langchain/docs/versioned_docs/version-0.2.x/integrations/text_embedding/volcengine.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "# Volc Engine\n",
    "\n",
    "This notebook provides you with a guide on how to load the Volcano Embedding class.\n",
    "\n",
    "\n",
    "## API Initialization\n",
    "\n",
    "To use the LLM services based on [VolcEngine](https://www.volcengine.com/docs/82379/1099455), you have to initialize these parameters:\n",
    "\n",
    "You could either choose to init the AK,SK in environment variables or init params:\n",
    "\n",
    "```base\n",
    "export VOLC_ACCESSKEY=XXX\n",
    "export VOLC_SECRETKEY=XXX\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "ExecuteTime": {
     "start_time": "2023-12-14T03:05:29.857798Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "embed_documents result:\n",
      " [0.02929673343896866, -0.009310632012784481, -0.060323506593704224, 0.0031018739100545645, -0.002218986628577113, -0.0023125179577618837, -0.04864659160375595, -2.062115163425915e-05]\n",
      " [0.01987231895327568, -0.026041055098176003, -0.08395249396562576, 0.020043574273586273, -0.028862033039331436, 0.004629664588719606, -0.023107370361685753, -0.0342753604054451]\n"
     ]
    }
   ],
   "source": [
    "\"\"\"For basic init and call\"\"\"\n",
    "import os\n",
    "\n",
    "from langchain_community.embeddings import VolcanoEmbeddings\n",
    "\n",
    "os.environ[\"VOLC_ACCESSKEY\"] = \"\"\n",
    "os.environ[\"VOLC_SECRETKEY\"] = \"\"\n",
    "\n",
    "embed = VolcanoEmbeddings(volcano_ak=\"\", volcano_sk=\"\")\n",
    "print(\"embed_documents result:\")\n",
    "res1 = embed.embed_documents([\"foo\", \"bar\"])\n",
    "for r in res1:\n",
    "    print(\"\", r[:8])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "ExecuteTime": {
     "start_time": "2023-12-14T03:05:29.859276Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "embed_query result:\n",
      " [0.01987231895327568, -0.026041055098176003, -0.08395249396562576, 0.020043574273586273, -0.028862033039331436, 0.004629664588719606, -0.023107370361685753, -0.0342753604054451]\n"
     ]
    }
   ],
   "source": [
    "print(\"embed_query result:\")\n",
    "res2 = embed.embed_query(\"foo\")\n",
    "print(\"\", r[:8])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "start_time": "2023-12-14T03:05:29.860282Z"
    }
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.18"
  },
  "vscode": {
   "interpreter": {
    "hash": "6fa70026b407ae751a5c9e6bd7f7d482379da8ad616f98512780b705c84ee157"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}