updating notebooks

Author: aayush3011

Python/CosmosDB-MongoDB-vCore-Integrations/LangChain-CosmosDBMongovCoreVectorSearch-AzureOpenAI.ipynb

@@ -5,7 +5,9 @@
    "id": "817264fe",
    "metadata": {},
    "source": [
-    "In this tutorial, we'll demonstrate how to leverage a pdf files sample dataset(abstracts from Computer Vision and Pattern Recognition 2019 conference) stored in Azure Cosmos DB for MongoDB vCore to ground OpenAI models using LangChain. We'll do this taking advantage of Azure Cosmos DB for Mongo DB vCore's vector similarity search functionality. In the end, we'll create an interative chat session with the GPT-3.5 completions model to answer questions informed by our dataset. This process is known as Retrieval Augmented Generation, or RAG."
+    "In this tutorial, we'll demonstrate how to leverage a pdf files sample dataset(abstracts from Computer Vision and Pattern Recognition 2019 conference) stored in Azure Cosmos DB for MongoDB vCore to ground OpenAI models using LangChain. We'll do this taking advantage of Azure Cosmos DB for Mongo DB vCore's vector similarity search functionality. In the end, we'll create an interative chat session with the GPT-3.5 completions model to answer questions informed by our dataset. This process is known as Retrieval Augmented Generation, or RAG.\n",
+    "\n",
+    "Read more about vector search using Azure Cosmos Mongo vCore [here](https://learn.microsoft.com/en-us/azure/cosmos-db/mongodb/vcore/vector-search)"
    ]
   },
   {
@@ -24,16 +26,6 @@
     "![image.png](attachment:image.png)"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "f8510e26",
-   "metadata": {},
-   "source": [
-    "## Table of Contents\n",
-    "### [Step by Step Retrieval Augmented Generation](#RAG)\n",
-    "### [Interactive Chat Bot](#ChatBot)"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 1,

Python/CosmosDB-NoSQL-Integrations/LangChain-CosmosDBNoSQL-AzureOpenAI.ipynb

@@ -15,6 +15,9 @@
     "\n",
     "RAG (Retrieval-Augmented Generation) is an AI framework that combines the strengths of traditional information retrieval systems (such as databases) with the capabilities of generative large language models (LLMs)\n",
     "\n",
+    "Read more about vector search using Azure CosmosDB No SQL [here](https://learn.microsoft.com/en-us/azure/cosmos-db/nosql/vector-search)\n",
+    "\n",
+    "\n",
     "![image.png](attachment:image.png)"
    ]
   },
@@ -894,31 +897,6 @@
     "    return response"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "921fc3a3",
-   "metadata": {},
-   "source": [
-    "## Insert documents in the container using CosmosDB APIs"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 123,
-   "id": "6286ae44",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# import uuid\n",
-    "# for i in range(0, len(documents)):\n",
-    "#     item = {\n",
-    "#         'id': str(uuid.uuid4()),  # Ensure 'id' is a string\n",
-    "#         'text': documents[i].page_content,\n",
-    "#         'embedding': generate_embeddings(documents[i].page_content),        \n",
-    "#     }\n",
-    "#     container.create_item(body=item)"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "d7ef9e52",