new: Added multi-gpu example

docs/examples/FastEmbed_Multi_GPU.ipynb

@@ -0,0 +1,148 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Fastembed Multi-GPU Tutorial\n",
+    "This tutorial demonstrates how to leverage multi-GPU support in Fastembed. Fastembed supports embedding text and images utilizing modern GPUs for acceleration. Let's explore how to use Fastembed with multiple GPUs step by step."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Prerequisites\n",
+    "To get started, ensure you have the following installed:\n",
+    "- Python 3.8 or later\n",
+    "- Fastembed (`pip install fastembed-gpu`)\n",
+    "- Refer to [this](https://github.com/qdrant/fastembed/blob/main/docs/examples/FastEmbed_GPU.ipynb) tutorial if you have issues in GPU dependencies\n",
+    "- Access to a multi-GPU server"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Multi-GPU using cuda argument with TextEmbedding Model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from fastembed import TextEmbedding\n",
+    "\n",
+    "# define the documents to embed\n",
+    "docs = [\"hello world\", \"flag embedding\"]\n",
+    "\n",
+    "# define gpu ids\n",
+    "device_ids = [0, 1]\n",
+    "\n",
+    "# initialize a TextEmbedding model using CUDA\n",
+    "embedding_model = TextEmbedding(\n",
+    "    model_name=\"sentence-transformers/all-MiniLM-L6-v2\",\n",
+    "    cuda=True,\n",
+    "    device_ids=device_ids,\n",
+    "    cache_dir=\"models\",\n",
+    ")\n",
+    "\n",
+    "# generate embeddings\n",
+    "embeddings = embedding_model.embed(docs, parallel=len(device_ids))\n",
+    "print(embeddings)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "In this snippet:\n",
+    "- `cuda=True` enables GPU acceleration.\n",
+    "- `device_ids=[0, 1]` specifies GPUs to use. Replace `[0, 1]` with your available GPU IDs."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Multi-GPU using cuda argument with ImageEmbedding"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from io import BytesIO\n",
+    "\n",
+    "import requests\n",
+    "from PIL import Image\n",
+    "from fastembed import ImageEmbedding\n",
+    "\n",
+    "\n",
+    "# load sample image\n",
+    "images = [Image.open(BytesIO(requests.get(\"https://qdrant.tech/img/logo.png\").content))]\n",
+    "\n",
+    "# define gpu ids\n",
+    "device_ids = [0, 1]\n",
+    "\n",
+    "# initialize ImageEmbedding model\n",
+    "image_model = ImageEmbedding(\n",
+    "    model_name=\"Qdrant/clip-ViT-B-32-vision\", cuda=True, device_ids=device_ids, cache_dir=\"models\"\n",
+    ")\n",
+    "\n",
+    "# generate image embeddings\n",
+    "image_embeddings = image_model.embed(images, parallel=len(device_ids))\n",
+    "print(image_embeddings)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Multi-GPU using Provider Options\n",
+    "For advanced users, Fastembed allows customization of ONNX runtime providers."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# customize provider options for CUDA\n",
+    "first_device_id = 0\n",
+    "second_device_id = 1\n",
+    "providers = [\n",
+    "    (\"CUDAExecutionProvider\", {\"device_id\": first_device_id}),\n",
+    "    (\"CUDAExecutionProvider\", {\"device_id\": second_device_id}),\n",
+    "]\n",
+    "\n",
+    "# initialize model with custom providers\n",
+    "custom_model = TextEmbedding(\n",
+    "    model_name=\"sentence-transformers/all-MiniLM-L6-v2\", providers=providers, cache_dir=\"models\"\n",
+    ")\n",
+    "\n",
+    "# generate embeddings\n",
+    "custom_embeddings = custom_model.embed(docs, parallel=2)\n",
+    "print(custom_embeddings)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.10.15"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}