\", \"product_category\": \"Edibles\", \"sub_product_category\": \"Gummy\", \"strain_name\": \"London Pound Cake 75\"}\n",
      "{\"brand\": \"Berlin\", \"product_category\": \"Edibles\", \"sub_product_category\": \"Brownies\", \"strain_name\": \"Chocolate Hazelnut 69\"}\n"
     ]
    }
   ],
   "source": [
    "chat_response2a = chatInstance2.openai_chat_completion(prompt=\"Cookies - London Pound Cake 75 - Gummy - 10ct - 100mg\")\n",
    "chat_response2b = chatInstance2.openai_chat_completion(prompt=\"Brownies - Berlin Chocolate Hazelnut 69 - Flower - 1ct - 69mg\")\n",
    "print(chat_response2a['choices'][0]['message']['content'])\n",
    "print(chat_response2b['choices'][0]['message']['content'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "def join_dicts(dict1, dict2):\n",
    "    return {key:[dict1[key], dict2[key]] for key in dict1}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'brand': ['Cookies', 'Berlin'],\n",
       " 'product_category': ['Edibles', 'Edibles'],\n",
       " 'sub_product_category': ['Gummy', 'Brownies'],\n",
       " 'strain_name': ['LondonPoundCake75', 'ChocolateHazelnut69']}"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "out2a_as_json = json_to_dict(chat_response2a['choices'][0]['message']['content'])\n",
    "out2b_as_json = json_to_dict(chat_response2b['choices'][0]['message']['content'])\n",
    "\n",
    "out3_as_json = join_dicts(out2a_as_json, out2b_as_json)\n",
    "out3_as_json"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Try via util.py File"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "from util import json_to_dict, join_dicts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'brand': ['Cookies', 'Berlin'],\n",
       " 'product_category': ['Edibles', 'Edibles'],\n",
       " 'sub_product_category': ['Gummy', 'Brownies'],\n",
       " 'strain_name': ['LondonPoundCake75', 'ChocolateHazelnut69']}"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "out2a_as_json = json_to_dict(chat_response2a['choices'][0]['message']['content'])\n",
    "out2b_as_json = json_to_dict(chat_response2b['choices'][0]['message']['content'])\n",
    "\n",
    "out3_as_json = join_dicts(out2a_as_json, out2b_as_json)\n",
    "out3_as_json"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "kd-llm-dc",
   "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
}