langchain/docs/extras/integrations/text_embedding/openai.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "278b6c63",
   "metadata": {},
   "source": [
    "# OpenAI\n",
    "\n",
    "Let's load the OpenAI Embedding class."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "0be1af71",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.embeddings import OpenAIEmbeddings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "2c66e5da",
   "metadata": {},
   "outputs": [],
   "source": [
    "embeddings = OpenAIEmbeddings()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "01370375",
   "metadata": {},
   "outputs": [],
   "source": [
    "text = \"This is a test document.\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "bfb6142c",
   "metadata": {},
   "outputs": [],
   "source": [
    "query_result = embeddings.embed_query(text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "91bc875d-829b-4c3d-8e6f-fc2dda30a3bd",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[-0.003186025367556387,\n",
       " 0.011071979803637493,\n",
       " -0.004020420763285827,\n",
       " -0.011658221276953042,\n",
       " -0.0010534035786864363]"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "query_result[:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "0356c3b7",
   "metadata": {},
   "outputs": [],
   "source": [
    "doc_result = embeddings.embed_documents([text])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "a4b0d49e-0c73-44b6-aed5-5b426564e085",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[-0.003186025367556387,\n",
       " 0.011071979803637493,\n",
       " -0.004020420763285827,\n",
       " -0.011658221276953042,\n",
       " -0.0010534035786864363]"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "doc_result[0][:5]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bb61bbeb",
   "metadata": {},
   "source": [
    "Let's load the OpenAI Embedding class with first generation models (e.g. text-search-ada-doc-001/text-search-ada-query-001). Note: These are not recommended models - see [here](https://platform.openai.com/docs/guides/embeddings/what-are-embeddings)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "c0b072cc",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.embeddings.openai import OpenAIEmbeddings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "a56b70f5",
   "metadata": {},
   "outputs": [],
   "source": [
    "embeddings = OpenAIEmbeddings(model=\"text-search-ada-doc-001\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "14aefb64",
   "metadata": {},
   "outputs": [],
   "source": [
    "text = \"This is a test document.\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "3c39ed33",
   "metadata": {},
   "outputs": [],
   "source": [
    "query_result = embeddings.embed_query(text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "2ee7ce9f-d506-4810-8897-e44334412714",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0.004452846988523035,\n",
       " 0.034550655976098514,\n",
       " -0.015029939040690051,\n",
       " 0.03827273883655212,\n",
       " 0.005785414075152477]"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "query_result[:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "e3221db6",
   "metadata": {},
   "outputs": [],
   "source": [
    "doc_result = embeddings.embed_documents([text])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "a0865409-3a6d-468f-939f-abde17c7cac3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0.004452846988523035,\n",
       " 0.034550655976098514,\n",
       " -0.015029939040690051,\n",
       " 0.03827273883655212,\n",
       " 0.005785414075152477]"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "doc_result[0][:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "aaad49f8",
   "metadata": {},
   "outputs": [],
   "source": [
    "# if you are behind an explicit proxy, you can use the OPENAI_PROXY environment variable to pass through\n",
    "os.environ[\"OPENAI_PROXY\"] = \"http://proxy.yourcompany.com:8080\""
   ]
  }
 ],
 "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": "3.9.1"
  },
  "vscode": {
   "interpreter": {
    "hash": "e971737741ff4ec9aff7dc6155a1060a59a8a6d52c757dbbe66bf8ee389494b1"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}