{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a href=\"https://colab.research.google.com/github/run-llama/llama_index/blob/main/docs/examples/embeddings/text_embedding_inference.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Text Embedding Inference\n",
    "\n",
    "This notebook demonstrates how to configure `TextEmbeddingInference` embeddings.\n",
    "\n",
    "The first step is to deploy the embeddings server. For detailed instructions, see the [official repository for Text Embeddings Inference](https://github.com/huggingface/text-embeddings-inference). Or [tei-gaudi repository](https://github.com/huggingface/tei-gaudi) if you are deploying on Habana Gaudi/Gaudi 2. \n",
    "\n",
    "Once deployed, the code below will connect to and submit embeddings for inference."
   ]
  },
  {
   "attachments": {},
   "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-text-embeddings-inference"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install llama-index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from llama_index.embeddings.text_embeddings_inference import (\n",
    "    TextEmbeddingsInference,\n",
    ")\n",
    "\n",
    "\n",
    "embed_model = TextEmbeddingsInference(\n",
    "    model_name=\"BAAI/bge-large-en-v1.5\",  # required for formatting inference text,\n",
    "    timeout=60,  # timeout in seconds\n",
    "    embed_batch_size=10,  # batch size for embedding\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1024\n",
      "[0.010597229, 0.05895996, 0.022445679, -0.012046814, -0.03164673]\n"
     ]
    }
   ],
   "source": [
    "embeddings = embed_model.get_text_embedding(\"Hello World!\")\n",
    "print(len(embeddings))\n",
    "print(embeddings[:5])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1024\n",
      "[0.010597229, 0.05895996, 0.022445679, -0.012046814, -0.03164673]\n"
     ]
    }
   ],
   "source": [
    "embeddings = await embed_model.aget_text_embedding(\"Hello World!\")\n",
    "print(len(embeddings))\n",
    "print(embeddings[:5])"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "llama-index-4a-wkI5X-py3.11",
   "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": 2
}