Raspawar/add vlm support

docs/docs/examples/multi_modal/nvidia_multi_modal.ipynb

@@ -0,0 +1,302 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_index/blob/main/docs/docs/examples/multi_modal/nvidia_multi_modal.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
+    "\n",
+    "# Multi-Modal LLM using NVIDIA endpoints for image reasoning\n",
+    "\n",
+    "In this notebook, we show how to use NVIDIA MultiModal LLM class/abstraction for image understanding/reasoning.\n",
+    "\n",
+    "We also show several functions we are now supporting for NVIDIA LLM:\n",
+    "* `complete` (both sync and async): for a single prompt and list of images\n",
+    "* `stream complete` (both sync and async): for steaming output of complete"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet llama-index-multi-modal-llms-nvidia llama-index-embeddings-nvidia llama-index-readers-file"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "# del os.environ['NVIDIA_API_KEY']  ## delete key and reset\n",
+    "if os.environ.get(\"NVIDIA_API_KEY\", \"\").startswith(\"nvapi-\"):\n",
+    "    print(\"Valid NVIDIA_API_KEY already in environment. Delete to reset\")\n",
+    "else:\n",
+    "    nvapi_key = getpass.getpass(\"NVAPI Key (starts with nvapi-): \")\n",
+    "    assert nvapi_key.startswith(\n",
+    "        \"nvapi-\"\n",
+    "    ), f\"{nvapi_key[:5]}... is not a valid key\"\n",
+    "    os.environ[\"NVIDIA_API_KEY\"] = nvapi_key"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.multi_modal.nvidia import NVIDIAMultiModal\n",
+    "import base64\n",
+    "from llama_index.core.schema import ImageDocument\n",
+    "from PIL import Image\n",
+    "import requests\n",
+    "from io import BytesIO\n",
+    "import matplotlib.pyplot as plt\n",
+    "from llama_index.core.multi_modal_llms.generic_utils import load_image_urls\n",
+    "\n",
+    "llm = NVIDIAMultiModal()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Initialize `OpenAIMultiModal` and Load Images from URLs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "image_urls = [\n",
+    "    \"https://res.cloudinary.com/hello-tickets/image/upload/c_limit,f_auto,q_auto,w_1920/v1640835927/o3pfl41q7m5bj8jardk0.jpg\",\n",
+    "    \"https://www.visualcapitalist.com/wp-content/uploads/2023/10/US_Mortgage_Rate_Surge-Sept-11-1.jpg\",\n",
+    "    \"https://www.sportsnet.ca/wp-content/uploads/2023/11/CP1688996471-1040x572.jpg\",\n",
+    "    # Add yours here!\n",
+    "]\n",
+    "\n",
+    "img_response = requests.get(image_urls[0])\n",
+    "img = Image.open(BytesIO(img_response.content))\n",
+    "plt.imshow(img)\n",
+    "\n",
+    "image_url_documents = load_image_urls(image_urls)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Complete a prompt with a bunch of images"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "response = llm.complete(\n",
+    "    prompt=f\"What is this image?\",\n",
+    "    image_documents=image_url_documents,\n",
+    ")\n",
+    "\n",
+    "print(response)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Steam Complete a prompt with a bunch of images"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "stream_complete_response = llm.stream_complete(\n",
+    "    prompt=f\"What is this image?\",\n",
+    "    image_documents=image_url_documents,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for r in stream_complete_response:\n",
+    "    print(r.text, end=\"\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "response_acomplete = await llm.acomplete(\n",
+    "    prompt=\"Describe the images as an alternative text\",\n",
+    "    image_documents=image_url_documents,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "##  Passing an image as a base64 encoded string"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "imgr_content = base64.b64encode(\n",
+    "    requests.get(\n",
+    "        \"https://helloartsy.com/wp-content/uploads/kids/cats/how-to-draw-a-small-cat/how-to-draw-a-small-cat-step-6.jpg\"\n",
+    "    ).content\n",
+    ").decode(\"utf-8\")\n",
+    "\n",
+    "response = llm.complete(\n",
+    "    prompt=\"List models in image\",\n",
+    "    image_documents=[ImageDocument(image=imgr_content, mimetype=\"jpeg\")],\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(response)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "##  Passing an image as an NVCF asset\n",
+    "If your image is sufficiently large or you will pass it multiple times in a chat conversation, you may upload it once and reference it in your chat conversation\n",
+    "\n",
+    "See https://docs.nvidia.com/cloud-functions/user-guide/latest/cloud-function/assets.html for details about how upload the image."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import requests\n",
+    "\n",
+    "content_type = \"image/jpg\"\n",
+    "description = \"example-image-from-lc-nv-ai-e-notebook\"\n",
+    "\n",
+    "create_response = requests.post(\n",
+    "    \"https://api.nvcf.nvidia.com/v2/nvcf/assets\",\n",
+    "    headers={\n",
+    "        \"Authorization\": f\"Bearer {os.environ['NVIDIA_API_KEY']}\",\n",
+    "        \"accept\": \"application/json\",\n",
+    "        \"Content-Type\": \"application/json\",\n",
+    "    },\n",
+    "    json={\"contentType\": content_type, \"description\": description},\n",
+    ")\n",
+    "create_response.raise_for_status()\n",
+    "\n",
+    "upload_response = requests.put(\n",
+    "    create_response.json()[\"uploadUrl\"],\n",
+    "    headers={\n",
+    "        \"Content-Type\": content_type,\n",
+    "        \"x-amz-meta-nvcf-asset-description\": description,\n",
+    "    },\n",
+    "    data=img_response.content,\n",
+    ")\n",
+    "upload_response.raise_for_status()\n",
+    "\n",
+    "asset_id = create_response.json()[\"assetId\"]\n",
+    "asset_id"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "response = llm.stream_complete(\n",
+    "    prompt=f\"Describe the image\",\n",
+    "    image_documents=[\n",
+    "        ImageDocument(metadata={\"asset_id\": asset_id}, mimetype=\"png\")\n",
+    "    ],\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "##  Passing images from local files"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core import SimpleDirectoryReader\n",
+    "\n",
+    "# put your local directore here\n",
+    "image_documents = SimpleDirectoryReader(\"./images_wiki\").load_data()\n",
+    "\n",
+    "response = llm.complete(\n",
+    "    prompt=\"Describe the images as an alternative text\",\n",
+    "    image_documents=image_documents,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(response)"
+   ]
+  }
+ ],
+ "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": 2
+}