{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "ccdc7909",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "# ! pip install -r ../../../../requirements.txt -U"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "25aece1d",
   "metadata": {},
   "outputs": [],
   "source": [
    "from agent_framework import Agent, Content\n",
    "from agent_framework.foundry import FoundryChatClient\n",
    "from azure.identity import AzureCliCredential"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "4e54cdb7",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "import os\n",
    "import base64\n",
    "from dotenv import load_dotenv\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "6b0e6968",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "load_dotenv(\"../../../../.env\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "5b560781",
   "metadata": {},
   "outputs": [],
   "source": [
    "AgentName = \"Vision-Agent\"\n",
    "AgentInstructions = \"You are my furniture sales consultant, you can find different furniture elements from the pictures and give me a purchase suggestion\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "26ff8fae",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "User: Please find the relevant furniture according to the image and give the corresponding price for each piece of furniture [Image provided]\n",
      "Agent: From the image, I can identify the main furniture and decor pieces and give you **estimated market prices** based on similar modern/minimalist items. Since I can’t confirm the exact brand from the photo alone, these are **reference purchase suggestions**.\n",
      "\n",
      "## Furniture identified from the image\n",
      "\n",
      "| Item | Description | Estimated Price |\n",
      "|---|---|---:|\n",
      "| **3-seat sofa** | White modern fabric sofa with square arms | **$700–$1,500** |\n",
      "| **Accent lounge chair** | Dark blue upholstered lounge/armchair | **$300–$900** |\n",
      "| **Coffee table** | Small oval/rounded white-top coffee table with wood legs | **$150–$450** |\n",
      "| **TV stand / media console** | Light wood low-profile TV cabinet | **$250–$700** |\n",
      "| **Side table** | Small black metal side table next to the sofa | **$60–$180** |\n",
      "| **Round pedestal side table** | Small round table near the blue chair | **$80–$250** |\n",
      "| **Main chandelier** | Modern black branched chandelier with globe bulbs | **$180–$600** |\n",
      "| **Pendant lights** | 2–3 glass globe pendant lights near the corner | **$50–$180 each** |\n",
      "| **Curtains (full set)** | Sheer white inner curtains + gray blackout drapes | **$200–$600** |\n",
      "| **Wall art** | Framed deer artwork | **$50–$200** |\n",
      "| **Decor pillows** | Assorted blue/black/white throw pillows | **$20–$50 each** |\n",
      "| **TV** | Flat-screen TV, approx. 55\"–65\" | **$400–$1,200** |\n",
      "\n",
      "## Estimated total budget\n",
      "\n",
      "Depending on quality level:\n",
      "\n",
      "- **Budget setup:** **$2,440–$4,500**\n",
      "- **Mid-range setup:** **$4,500–$7,500**\n",
      "- **Higher-end look:** **$7,500+**\n",
      "\n",
      "## Purchase suggestions by style\n",
      "To match this room, look for these keywords:\n",
      "\n",
      "- **Style:** Modern / Scandinavian / Minimalist\n",
      "- **Colors:** White, light oak, black, navy blue, gray\n",
      "- **Materials:** Fabric upholstery, light wood veneer, metal legs, glass globe lighting\n",
      "\n",
      "## Best priority purchases\n",
      "If you want to recreate the look efficiently, buy in this order:\n",
      "\n",
      "1. **White sofa**\n",
      "2. **Light wood TV stand**\n",
      "3. **Oval coffee table**\n",
      "4. **Blue accent chair**\n",
      "5. **Black chandelier**\n",
      "6. **Curtains**\n",
      "7. **Side tables + pillows + wall art**\n",
      "\n",
      "If you want, I can also turn this into a **shopping list with specific products and estimated prices from IKEA, Amazon, Wayfair, or local furniture stores**.\n"
     ]
    }
   ],
   "source": [
    "# Create a Foundry-backed agent with vision capabilities\n",
    "agent = Agent(\n",
    "    client=FoundryChatClient(credential=AzureCliCredential()),\n",
    "    name=AgentName,\n",
    "    instructions=AgentInstructions,\n",
    ")\n",
    "\n",
    "# Prepare image\n",
    "image_path = \"../../files/home.png\"\n",
    "with open(image_path, \"rb\") as image_file:\n",
    "    image_b64 = base64.b64encode(image_file.read()).decode()\n",
    "image_uri = f\"data:image/png;base64,{image_b64}\"\n",
    "\n",
    "# Send text and image as separate content items\n",
    "print(\"User: Please find the relevant furniture according to the image and give the corresponding price for each piece of furniture [Image provided]\")\n",
    "first_result = await agent.run(\n",
    "        [\n",
    "            Content.from_text(text=\"Please find the relevant furniture according to the image and give the corresponding price for each piece of furniture\"),\n",
    "            Content.from_uri(uri=image_uri, media_type=\"image/png\")\n",
    "        ]\n",
    ")\n",
    "\n",
    "print(f\"Agent: {first_result.text}\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "agentdev",
   "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
}