Merge pull request #269417 from gourdsay/main

LLM feature update

Author: PMEds28

articles/data-manager-for-agri/concepts-llm-apis.md

@@ -1,19 +1,23 @@
 ---
-title: Using LLM APIs in Azure Data Manager for Agriculture
-description: Provides information on using natural language to query Azure Data Manager for Agriculture APIs 
+title: Using generative AI in Data Manager for Agriculture
+description: Provides information on using generative AI feature in Azure Data Manager for Agriculture 
 author: gourdsay
 ms.author: angour
 ms.service: data-manager-for-agri
 ms.topic: conceptual
-ms.date: 11/14/2023
+ms.date: 3/19/2024
 ms.custom: template-concept
 ---
 
-# About Azure Data Manager for Agriculture LLM APIs
+# About Generative AI and Data Manager for Agriculture
 
-Azure Data Manager for Agriculture brings together and transforms data to simplify the process of building digital agriculture and sustainability applications. With new large language model (LLM) APIs, others can develop copilots that turn data into insights on yield, labor needs, harvest windows and more—bringing generative AI to life in agriculture.
+The copilot templates for agriculture enable seamless retrieval of data stored in Data Manager for Agriculture so that farming-related context and insights can be queried in conversational context. These capabilities enable customers and partners to build their own agriculture copilots. Customers and partners can deliver insights to users around disease, yield, harvest windows and more, using actual planning, and observational data. While Data Manager for Agriculture isn't required to operationalize copilot templates for agriculture, the Data Manager enables customers to more easily integrate generative AI scenarios for their users. 
 
-Our LLM capability enables seamless selection of APIs mapped to farm operations today. In the time to come we'll add the capability to select APIs mapped to soil sensors, weather, and imagery type of data. The skills in our LLM capability allow for a combination of results, calculation of area, ranking, summarizing to help serve customer prompts. Our B2B customers can take the context from our data manager, add their own knowledge base, and get summaries, insights and answers to their data questions through our data manager LLM plugin using natural language.
+Many customers have proprietary data outside of our data manager, for example Agronomy PDFs, market price data etc. These customers can benefit from our orchestration framework that allows for plugins, embedded data structures, and sub processes to be selected as part of the query flow. 
+
+Customers with farm operations data in our data manager can use our plugins that enable seamless selection of APIs mapped to farm operations today. In the time to come we'll add the capability to select APIs mapped to soil sensors, weather, and imagery type of data. Our data manager focused plugin allows for a combination of results, calculation of area, ranking, summarizing to help serve customer prompts.
+
+Our copilot templates for agriculture make generative AI in agriculture a reality.
 
 > [!NOTE]
 >Azure might include preview, beta, or other pre-release features, services, software, or regions offered by Microsoft for optional evaluation ("Previews"). Previews are licensed to you as part of [**your agreement**](https://azure.microsoft.com/support) governing use of Azure, and subject to terms applicable to "Previews".
@@ -24,23 +28,23 @@ Our LLM capability enables seamless selection of APIs mapped to farm operations
 
 ## Prerequisites
 - An instance of [Azure Data Manager for Agriculture](quickstart-install-data-manager-for-agriculture.md)
-- An instance of [Azure OpenAI](../ai-services/openai/how-to/create-resource.md) created in your Azure subscription.
+- An instance of [Azure OpenAI](../ai-services/openai/how-to/create-resource.md) created in your Azure subscription
 - You need [Azure Key Vault](../key-vault/general/quick-create-portal.md)
 - You need [Azure Container Registry](../container-registry/container-registry-get-started-portal.md)
 
 > [!TIP]
 >To get started with testing our Azure Data Manager for Agriculture LLM Plugin APIs please fill in this onboarding [**form**](https://forms.office.com/r/W4X381q2rd). In case you need help then reach out to us at [email protected].
 
 ## High level architecture 
-The customer has full control as key component deployment is within the customer tenant.  Our feature is available to customers via a docker container, which needs to be deployed to the customers Azure App Service. 
+The customer has full control as key component deployment is within the customer tenant. Our feature is available to customers via a docker container, which needs to be deployed to the customers Azure App Service. 
 
 :::image type="content" source="./media/concepts-llm-apis/high-level-architecture.png" alt-text="Screenshot showing high level feature architecture.":::
 
-We recommend that you apply content and safety filters on your Azure OpenAI instance. Taking this step ensures that the LLM capability is aligned with guidelines from Microsoft’s Office of Responsible AI. Follow instructions on how to use content filters with Azure OpenAI service at this [link](../ai-services/openai/how-to/content-filters.md) to get started.
+We recommend that you apply content and safety filters on your Azure OpenAI instance. Taking this step ensures that the generative AI capability is aligned with guidelines from Microsoft’s Office of Responsible AI. Follow instructions on how to use content filters with Azure OpenAI service at this [link](../ai-services/openai/how-to/content-filters.md) to get started.
 
-## Current uses cases
+## Current farm operations related uses cases
 
-We support seamless selection of APIs mapped to farm operations today. This enables use cases that are based on tillage, planting, applications and harvesting type of farm operations. Here's a sample list of queries that you can test and use: 
+We support seamless selection of APIs mapped to farm operations today. This enables use cases that are based on tillage, planting, applications, and harvesting type of farm operations. Here's a sample list of queries that you can test and use: 
 
 * Show me active fields
 * What crop was planted in my field (use field name) 
@@ -54,9 +58,9 @@ We support seamless selection of APIs mapped to farm operations today. This enab
 * What is the average yield for my field (use field name) with crop (use crop name)
 * What is the effect of planting dates on yield for crop (use crop name) 
 
-These use cases help input providers to plan equipment, seeds, applications and related services and engage better with the farmer.
+These use cases help input providers to plan equipment, seeds, applications, and related services and engage better with the farmer.
 
