added new structured index notebooks and docs

tutorials/README.md

@@ -16,9 +16,9 @@
 + [Open Data](#open)
 
 ## **Artificial Intelligence** <a name="ai"></a>
-Machine learning is a subfield of artificial intelligence that focuses on the development of algorithms and models that enable computers to learn from and make predictions or decisions based on data, without being explicitly programmed. Artificial intelligence and machine learning algorithms are being applied to a variety of biomedical research questions, ranging from image classification to genomic variant calling. Azure offers AI services through the Azure AI Studio, as well as Azure Machine Learning.
+Machine learning is a subfield of artificial intelligence that focuses on the development of algorithms and models that enable computers to learn from and make predictions or decisions based on data, without being explicitly programmed. Artificial intelligence and machine learning algorithms are being applied to a variety of biomedical research questions, ranging from image classification to genomic variant calling. Azure offers AI services through Azure AI Studio and Azure Machine Learning.
 
-See our suite of tutorials to learn more about [Gen AI on Azure](/tutorials/notebooks/GenAI/) that go over several Azure products such as [Azure AI Studio](/tutorials/notebooks/GenAI/Azure_AI_Studio_README.md), [Azure OpenAI](/tutorials/notebooks/GenAI/Azure_Open_AI_README.md) and [Azure AI Search](/tutorials/notebooks/GenAI/notebooks/Azure_Pubmed_chatbot.ipynb) and other tools like [Langchain](/tutorials/notebooks/GenAI/notebooks/AzureOpenAI-langchain.ipynb) to deploy, train, prompt, and implement techniques like [Retrieval-Augmented Generation (RAG)](/tutorials/notebooks/GenAI/notebooks/Azure_Pubmed_chatbot.ipynb) to GenAI models.
+See our suite of tutorials to learn more about [Gen AI on Azure](/tutorials/notebooks/GenAI/) that highlight Azure products such as [Azure AI Studio](/tutorials/notebooks/GenAI/Azure_AI_Studio_README.md), [Azure OpenAI](/tutorials/notebooks/GenAI/Azure_Open_AI_README.md) and [Azure AI Search](/tutorials/notebooks/GenAI/notebooks/Azure_Pubmed_chatbot.ipynb) and external tools like [Langchain](/tutorials/notebooks/GenAI/notebooks/AzureOpenAI-langchain.ipynb). These notebooks walk you through how to deploy, train, and query models, as well as how to implement techniques like [Retrieval-Augmented Generation (RAG)](/tutorials/notebooks/GenAI/notebooks/Azure_Pubmed_chatbot.ipynb). If you are interested in applying RAG to structured data like a csv file, we created one tutorials that walks you through how to index your csv using the [Azure UI](/docs/create_index_from_csv.md) and a query your database using a [notebook within Azure ML](/tutorials/notebooks/GenAI/notebooks/llm_query_csv.ipynb), and [one tutorial that runs all the necessary steps directly from a notebook](/tutorials/notebooks/GenAI/notebooks/azure_ai_search_structured.ipynb). 
 
  ## **Clinical Informatics with FHIR** <a name="ci"></a>
  Azure Health Data Services is a set of services that enables you to store, process, and analyze medical data in Azure. These services are designed to help organizations quickly connect disparate health data sources and formats, such as structured, imaging, and device data, and normalize it to be persisted in the cloud. At its core, Azure Health Data Services possesses the ability to transform and ingest data into FHIR (Fast Healthcare Interoperability Resources) format. This allows you to transform health data from legacy formats, such as HL7v2 or CDA, or from high-frequency IoT data in device proprietary formats to FHIR. This makes it easier to connect data stored in Azure Health Data Services with services across the Azure ecosystem, like Azure Synapse Analytics, and Azure Machine Learning (Azure ML).