{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-31T18:13:23.806907Z",
     "start_time": "2024-05-31T18:13:23.797078Z"
    }
   },
   "outputs": [],
   "source": [
    "%load_ext autoreload\n",
    "%autoreload 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-31T18:14:31.147674Z",
     "start_time": "2024-05-31T18:14:31.134015Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/hossam/.pyenv/versions/.venv/lib/python3.10/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": [
    "import pandas as pd\n",
    "\n",
    "from fastembed import (\n",
    "    SparseTextEmbedding,\n",
    "    TextEmbedding,\n",
    "    LateInteractionTextEmbedding,\n",
    "    ImageEmbedding,\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Supported Text Embedding Models"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-31T18:13:25.863008Z",
     "start_time": "2024-05-31T18:13:25.837795Z"
    }
   },
   "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>model</th>\n",
       "      <th>dim</th>\n",
       "      <th>description</th>\n",
       "      <th>license</th>\n",
       "      <th>size_in_GB</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>BAAI/bge-small-en-v1.5</td>\n",
       "      <td>384</td>\n",
       "      <td>Text embeddings, Unimodal (text), English, 512...</td>\n",
       "      <td>mit</td>\n",
       "      <td>0.067</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>BAAI/bge-small-zh-v1.5</td>\n",
       "      <td>512</td>\n",
       "      <td>Text embeddings, Unimodal (text), Chinese, 512...</td>\n",
       "      <td>mit</td>\n",
       "      <td>0.090</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>snowflake/snowflake-arctic-embed-xs</td>\n",
       "      <td>384</td>\n",
       "      <td>Text embeddings, Unimodal (text), English, 512...</td>\n",
       "      <td>apache-2.0</td>\n",
       "      <td>0.090</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>sentence-transformers/all-MiniLM-L6-v2</td>\n",
       "      <td>384</td>\n",
       "      <td>Text embeddings, Unimodal (text), English, 256...</td>\n",
       "      <td>apache-2.0</td>\n",
       "      <td>0.090</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>jinaai/jina-embeddings-v2-small-en</td>\n",
       "      <td>512</td>\n",
       "      <td>Text embeddings, Unimodal (text), English, 819...</td>\n",
       "      <td>apache-2.0</td>\n",
       "      <td>0.120</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>BAAI/bge-small-en</td>\n",
       "      <td>384</td>\n",
       "      <td>Text embeddings, Unimodal (text), English, 512...</td>\n",
       "      <td>mit</td>\n",
       "      <td>0.130</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>snowflake/snowflake-arctic-embed-s</td>\n",
       "      <td>384</td>\n",
       "      <td>Text embeddings, Unimodal (text), English, 512...</td>\n",
       "      <td>apache-2.0</td>\n",
       "      <td>0.130</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>nomic-ai/nomic-embed-text-v1.5-Q</td>\n",
       "      <td>768</td>\n",
       "      <td>Text embeddings, Multimodal (text, image), Eng...</td>\n",
       "      <td>apache-2.0</td>\n",
       "      <td>0.130</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>BAAI/bge-base-en-v1.5</td>\n",
       "      <td>768</td>\n",
       "      <td>Text embeddings, Unimodal (text), English, 512...</td>\n",
       "      <td>mit</td>\n",
       "      <td>0.210</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>sentence-transformers/paraphrase-multilingual-...</td>\n",
       "      <td>384</td>\n",
       "      <td>Text embeddings, Unimodal (text), Multilingual...</td>\n",
       "      <td>apache-2.0</td>\n",
       "      <td>0.220</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Qdrant/clip-ViT-B-32-text</td>\n",
       "      <td>512</td>\n",
       "      <td>Text embeddings, Multimodal (text&amp;image), Engl...</td>\n",
       "      <td>mit</td>\n",
       "      <td>0.250</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>jinaai/jina-embeddings-v2-base-de</td>\n",
