From b6a9d734a3ff052367834adaa1293444d57adc58 Mon Sep 17 00:00:00 2001 From: Timna Brown <24630902+brown9804@users.noreply.github.com> Date: Fri, 2 May 2025 09:09:28 -0600 Subject: [PATCH 1/8] updating from AI Skills to Data Agents --- .../DataScience/Data_Agents/.md | 105 ++++++++++++++++++ 1 file changed, 105 insertions(+) create mode 100644 Workloads-Specific/DataScience/Data_Agents/.md diff --git a/Workloads-Specific/DataScience/Data_Agents/.md b/Workloads-Specific/DataScience/Data_Agents/.md new file mode 100644 index 0000000..9f949fd --- /dev/null +++ b/Workloads-Specific/DataScience/Data_Agents/.md @@ -0,0 +1,105 @@ +# Demostration: Data Agents in Microsoft Fabric (Preview) + +Costa Rica + +[![GitHub](https://img.shields.io/badge/--181717?logo=github&logoColor=ffffff)](https://github.com/) +[brown9804](https://github.com/brown9804) + +Last updated: 2025-03-13 + +---------- + + +
+List of References (Click to expand) + +- [Fabric data agent concepts (preview)](https://learn.microsoft.com/en-us/fabric/data-science/concept-data-agent) +- [How to create a Fabric data agent (preview)](https://learn.microsoft.com/en-us/fabric/data-science/how-to-create-data-agent) +- [Fabric data agent example with the AdventureWorks dataset (preview)](https://learn.microsoft.com/en-us/fabric/data-science/data-agent-scenario): `This example sets up a Fabric data agent to enable conversational AI over enterprise data`. It connects to a lakehouse with the AdventureWorks dataset and allows users to ask natural language questions. The agent interprets queries, accesses data from sources like warehouses, semantic models, and KQL databases, and returns insights. It simplifies data interaction without requiring code or SQL. +- [Create a Fabric data agent (preview)](https://learn.microsoft.com/en-us/fabric/data-science/how-to-create-data-agent) + +
+ +
+Table of Content (Click to expand) + +- [Setup required](#setup-required) +- [How it works](#how-it-works) +- [Examples of what to ask](#examples-of-what-to-ask) + +
+ + +> AI skills in Microsoft Fabric enable users to `create conversational AI experiences that answer questions about data stored +> in lakehouses, warehouses, Power BI semantic models, and KQL databases`. These skills make data insights accessible and +> actionable, allowing users to `interact with data naturally and receive relevant answers without needing technical expertise`. +> You can create custom Q&A systems using generative AI, guiding the AI with instructions and examples to ensure it understands your organization's context and data. + +Key Features: +- Customizable Q&A Systems: Tailor the AI to answer specific questions relevant to your organization. +- Generative AI: Leverage advanced AI to interact with your data, enhancing data-driven decision-making. +- Ease of Use: Once set up, users can simply ask questions and get accurate answers without needing deep technical knowledge. + +## Setup required + +1. **F64 Fabric capacity or higher**: Ensure you have the appropriate Fabric capacity. +2. **Workspace configured with Fabric Capacity**: + + image + + + image + + +3. **Tenant switch enabled**: This feature must be activated. + - Enable tenant configuration for AI Skills: + + image + + - Enable tenant configuration for Copilot and AI: + + image + +4. **Cross-Geo sharing for AI enabled**: If relevant to your setup, this should be enabled. +5. **A Warehouse or Lakehouse with data**: You need to have data available in either a Warehouse or Lakehouse. + +## How it works + +1. Go to Data Science space: + + image + +2. Choose the name for the AI Skill instance: + + image + +3. Add data: + + image + +4. If new, choose the source/connection: + + image + +5. Relate tables, and start asking! + + image + +## Examples of what to ask + + +| **Question** | **Example of it looks** | +|------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------| +| **Data Exploration** | | +| - Can you provide an overview of this dataset?
- Are there any missing values or anomalies in this dataset? | image | +| What are the key variables in this data? | image | +| **Data Insights** | | +| What patterns or trends can you identify in this data? |image | +| Can you highlight any correlations between variables? | image | +| What are the outliers in this dataset? | image | + + +
+

