Add multimodal rag notebook

Signed-off-by: Jael Gu <[email protected]>

bootcamp/tutorials/quickstart/cir_with_milvus.ipynb

@@ -34,6 +34,13 @@
     "!pip install --upgrade pymilvus openai datasets timm einops ftfy peft tqdm"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To enable the latest codes of Visualized BGE, we will download the official repository and then install with the source code."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 2,
@@ -57,8 +64,6 @@
    "source": [
     "### Download Data\n",
     "\n",
-    "In this tutorial, we will use \n",
-    "\n",
     "The following command will download the example data and extract to a local folder \"./images_folder\" including:\n",
     "\n",
     "- **amazon_fashion**: A subset of [Amazon Reviews 2023](https://github.com/hyp1231/AmazonReviews2023) as containing approximately 145 images from the category \"Amazon_Fashion\".\n",
@@ -81,7 +86,7 @@
    "source": [
     "### Load Embedding Model\n",
     "\n",
-    "In this tutorial, we will use the Visualized BGE model \"bge-visualized-base-en-v1.5\" to generate embeddings for both images and text. \n",
+    "We will use the Visualized BGE model \"bge-visualized-base-en-v1.5\" to generate embeddings for both images and text. \n",
     "\n",
     "**1. Download weight**"
    ]
@@ -139,7 +144,11 @@
    "source": [
     "## Load Data\n",
     "\n",
-    "### Generate embeddings"
+    "This section will load example images into the database with corresponding embeddings.\n",
+    "\n",
+    "### Generate embeddings\n",
+    "\n",
+    "Load all jpeg images from the data directory and apply the encoder to convert images to embeddings."
    ]
   },
   {
@@ -196,7 +205,14 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Insert into Milvus"
+    "### Insert into Milvus\n",
+    "\n",
+    "Insert images with corresponding paths and embeddings into Milvus collection.\n",
+    "\n",
+    "> As for the argument of `MilvusClient`:\n",
+    "> - Setting the `uri` as a local file, e.g. `./milvus_demo.db`, is the most convenient method, as it automatically utilizes [Milvus Lite](https://milvus.io/docs/milvus_lite.md) to store all data in this file.\n",
+    "> - If you have large scale of data, you can set up a more performant Milvus server on [docker or kubernetes](https://milvus.io/docs/quickstart.md). In this setup, please use the server uri, e.g.`http://localhost:19530`, as your `uri`.\n",
+    "> - If you want to use [Zilliz Cloud](https://zilliz.com/cloud), the fully managed cloud service for Milvus, adjust the `uri` and `token`, which correspond to the [Public Endpoint and Api key](https://docs.zilliz.com/docs/on-zilliz-cloud-console#free-cluster-details) in Zilliz Cloud."
    ]
   },
   {
@@ -248,7 +264,9 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Multimodal Search"
+    "## Multimodal Search\n",
+    "\n",
+    "Now we are ready to perform the advanced image search with query data composed of both image and text instruction."
    ]
   },
   {
@@ -260,7 +278,7 @@
     "query_image = os.path.join(\n",
     "    data_dir, \"clothes.jpg\"\n",
     ")  # Change to your own query image path\n",
-    "query_text = \"black tops of this style\"\n",
+    "query_text = \"black tops of this style\"  # Change to your own text instruction, or None\n",
     "\n",
     "# Generate query embedding given image and text instructions\n",
     "query_vec = encoder.encode_query(image_path=query_image, text=query_text)\n",