       "      <td>768</td>\n",
       "      <td>Text embeddings, Unimodal (text), Multilingual...</td>\n",
       "      <td>apache-2.0</td>\n",
       "      <td>0.320</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>BAAI/bge-base-en</td>\n",
       "      <td>768</td>\n",
       "      <td>Text embeddings, Unimodal (text), English, 512...</td>\n",
       "      <td>mit</td>\n",
       "      <td>0.420</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>snowflake/snowflake-arctic-embed-m</td>\n",
       "      <td>768</td>\n",
       "      <td>Text embeddings, Unimodal (text), English, 512...</td>\n",
       "      <td>apache-2.0</td>\n",
       "      <td>0.430</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>nomic-ai/nomic-embed-text-v1.5</td>\n",
       "      <td>768</td>\n",
       "      <td>Text embeddings, Multimodal (text, image), Eng...</td>\n",
       "      <td>apache-2.0</td>\n",
       "      <td>0.520</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>jinaai/jina-embeddings-v2-base-en</td>\n",
       "      <td>768</td>\n",
       "      <td>Text embeddings, Unimodal (text), English, 819...</td>\n",
       "      <td>apache-2.0</td>\n",
       "      <td>0.520</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>nomic-ai/nomic-embed-text-v1</td>\n",
       "      <td>768</td>\n",
       "      <td>Text embeddings, Multimodal (text, image), Eng...</td>\n",
       "      <td>apache-2.0</td>\n",
       "      <td>0.520</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>snowflake/snowflake-arctic-embed-m-long</td>\n",
       "      <td>768</td>\n",
       "      <td>Text embeddings, Unimodal (text), English, 204...</td>\n",
       "      <td>apache-2.0</td>\n",
       "      <td>0.540</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>mixedbread-ai/mxbai-embed-large-v1</td>\n",
       "      <td>1024</td>\n",
       "      <td>Text embeddings, Unimodal (text), English, 512...</td>\n",
       "      <td>apache-2.0</td>\n",
       "      <td>0.640</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>jinaai/jina-embeddings-v2-base-code</td>\n",
       "      <td>768</td>\n",
       "      <td>Text embeddings, Unimodal (text), Multilingual...</td>\n",
       "      <td>apache-2.0</td>\n",
       "      <td>0.640</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>sentence-transformers/paraphrase-multilingual-...</td>\n",
       "      <td>768</td>\n",
       "      <td>Text embeddings, Unimodal (text), Multilingual...</td>\n",
       "      <td>apache-2.0</td>\n",
       "      <td>1.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>snowflake/snowflake-arctic-embed-l</td>\n",
       "      <td>1024</td>\n",
       "      <td>Text embeddings, Unimodal (text), English, 512...</td>\n",
       "      <td>apache-2.0</td>\n",
       "      <td>1.020</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>thenlper/gte-large</td>\n",
       "      <td>1024</td>\n",
       "      <td>Text embeddings, Unimodal (text), English, 512...</td>\n",
       "      <td>mit</td>\n",
       "      <td>1.200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>BAAI/bge-large-en-v1.5</td>\n",
       "      <td>1024</td>\n",
       "      <td>Text embeddings, Unimodal (text), English, 512...</td>\n",
       "      <td>mit</td>\n",
       "      <td>1.200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>intfloat/multilingual-e5-large</td>\n",
       "      <td>1024</td>\n",
       "      <td>Text embeddings, Unimodal (text), Multilingual...</td>\n",
       "      <td>mit</td>\n",
       "      <td>2.240</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                model   dim  \\\n",
       "0                              BAAI/bge-small-en-v1.5   384   \n",
       "1                              BAAI/bge-small-zh-v1.5   512   \n",
       "2                 snowflake/snowflake-arctic-embed-xs   384   \n",
       "3              sentence-transformers/all-MiniLM-L6-v2   384   \n",
