{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\li'zhen\\AppData\\Roaming\\Python\\Python311\\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"
     ]
    }
   ],
   "source": [
    "from gradio_tools.tools import StableDiffusionTool"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Loaded as API: https://gradio-client-demos-stable-diffusion.hf.space ✔\n",
      "\n",
      "Job Status: Status.STARTING eta: None\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'d:\\\\LangChainGo\\\\005f9692-3bcc-4490-adf0-d617273ab9da\\\\tmp02m0jq2t.jpg'"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "local_file_path = StableDiffusionTool().langchain.run(\"Please create a photo of a dog riding a skateboard\")\n",
    "local_file_path"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Loaded as API: https://gradio-client-demos-stable-diffusion.hf.space ✔\n",
      "Loaded as API: https://taesiri-blip-2.hf.space ✔\n"
     ]
    },
    {
     "ename": "ValueError",
     "evalue": "Could not get Gradio config from: https://taesiri-blip-2.hf.space",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
      "File \u001b[1;32m~\\AppData\\Roaming\\Python\\Python311\\site-packages\\gradio_client\\client.py:549\u001b[0m, in \u001b[0;36mClient._get_config\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    548\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[1;32m--> 549\u001b[0m     config \u001b[39m=\u001b[39m json\u001b[39m.\u001b[39mloads(result\u001b[39m.\u001b[39;49mgroup(\u001b[39m1\u001b[39m))  \u001b[39m# type: ignore\u001b[39;00m\n\u001b[0;32m    550\u001b[0m \u001b[39mexcept\u001b[39;00m \u001b[39mAttributeError\u001b[39;00m:\n",
      "\u001b[1;31mAttributeError\u001b[0m: 'NoneType' object has no attribute 'group'",
      "\nDuring handling of the above exception, another exception occurred:\n",
      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[3], line 10\u001b[0m\n\u001b[0;32m      8\u001b[0m llm \u001b[39m=\u001b[39m OpenAI(temperature\u001b[39m=\u001b[39m\u001b[39m0\u001b[39m)\n\u001b[0;32m      9\u001b[0m memory \u001b[39m=\u001b[39m ConversationBufferMemory(memory_key\u001b[39m=\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mchat_history\u001b[39m\u001b[39m\"\u001b[39m)\n\u001b[1;32m---> 10\u001b[0m tools \u001b[39m=\u001b[39m [StableDiffusionTool()\u001b[39m.\u001b[39mlangchain, ImageCaptioningTool()\u001b[39m.\u001b[39mlangchain,\n\u001b[0;32m     11\u001b[0m          StableDiffusionPromptGeneratorTool()\u001b[39m.\u001b[39mlangchain, TextToVideoTool()\u001b[39m.\u001b[39mlangchain]\n\u001b[0;32m     14\u001b[0m agent \u001b[39m=\u001b[39m initialize_agent(tools, llm, memory\u001b[39m=\u001b[39mmemory, agent\u001b[39m=\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mconversational-react-description\u001b[39m\u001b[39m\"\u001b[39m, verbose\u001b[39m=\u001b[39m\u001b[39mTrue\u001b[39;00m)\n\u001b[0;32m     15\u001b[0m output \u001b[39m=\u001b[39m agent\u001b[39m.\u001b[39mrun(\u001b[39minput\u001b[39m\u001b[39m=\u001b[39m(\u001b[39m\"\u001b[39m\u001b[39mPlease create a photo of a dog riding a skateboard \u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m     16\u001b[0m                           \u001b[39m\"\u001b[39m\u001b[39mbut improve my prompt prior to using an image generator.\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m     17\u001b[0m                           \u001b[39m\"\u001b[39m\u001b[39mPlease caption the generated image and create a video for it using the improved prompt.\u001b[39m\u001b[39m\"\u001b[39m))\n",
      "File \u001b[1;32m~\\AppData\\Roaming\\Python\\Python311\\site-packages\\gradio_tools\\tools\\image_captioning.py:28\u001b[0m, in \u001b[0;36mImageCaptioningTool.__init__\u001b[1;34m(self, name, description, src, hf_token, duplicate)\u001b[0m\n\u001b[0;32m     16\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39m__init__\u001b[39m(\n\u001b[0;32m     17\u001b[0m     \u001b[39mself\u001b[39m,\n\u001b[0;32m     18\u001b[0m     name\u001b[39m=\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mImageCaptioner\u001b[39m\u001b[39m\"\u001b[39m,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m     26\u001b[0m     duplicate\u001b[39m=\u001b[39m\u001b[39mTrue\u001b[39;00m,\n\u001b[0;32m     27\u001b[0m ) \u001b[39m-\u001b[39m\u001b[39m>\u001b[39m \u001b[39mNone\u001b[39;00m:\n\u001b[1;32m---> 28\u001b[0m     \u001b[39msuper\u001b[39;49m()\u001b[39m.\u001b[39;49m\u001b[39m__init__\u001b[39;49m(name, description, src, hf_token, duplicate)\n",
