run-llama--llama_index/docs/examples/embeddings/fireworks.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>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Fireworks Embeddings\n",
    "\n",
    "This guide shows you how to use Fireworks Embeddings through [Fireworks Endpoints](https://readme.fireworks.ai/)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "First, let's install LlamaIndex and the Fireworks dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%pip install llama-index-embeddings-fireworks"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install llama-index"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can then query embeddings on Fireworks"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from llama_index.embeddings.fireworks import FireworksEmbedding\n",
    "\n",
    "embed_model = FireworksEmbedding(api_key=\"YOUR API KEY\", embed_batch_size=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "768 [-0.67973792552948, 1.5226128101348877, -3.9547336101531982, 0.3112764358520508, -0.19723102450370789, 1.8839401006698608, -1.1595842838287354, -0.20612922310829163, 0.16740809381008148, -0.9071207046508789]\n"
     ]
    }
   ],
   "source": [
    "# Basic embedding example\n",
    "embeddings = embed_model.get_text_embedding(\"How do I sail to the moon?\")\n",
    "print(len(embeddings), embeddings[:10])"
   ]
  }
 ],
 "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
}