run-llama--llama_index/docs/examples/embeddings/OpenAI.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a href=\"https://colab.research.google.com/github/run-llama/llama_index/blob/main/docs/examples/embeddings/OpenAI.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# OpenAI Embeddings"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "If you're opening this Notebook on colab, you will probably need to install LlamaIndex 🦙."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%pip install llama-index-embeddings-openai"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install llama-index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "\n",
    "os.environ[\"OPENAI_API_KEY\"] = \"sk-...\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from llama_index.embeddings.openai import OpenAIEmbedding\n",
    "from llama_index.core import Settings\n",
    "\n",
    "embed_model = OpenAIEmbedding(embed_batch_size=10)\n",
    "Settings.embed_model = embed_model"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Using OpenAI `text-embedding-3-large` and `text-embedding-3-small`\n",
    "\n",
    "Note, you may have to update your openai client: `pip install -U openai`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# get API key and create embeddings\n",
    "from llama_index.embeddings.openai import OpenAIEmbedding\n",
    "\n",
    "embed_model = OpenAIEmbedding(model=\"text-embedding-3-large\")\n",
    "\n",
    "embeddings = embed_model.get_text_embedding(\n",
    "    \"Open AI new Embeddings models is great.\"\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[-0.011500772088766098, 0.02457442320883274, -0.01760469563305378, -0.017763426527380943, 0.029841400682926178]\n"
     ]
    }
   ],
   "source": [
    "print(embeddings[:5])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "3072\n"
     ]
    }
   ],
   "source": [
    "print(len(embeddings))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# get API key and create embeddings\n",
    "from llama_index.embeddings.openai import OpenAIEmbedding\n",
    "\n",
    "embed_model = OpenAIEmbedding(\n",
    "    model=\"text-embedding-3-small\",\n",
    ")\n",
    "\n",
    "embeddings = embed_model.get_text_embedding(\n",
    "    \"Open AI new Embeddings models is awesome.\"\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1536\n"
     ]
    }
   ],
   "source": [
    "print(len(embeddings))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Change the dimension of output embeddings\n",
    "Note: Make sure you have the latest OpenAI client"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "512\n"
     ]
    }
   ],
   "source": [
    "# get API key and create embeddings\n",
    "from llama_index.embeddings.openai import OpenAIEmbedding\n",
    "\n",
    "\n",
    "embed_model = OpenAIEmbedding(\n",
    "    model=\"text-embedding-3-large\",\n",
    "    dimensions=512,\n",
    ")\n",
    "\n",
    "embeddings = embed_model.get_text_embedding(\n",
    "    \"Open AI new Embeddings models with different dimensions is awesome.\"\n",
    ")\n",
    "print(len(embeddings))"
   ]
  }
 ],
 "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"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}