Merge pull request #59 from RichmondAlake/main

Filling information gaps in the MongoDB notebook

notebooks/en/rag_with_hugging_face_gemma_mongodb.ipynb

@@ -1533,7 +1533,22 @@
     "\n",
     "6. This tutorial only requires the cluster's URI(unique resource identifier). Grab the URI and copy it into the Google Colabs Secrets environment in a variable named `MONGO_URI` or place it in a .env file or equivalent.\n",
     "\n",
-    "\n"
+    "\n",
+    "### 4.1 Database and Collection Setup\n",
+    "\n",
+    "Before moving forward, ensure the following prerequisites are met\n",
+    "- Database cluster set up on MongoDB Atlas\n",
+    "- Obtained the URI to your cluster\n",
+    "\n",
+    "For assistance with database cluster setup and obtaining the URI, refer to our guide for [setting up a MongoDB cluster](https://www.mongodb.com/docs/guides/atlas/cluster/) and [getting your connection string](https://www.mongodb.com/docs/guides/atlas/connection-string/)\n",
+    "\n",
+    "Once you have created a cluster, create the database and collection within the MongoDB Atlas cluster by clicking + Create Database in the cluster overview page. \n",
+    "\n",
+    "Here is a guide for [creating a database and collection](https://www.mongodb.com/basics/create-database)\n",
+    "\n",
+    "**The database will be named `movies`.**\n",
+    "\n",
+    "**The collection will be named `movie_collection_2`.**\n"
    ]
   },
   {
@@ -1545,9 +1560,12 @@
     "## Step 5: Create a Vector Search Index\n",
     "\n",
     "At this point make sure that your vector index is created via MongoDB Atlas.\n",
-    "Follow instructions here:\n",
     "\n",
-    "This next step is mandatory for conducting efficient and accurate vector-based searches based on the vector embeddings stored within the documents in the `movie_collection_2` collection. Creating a Vector Search Index enables the ability to traverse the documents efficiently to retrieve documents with embeddings that match the query embedding based on vector similarity. Go here to read more about [MongoDB Vector Search Index](https://www.mongodb.com/docs/atlas/atlas-search/field-types/knn-vector/).\n",
+    "This next step is mandatory for conducting efficient and accurate vector-based searches based on the vector embeddings stored within the documents in the `movie_collection_2` collection. \n",
+    "\n",
+    "Creating a Vector Search Index enables the ability to traverse the documents efficiently to retrieve documents with embeddings that match the query embedding based on vector similarity. \n",
+    "\n",
+    "Go here to read more about [MongoDB Vector Search Index](https://www.mongodb.com/docs/atlas/atlas-search/field-types/knn-vector/).\n",
     "\n",
     "\n",
     "```\n",