{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.document_loaders import ImageCaptionLoader"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "list_image_urls = [\n",
    "    'https://t7.baidu.com/it/u=2168645659,3174029352&fm=193&f=GIF',\n",
    "    'https://t7.baidu.com/it/u=2851687453,2321283050&fm=193&f=GIF',\n",
    "    'https://t7.baidu.com/it/u=3601447414,1764260638&fm=193&f=GIF',\n",
    "    'https://gimg2.baidu.com/image_search/src=http%3A%2F%2Fc-ssl.duitang.com%2Fuploads%2Fblog%2F202111%2F17%2F20211117092914_579a7.thumb.1000_0.jpeg&refer=http%3A%2F%2Fc-ssl.duitang.com&app=2002&size=f9999,10000&q=a80&n=0&g=0n&fmt=auto?sec=1685104926&t=62afde36bb3200aa727ced1c8fb18eab',\n",
    "    'https://img1.baidu.com/it/u=219752959,2207818343&fm=253&fmt=auto&app=138&f=JPEG?w=500&h=725',\n",
    "    'https://img2.baidu.com/it/u=3813658383,1119780612&fm=253&fmt=auto&app=120&f=JPEG?w=1280&h=800',\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/tutu/anaconda3/lib/python3.10/site-packages/transformers/generation/utils.py:1313: UserWarning: Using `max_length`'s default (20) to control the generation length. This behaviour is deprecated and will be removed from the config in v5 of Transformers -- we recommend using `max_new_tokens` to control the maximum length of the generation.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[Document(page_content='an image of two women in kimono [SEP]', metadata={'image_path': 'https://t7.baidu.com/it/u=2168645659,3174029352&fm=193&f=GIF'}),\n",
       " Document(page_content='an image of a cat eating fish [SEP]', metadata={'image_path': 'https://t7.baidu.com/it/u=2851687453,2321283050&fm=193&f=GIF'}),\n",
       " Document(page_content='an image of a cat and dog [SEP]', metadata={'image_path': 'https://t7.baidu.com/it/u=3601447414,1764260638&fm=193&f=GIF'}),\n",
       " Document(page_content='an image of a girl in a school uniform [SEP]', metadata={'image_path': 'https://gimg2.baidu.com/image_search/src=http%3A%2F%2Fc-ssl.duitang.com%2Fuploads%2Fblog%2F202111%2F17%2F20211117092914_579a7.thumb.1000_0.jpeg&refer=http%3A%2F%2Fc-ssl.duitang.com&app=2002&size=f9999,10000&q=a80&n=0&g=0n&fmt=auto?sec=1685104926&t=62afde36bb3200aa727ced1c8fb18eab'}),\n",
       " Document(page_content='an image of a woman in a blue sweater [SEP]', metadata={'image_path': 'https://img1.baidu.com/it/u=219752959,2207818343&fm=253&fmt=auto&app=138&f=JPEG?w=500&h=725'}),\n",
       " Document(page_content='an image of a woman in a yellow dress [SEP]', metadata={'image_path': 'https://img2.baidu.com/it/u=3813658383,1119780612&fm=253&fmt=auto&app=120&f=JPEG?w=1280&h=800'})]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "loader = ImageCaptionLoader(path_images=list_image_urls)\n",
    "list_docs = loader.load()\n",
    "list_docs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Using embedded DuckDB without persistence: data will be transient\n"
     ]
    }
   ],
   "source": [
    "from langchain.indexes import VectorstoreIndexCreator\n",
    "index = VectorstoreIndexCreator().from_loaders([loader])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "' 我不知道。'"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "query = \"用中文回答，狗是什么品种\"\n",
    "index.query(query)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "' There are images of a cat and dog, a cat eating fish, two women in kimono, and a woman in a blue sweater.'"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "query = \"What kind of images are there?\"\n",
    "index.query(query)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "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": "3.10.10"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}