 ## Next steps
 
-* Fill this onboarding [**form**](https://forms.office.com/r/W4X381q2rd) to get started with testing our LLM feature.
+* Fill this onboarding [**form**](https://forms.office.com/r/W4X381q2rd) to get started with testing our copilot templates feature.
 * View our Azure Data Manager for Agriculture APIs [here](/rest/api/data-manager-for-agri).

articles/data-manager-for-agri/release-notes.md

@@ -23,10 +23,15 @@ Azure Data Manager for Agriculture Preview is updated on an ongoing basis. To st
 
 [!INCLUDE [public-preview-notice.md](includes/public-preview-notice.md)]
 
+## March 2024
+
+### Copilot Templates for Agriculture
+Our copilot templates for agriculture enable seamless retrieval of data stored in our data manager and customers own data. Many customers have proprietary data outside of our data manager, for example Agronomy PDFs, market price data etc. Such customers can benefit from our orchestration framework that allows for plugins, embedded data structures, and sub processes to be selected as part of the query flow. While Data Manager for Agriculture isn't required to operationalize copilot templates for agriculture, the data manager enables customers to more easily integrate generative AI scenarios for their users. Learn more about this [here](concepts-llm-apis.md).
+
 ## November 2023
 
 ### LLM capability
-Our LLM capability enables seamless selection of APIs mapped to farm operations today. This enables use cases that are based on tillage, planting, applications and harvesting type of farm operations. In the time to come we'll add the capability to select APIs mapped to soil sensors, weather, and imagery type of data. The skills in our LLM capability allow for a combination of results, calculation of area, ranking, summarizing to help serve customer prompts. These capabilities enable others to build their own agriculture copilots that deliver insights to farmers. Learn more about this [here](concepts-llm-apis.md).
+Our LLM capability enables seamless selection of APIs mapped to farm operations today. This enables use cases that are based on tillage, planting, applications, and harvesting type of farm operations. In the time to come we'll add the capability to select APIs mapped to soil sensors, weather, and imagery type of data. The skills in our LLM capability allow for a combination of results, calculation of area, ranking, summarizing to help serve customer prompts. These capabilities enable others to build their own agriculture copilots that deliver insights to farmers. Learn more about this [here](concepts-llm-apis.md).
 
 ### Imagery enhancements
 We improved our satellite ingestion service. The improvements include:
@@ -43,18 +48,18 @@ Listing of activities by party ID and by activity ID is consolidated into a more
 ## October 2023
 
 ### Azure portal experience enhancement
-We released a new user friendly experience to install ISV solutions that are available for Azure Data Manager for Agriculture users. You can now go to your Azure Data Manager for Agriculture instance on the Azure portal, view and install available solutions in a seamless user experience. Today the ISV solutions available are from Bayer AgPowered services, you can see the marketplace listing [here](https://azuremarketplace.microsoft.com/marketplace/apps?search=bayer&page=1). You can learn more about installing ISV solutions [here](how-to-set-up-isv-solution.md).
+We released a new user friendly experience to install ISV solutions that are available for Azure Data Manager for Agriculture users. You can now go to your Azure Data Manager for Agriculture instance on the Azure portal, view, and install available solutions in a seamless user experience. Today the ISV solutions available are from Bayer AgPowered services, you can see the marketplace listing [here](https://azuremarketplace.microsoft.com/marketplace/apps?search=bayer&page=1). You can learn more about installing ISV solutions [here](how-to-set-up-isv-solution.md).
 
 ## July 2023
 
 ### Weather API update 
 We deprecated the old weather APIs from API version 2023-07-01. The old weather APIs are replaced with new simple yet powerful provider agnostic weather APIs. Have a look at the API documentation [here](/rest/api/data-manager-for-agri/#weather). 
 
 ### New farm operations connector
-We added support for Climate FieldView as a built-in data source. You can now auto sync planting, application and harvest activity files from FieldView accounts directly into Azure Data Manager for Agriculture. Learn more about this [here](concepts-farm-operations-data.md).
+We added support for Climate FieldView as a built-in data source. You can now auto sync planting, application, and harvest activity files from FieldView accounts directly into Azure Data Manager for Agriculture. Learn more about this [here](concepts-farm-operations-data.md).
 
 ### Common Data Model now with geo-spatial support
-We updated our data model to improve flexibility. The boundary object is deprecated in favor of a geometry property that is now supported in nearly all data objects. This change brings consistency to how space is handled across hierarchy, activity and observation themes. It allows for more flexible integration when ingesting data from a provider with strict hierarchy requirements. You can now sync data that might not perfectly align with an existing hierarchy definition and resolve the conflicts with spatial overlap queries. Learn more [here](concepts-hierarchy-model.md).
+We updated our data model to improve flexibility. The boundary object is deprecated in favor of a geometry property that is now supported in nearly all data objects. This change brings consistency to how space is handled across hierarchy, activity, and observation themes. It allows for more flexible integration when ingesting data from a provider with strict hierarchy requirements. You can now sync data that might not perfectly align with an existing hierarchy definition and resolve the conflicts with spatial overlap queries. Learn more [here](concepts-hierarchy-model.md).
 
 ## June 2023