       "4                  jinaai/jina-embeddings-v2-small-en   512   \n",
       "5                                   BAAI/bge-small-en   384   \n",
       "6                  snowflake/snowflake-arctic-embed-s   384   \n",
       "7                    nomic-ai/nomic-embed-text-v1.5-Q   768   \n",
       "8                               BAAI/bge-base-en-v1.5   768   \n",
       "9   sentence-transformers/paraphrase-multilingual-...   384   \n",
       "10                          Qdrant/clip-ViT-B-32-text   512   \n",
       "11                  jinaai/jina-embeddings-v2-base-de   768   \n",
       "12                                   BAAI/bge-base-en   768   \n",
       "13                 snowflake/snowflake-arctic-embed-m   768   \n",
       "14                     nomic-ai/nomic-embed-text-v1.5   768   \n",
       "15                  jinaai/jina-embeddings-v2-base-en   768   \n",
       "16                       nomic-ai/nomic-embed-text-v1   768   \n",
       "17            snowflake/snowflake-arctic-embed-m-long   768   \n",
       "18                 mixedbread-ai/mxbai-embed-large-v1  1024   \n",
       "19                jinaai/jina-embeddings-v2-base-code   768   \n",
       "20  sentence-transformers/paraphrase-multilingual-...   768   \n",
       "21                 snowflake/snowflake-arctic-embed-l  1024   \n",
       "22                                 thenlper/gte-large  1024   \n",
       "23                             BAAI/bge-large-en-v1.5  1024   \n",
       "24                     intfloat/multilingual-e5-large  1024   \n",
       "\n",
       "                                          description     license  size_in_GB  \n",
       "0   Text embeddings, Unimodal (text), English, 512...         mit       0.067  \n",
       "1   Text embeddings, Unimodal (text), Chinese, 512...         mit       0.090  \n",
       "2   Text embeddings, Unimodal (text), English, 512...  apache-2.0       0.090  \n",
       "3   Text embeddings, Unimodal (text), English, 256...  apache-2.0       0.090  \n",
       "4   Text embeddings, Unimodal (text), English, 819...  apache-2.0       0.120  \n",
       "5   Text embeddings, Unimodal (text), English, 512...         mit       0.130  \n",
       "6   Text embeddings, Unimodal (text), English, 512...  apache-2.0       0.130  \n",
       "7   Text embeddings, Multimodal (text, image), Eng...  apache-2.0       0.130  \n",
       "8   Text embeddings, Unimodal (text), English, 512...         mit       0.210  \n",
       "9   Text embeddings, Unimodal (text), Multilingual...  apache-2.0       0.220  \n",
       "10  Text embeddings, Multimodal (text&image), Engl...         mit       0.250  \n",
       "11  Text embeddings, Unimodal (text), Multilingual...  apache-2.0       0.320  \n",
       "12  Text embeddings, Unimodal (text), English, 512...         mit       0.420  \n",
       "13  Text embeddings, Unimodal (text), English, 512...  apache-2.0       0.430  \n",
       "14  Text embeddings, Multimodal (text, image), Eng...  apache-2.0       0.520  \n",
       "15  Text embeddings, Unimodal (text), English, 819...  apache-2.0       0.520  \n",
       "16  Text embeddings, Multimodal (text, image), Eng...  apache-2.0       0.520  \n",
       "17  Text embeddings, Unimodal (text), English, 204...  apache-2.0       0.540  \n",
       "18  Text embeddings, Unimodal (text), English, 512...  apache-2.0       0.640  \n",
       "19  Text embeddings, Unimodal (text), Multilingual...  apache-2.0       0.640  \n",
       "20  Text embeddings, Unimodal (text), Multilingual...  apache-2.0       1.000  \n",
       "21  Text embeddings, Unimodal (text), English, 512...  apache-2.0       1.020  \n",
       "22  Text embeddings, Unimodal (text), English, 512...         mit       1.200  \n",
       "23  Text embeddings, Unimodal (text), English, 512...         mit       1.200  \n",
       "24  Text embeddings, Unimodal (text), Multilingual...         mit       2.240  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "supported_models = (\n",
    "    pd.DataFrame(TextEmbedding.list_supported_models())\n",