      "File \u001b[1;32m~\\AppData\\Roaming\\Python\\Python311\\site-packages\\gradio_tools\\tools\\gradio_tool.py:36\u001b[0m, in \u001b[0;36mGradioTool.__init__\u001b[1;34m(self, name, description, src, hf_token, duplicate)\u001b[0m\n\u001b[0;32m     34\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[0;32m     35\u001b[0m     \u001b[39mself\u001b[39m\u001b[39m.\u001b[39msrc \u001b[39m=\u001b[39m src\n\u001b[1;32m---> 36\u001b[0m     \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mclient \u001b[39m=\u001b[39m grc\u001b[39m.\u001b[39;49mClient(\u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49msrc, hf_token\u001b[39m=\u001b[39;49mhf_token)\n\u001b[0;32m     37\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mdescription \u001b[39m+\u001b[39m\u001b[39m=\u001b[39m (\n\u001b[0;32m     38\u001b[0m     \u001b[39m\"\u001b[39m\u001b[39mIf the output is the string QUEUE_FULL you \u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m     39\u001b[0m     \u001b[39m\"\u001b[39m\u001b[39mshould try this action again and never stop until you \u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m     40\u001b[0m     \u001b[39m\"\u001b[39m\u001b[39mdon\u001b[39m\u001b[39m'\u001b[39m\u001b[39mt see this message.\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m     41\u001b[0m )\n\u001b[0;32m     42\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_block \u001b[39m=\u001b[39m \u001b[39mNone\u001b[39;00m\n",
      "File \u001b[1;32m~\\AppData\\Roaming\\Python\\Python311\\site-packages\\gradio_client\\client.py:114\u001b[0m, in \u001b[0;36mClient.__init__\u001b[1;34m(self, src, hf_token, max_workers, serialize, verbose)\u001b[0m\n\u001b[0;32m    112\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mupload_url \u001b[39m=\u001b[39m urllib\u001b[39m.\u001b[39mparse\u001b[39m.\u001b[39murljoin(\u001b[39mself\u001b[39m\u001b[39m.\u001b[39msrc, utils\u001b[39m.\u001b[39mUPLOAD_URL)\n\u001b[0;32m    113\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mreset_url \u001b[39m=\u001b[39m urllib\u001b[39m.\u001b[39mparse\u001b[39m.\u001b[39murljoin(\u001b[39mself\u001b[39m\u001b[39m.\u001b[39msrc, utils\u001b[39m.\u001b[39mRESET_URL)\n\u001b[1;32m--> 114\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mconfig \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_get_config()\n\u001b[0;32m    115\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39msession_hash \u001b[39m=\u001b[39m \u001b[39mstr\u001b[39m(uuid\u001b[39m.\u001b[39muuid4())\n\u001b[0;32m    117\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mendpoints \u001b[39m=\u001b[39m [\n\u001b[0;32m    118\u001b[0m     Endpoint(\u001b[39mself\u001b[39m, fn_index, dependency)\n\u001b[0;32m    119\u001b[0m     \u001b[39mfor\u001b[39;00m fn_index, dependency \u001b[39min\u001b[39;00m \u001b[39menumerate\u001b[39m(\u001b[39mself\u001b[39m\u001b[39m.\u001b[39mconfig[\u001b[39m\"\u001b[39m\u001b[39mdependencies\u001b[39m\u001b[39m\"\u001b[39m])\n\u001b[0;32m    120\u001b[0m ]\n",
      "File \u001b[1;32m~\\AppData\\Roaming\\Python\\Python311\\site-packages\\gradio_client\\client.py:551\u001b[0m, in \u001b[0;36mClient._get_config\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    549\u001b[0m     config \u001b[39m=\u001b[39m json\u001b[39m.\u001b[39mloads(result\u001b[39m.\u001b[39mgroup(\u001b[39m1\u001b[39m))  \u001b[39m# type: ignore\u001b[39;00m\n\u001b[0;32m    550\u001b[0m \u001b[39mexcept\u001b[39;00m \u001b[39mAttributeError\u001b[39;00m:\n\u001b[1;32m--> 551\u001b[0m     \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mCould not get Gradio config from: \u001b[39m\u001b[39m{\u001b[39;00m\u001b[39mself\u001b[39m\u001b[39m.\u001b[39msrc\u001b[39m}\u001b[39;00m\u001b[39m\"\u001b[39m)\n\u001b[0;32m    552\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39m\"\u001b[39m\u001b[39mallow_flagging\u001b[39m\u001b[39m\"\u001b[39m \u001b[39min\u001b[39;00m config:\n\u001b[0;32m    553\u001b[0m     \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\n\u001b[0;32m    554\u001b[0m         \u001b[39m\"\u001b[39m\u001b[39mGradio 2.x is not supported by this client. Please upgrade your Gradio app to Gradio 3.x or higher.\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m    555\u001b[0m     )\n",
      "\u001b[1;31mValueError\u001b[0m: Could not get Gradio config from: https://taesiri-blip-2.hf.space"
     ]
    }
   ],
   "source": [
    "from langchain.agents import initialize_agent\n",
    "from langchain.llms import OpenAI\n",
    "from gradio_tools.tools import (StableDiffusionTool, ImageCaptioningTool, StableDiffusionPromptGeneratorTool,\n",
    "                                TextToVideoTool)\n",
    "\n",
    "from langchain.memory import ConversationBufferMemory\n",
    "\n",
    "llm = OpenAI(temperature=0)\n",
    "memory = ConversationBufferMemory(memory_key=\"chat_history\")\n",
    "tools = [StableDiffusionTool().langchain, ImageCaptioningTool().langchain,\n",
    "         StableDiffusionPromptGeneratorTool().langchain, TextToVideoTool().langchain]\n",
    "\n",
    "\n",
    "agent = initialize_agent(tools, llm, memory=memory, agent=\"conversational-react-description\", verbose=True)\n",
    "output = agent.run(input=(\"Please create a photo of a dog riding a skateboard \"\n",
    "                          \"but improve my prompt prior to using an image generator.\"\n",
    "                          \"Please caption the generated image and create a video for it using the improved prompt.\"))"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.11.3"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}