Update AISearch_RAG_chatbot.ipynb with link to embeddings demo

Author: zbyosufzai

notebooks/GenAI/notebooks/AISearch_RAG_chatbot.ipynb

@@ -9,7 +9,7 @@
     "**Skill Level: Intermediate**\n",
     "\n",
     "## Overview \n",
-    "This tutorial provides a step-by-step guide on how to pull files from [Azure Blob Storage](https://learn.microsoft.com/en-us/azure/storage/blobs/storage-blobs-introduction), generate embeddings for these files, and store the embeddings in an [Azure AI Search](https://learn.microsoft.com/en-us/azure/search/search-what-is-azure-search) index. Embeddings are numerical representations of text that capture the semantic meaning of the content, facilitating advanced search and analysis. An index in AI search is a data structure that organizes these embeddings to improve the speed and efficiency of search queries. Additionally, this tutorial demonstrates how to enable users to interact with these embedding indexes through Azure AI Search and [Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-services/openai/overview), effectively allowing them to chat over the original files from Azure Blob Storage.\n",
+    "This tutorial provides a step-by-step guide on how to pull files from [Azure Blob Storage](https://learn.microsoft.com/en-us/azure/storage/blobs/storage-blobs-introduction), generate embeddings for these files, and store the embeddings in an [Azure AI Search](https://learn.microsoft.com/en-us/azure/search/search-what-is-azure-search) index. Embeddings are numerical representations of text that capture the semantic meaning of the content, facilitating advanced search and analysis. An index in AI search is a data structure that organizes these embeddings to improve the speed and efficiency of search queries. Additionally, this tutorial demonstrates how to enable users to interact with these embedding indexes through Azure AI Search and [Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-services/openai/overview), effectively allowing them to chat over the original files from Azure Blob Storage. After this tutorial, feel free to take a look at the [embeddings demos](../embedding_demos/readme.md) where you will have the chance to run a Streamlit app that will build a user interface with the same steps as this tutorial to vectorize and retrieve your data. Especially try out the **Embeddings** and **AI Search Query** (select **Retrieval** on this page) pages to get the feel of deploying a chatbot with a user interface.\n",
     "## Learning Objectives  \n",
     "1. **Vectorization**:\n",
     "    - Learn how to extract files from Azure Blob Storage.\n",
@@ -874,7 +874,9 @@
     "3. **Retrieve**:\n",
     "    - Implemented a function to perform retrieval queries over the documents indexed in Azure AI Search using Azure OpenAI.\n",
     "    - Executed a user query and performed a search using Azure AI Search.\n",
-    "    - Generated a chat completion based on the search results and formatted it for display."
+    "    - Generated a chat completion based on the search results and formatted it for display.\n",
+    "\n",
+    "Now that you have vectorized and retrieved your data, feel free to head to the [embeddings demos](../embedding_demos/readme.md) folder where you will have the chance to run a Streamlit app that will build a user interface with the same steps as this tutorial. Since we have already vectorized our data, try out the **Embeddings** and **AI Search Query** (select **Retrieval** option) pages to get a feel of how to run a chatbot with a user interface."
    ]
   },
   {