    "    .sort_values(\"size_in_GB\")\n",
    "    .drop(columns=[\"sources\", \"model_file\", \"additional_files\"])\n",
    "    .reset_index(drop=True)\n",
    ")\n",
    "supported_models"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Supported Sparse Text Embedding Models"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-31T18:13:27.124747Z",
     "start_time": "2024-05-31T18:13:27.096212Z"
    }
   },
   "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>model</th>\n",
       "      <th>vocab_size</th>\n",
       "      <th>description</th>\n",
       "      <th>license</th>\n",
       "      <th>size_in_GB</th>\n",
       "      <th>requires_idf</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Qdrant/bm25</td>\n",
       "      <td>NaN</td>\n",
       "      <td>BM25 as sparse embeddings meant to be used wit...</td>\n",
       "      <td>apache-2.0</td>\n",
       "      <td>0.010</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Qdrant/bm42-all-minilm-l6-v2-attentions</td>\n",
       "      <td>30522.0</td>\n",
       "      <td>Light sparse embedding model, which assigns an...</td>\n",
       "      <td>apache-2.0</td>\n",
       "      <td>0.090</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>prithivida/Splade_PP_en_v1</td>\n",
       "      <td>30522.0</td>\n",
       "      <td>Independent Implementation of SPLADE++ Model f...</td>\n",
       "      <td>apache-2.0</td>\n",
       "      <td>0.532</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>prithvida/Splade_PP_en_v1</td>\n",
       "      <td>30522.0</td>\n",
       "      <td>Independent Implementation of SPLADE++ Model f...</td>\n",
       "      <td>apache-2.0</td>\n",
       "      <td>0.532</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                     model  vocab_size  \\\n",
       "0                              Qdrant/bm25         NaN   \n",
       "1  Qdrant/bm42-all-minilm-l6-v2-attentions     30522.0   \n",
       "2               prithivida/Splade_PP_en_v1     30522.0   \n",
       "3                prithvida/Splade_PP_en_v1     30522.0   \n",
       "\n",
       "                                         description     license  size_in_GB  \\\n",
       "0  BM25 as sparse embeddings meant to be used wit...  apache-2.0       0.010   \n",
       "1  Light sparse embedding model, which assigns an...  apache-2.0       0.090   \n",
       "2  Independent Implementation of SPLADE++ Model f...  apache-2.0       0.532   \n",
       "3  Independent Implementation of SPLADE++ Model f...  apache-2.0       0.532   \n",
       "\n",
       "  requires_idf  \n",
       "0         True  \n",
       "1         True  \n",
       "2          NaN  \n",
       "3          NaN  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(\n",
    "    pd.DataFrame(SparseTextEmbedding.list_supported_models())\n",
    "    .sort_values(\"size_in_GB\")\n",
    "    .drop(columns=[\"sources\", \"model_file\", \"additional_files\"])\n",
    "    .reset_index(drop=True)\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "## Supported Late Interaction Text Embedding Models"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-31T18:14:34.370252Z",
     "start_time": "2024-05-31T18:14:34.354270Z"
    },
    "collapsed": false
   },
   "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>model</th>\n",
       "      <th>dim</th>\n",
       "      <th>description</th>\n",
       "      <th>license</th>\n",
       "      <th>size_in_GB</th>\n",
       "      <th>additional_files</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>answerdotai/answerai-colbert-small-v1</td>\n",
       "      <td>96</td>\n",
       "      <td>Text embeddings, Unimodal (text), Multilingual...</td>\n",
       "      <td>apache-2.0</td>\n",
       "      <td>0.13</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>colbert-ir/colbertv2.0</td>\n",
       "      <td>128</td>\n",
       "      <td>Late interaction model</td>\n",
       "      <td>mit</td>\n",
       "      <td>0.44</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>jinaai/jina-colbert-v2</td>\n",
       "      <td>1024</td>\n",
       "      <td>New model that expands capabilities of colbert...</td>\n",
       "      <td>cc-by-nc-4.0</td>\n",
       "      <td>2.24</td>\n",
       "      <td>[onnx/model.onnx_data]</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                   model   dim  \\\n",
       "0  answerdotai/answerai-colbert-small-v1    96   \n",
       "1                 colbert-ir/colbertv2.0   128   \n",
       "2                 jinaai/jina-colbert-v2  1024   \n",
       "\n",
       "                                         description       license  \\\n",
       "0  Text embeddings, Unimodal (text), Multilingual...    apache-2.0   \n",
       "1                             Late interaction model           mit   \n",
       "2  New model that expands capabilities of colbert...  cc-by-nc-4.0   \n",
       "\n",
       "   size_in_GB        additional_files  \n",
       "0        0.13                     NaN  \n",
       "1        0.44                     NaN  \n",
       "2        2.24  [onnx/model.onnx_data]  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(\n",
    "    pd.DataFrame(LateInteractionTextEmbedding.list_supported_models())\n",
    "    .sort_values(\"size_in_GB\")\n",
    "    .drop(columns=[\"sources\", \"model_file\"])\n",
    "    .reset_index(drop=True)\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "## Supported Image Embedding Models"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-31T18:14:42.501881Z",
     "start_time": "2024-05-31T18:14:42.484726Z"
    },
    "collapsed": false
   },
   "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>model</th>\n",
       "      <th>dim</th>\n",
       "      <th>description</th>\n",
       "      <th>license</th>\n",
       "      <th>size_in_GB</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Qdrant/resnet50-onnx</td>\n",
       "      <td>2048</td>\n",
       "      <td>Image embeddings, Unimodal (image), 2016 year</td>\n",
       "      <td>apache-2.0</td>\n",
       "      <td>0.10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Qdrant/clip-ViT-B-32-vision</td>\n",
       "      <td>512</td>\n",
       "      <td>Image embeddings, Multimodal (text&amp;image), 202...</td>\n",
       "      <td>mit</td>\n",
       "      <td>0.34</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Qdrant/Unicom-ViT-B-32</td>\n",
       "      <td>512</td>\n",
       "      <td>Image embeddings, Multimodal (text&amp;image), 202...</td>\n",
       "      <td>apache-2.0</td>\n",
       "      <td>0.48</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Qdrant/Unicom-ViT-B-16</td>\n",
       "      <td>768</td>\n",
       "      <td>Image embeddings (more detailed than Unicom-Vi...</td>\n",
       "      <td>apache-2.0</td>\n",
       "      <td>0.82</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                         model   dim  \\\n",
       "0         Qdrant/resnet50-onnx  2048   \n",
       "1  Qdrant/clip-ViT-B-32-vision   512   \n",
       "2       Qdrant/Unicom-ViT-B-32   512   \n",
       "3       Qdrant/Unicom-ViT-B-16   768   \n",
       "\n",
       "                                         description     license  size_in_GB  \n",
       "0      Image embeddings, Unimodal (image), 2016 year  apache-2.0        0.10  \n",
       "1  Image embeddings, Multimodal (text&image), 202...         mit        0.34  \n",
       "2  Image embeddings, Multimodal (text&image), 202...  apache-2.0        0.48  \n",
       "3  Image embeddings (more detailed than Unicom-Vi...  apache-2.0        0.82  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(\n",
    "    pd.DataFrame(ImageEmbedding.list_supported_models())\n",
    "    .sort_values(\"size_in_GB\")\n",
    "    .drop(columns=[\"sources\", \"model_file\"])\n",
    "    .reset_index(drop=True)\n",
    ")"
   ]
  }
 ],
 "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": "3.10.15"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}