Total Visitors

+ Visitor Count +
From d8ad1d1598b02de72c519fa9a3687aed1124e53f Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Fri, 2 May 2025 15:09:47 +0000 Subject: [PATCH 2/8] Update last modified date in Markdown files --- Workloads-Specific/DataScience/Data_Agents/.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Workloads-Specific/DataScience/Data_Agents/.md b/Workloads-Specific/DataScience/Data_Agents/.md index 9f949fd..4ac0ccd 100644 --- a/Workloads-Specific/DataScience/Data_Agents/.md +++ b/Workloads-Specific/DataScience/Data_Agents/.md @@ -5,7 +5,7 @@ Costa Rica [![GitHub](https://img.shields.io/badge/--181717?logo=github&logoColor=ffffff)](https://github.com/) [brown9804](https://github.com/brown9804) -Last updated: 2025-03-13 +Last updated: 2025-05-02 ---------- From c7fa5bcf1d74b9de4d1ce185fa13cbd39fa68a0f Mon Sep 17 00:00:00 2001 From: Timna Brown <24630902+brown9804@users.noreply.github.com> Date: Fri, 2 May 2025 09:11:15 -0600 Subject: [PATCH 3/8] renamed --- .../DataScience/{Data_Agents/.md => Data_Agents.md} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename Workloads-Specific/DataScience/{Data_Agents/.md => Data_Agents.md} (100%) diff --git a/Workloads-Specific/DataScience/Data_Agents/.md b/Workloads-Specific/DataScience/Data_Agents.md similarity index 100% rename from Workloads-Specific/DataScience/Data_Agents/.md rename to Workloads-Specific/DataScience/Data_Agents.md From 20cf162ce2f9a0c7cbc14588726a62a0ae1975b5 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Fri, 2 May 2025 15:11:34 +0000 Subject: [PATCH 4/8] Fix Markdown syntax issues --- Workloads-Specific/DataScience/Data_Agents.md | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/Workloads-Specific/DataScience/Data_Agents.md b/Workloads-Specific/DataScience/Data_Agents.md index 4ac0ccd..d20381c 100644 --- a/Workloads-Specific/DataScience/Data_Agents.md +++ b/Workloads-Specific/DataScience/Data_Agents.md @@ -9,7 +9,6 @@ Last updated: 2025-05-02 ---------- -
List of References (Click to expand) @@ -29,13 +28,13 @@ Last updated: 2025-05-02
- > AI skills in Microsoft Fabric enable users to `create conversational AI experiences that answer questions about data stored > in lakehouses, warehouses, Power BI semantic models, and KQL databases`. These skills make data insights accessible and > actionable, allowing users to `interact with data naturally and receive relevant answers without needing technical expertise`. > You can create custom Q&A systems using generative AI, guiding the AI with instructions and examples to ensure it understands your organization's context and data. Key Features: + - Customizable Q&A Systems: Tailor the AI to answer specific questions relevant to your organization. - Generative AI: Leverage advanced AI to interact with your data, enhancing data-driven decision-making. - Ease of Use: Once set up, users can simply ask questions and get accurate answers without needing deep technical knowledge. @@ -47,10 +46,8 @@ Key Features: image - image - 3. **Tenant switch enabled**: This feature must be activated. - Enable tenant configuration for AI Skills: @@ -87,7 +84,6 @@ Key Features: ## Examples of what to ask - | **Question** | **Example of it looks** | |------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------| | **Data Exploration** | | @@ -98,7 +94,6 @@ Key Features: | Can you highlight any correlations between variables? | image | | What are the outliers in this dataset? | image | -

Total Visitors

Visitor Count From fbba0b4aec2fd7ff274ae1af9b765e6d1aa98098 Mon Sep 17 00:00:00 2001 From: Timna Brown <24630902+brown9804@users.noreply.github.com> Date: Fri, 2 May 2025 10:46:22 -0600 Subject: [PATCH 5/8] setup required in place --- Workloads-Specific/DataScience/Data_Agents.md | 21 +++++++------------ 1 file changed, 8 insertions(+), 13 deletions(-) diff --git a/Workloads-Specific/DataScience/Data_Agents.md b/Workloads-Specific/DataScience/Data_Agents.md index d20381c..d0b1873 100644 --- a/Workloads-Specific/DataScience/Data_Agents.md +++ b/Workloads-Specific/DataScience/Data_Agents.md @@ -41,24 +41,19 @@ Key Features: ## Setup required -1. **F64 Fabric capacity or higher**: Ensure you have the appropriate Fabric capacity. -2. **Workspace configured with Fabric Capacity**: +1. Please ensure you read all the [prerequisites](https://learn.microsoft.com/en-us/fabric/data-science/how-to-create-data-agent#prerequisites) +2. **Tenant switch enabled**: These features must be activated as mentioned here [prerequisites](https://learn.microsoft.com/en-us/fabric/data-science/how-to-create-data-agent#prerequisites) + + https://github.com/user-attachments/assets/f0df6fb9-e139-4c97-9b68-a6ea05eb6584 + +3. **F2 Fabric capacity or higher**: Ensure you have the appropriate Fabric capacity. +4. **Workspace configured with Fabric Capacity**: image image -3. **Tenant switch enabled**: This feature must be activated. - - Enable tenant configuration for AI Skills: - - image - - - Enable tenant configuration for Copilot and AI: - - image - -4. **Cross-Geo sharing for AI enabled**: If relevant to your setup, this should be enabled. -5. **A Warehouse or Lakehouse with data**: You need to have data available in either a Warehouse or Lakehouse. +5. At least one of these: A warehouse, a lakehouse, one or more Power BI semantic models, or a KQL database with data. ## How it works From b5f1516cf0cfd0f03a16559fe930986cd7777c93 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Fri, 2 May 2025 16:46:39 +0000 Subject: [PATCH 6/8] Fix Markdown syntax issues --- Workloads-Specific/DataScience/Data_Agents.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Workloads-Specific/DataScience/Data_Agents.md b/Workloads-Specific/DataScience/Data_Agents.md index d0b1873..945f6f1 100644 --- a/Workloads-Specific/DataScience/Data_Agents.md +++ b/Workloads-Specific/DataScience/Data_Agents.md @@ -44,7 +44,7 @@ Key Features: 1. Please ensure you read all the [prerequisites](https://learn.microsoft.com/en-us/fabric/data-science/how-to-create-data-agent#prerequisites) 2. **Tenant switch enabled**: These features must be activated as mentioned here [prerequisites](https://learn.microsoft.com/en-us/fabric/data-science/how-to-create-data-agent#prerequisites) - https://github.com/user-attachments/assets/f0df6fb9-e139-4c97-9b68-a6ea05eb6584 + 3. **F2 Fabric capacity or higher**: Ensure you have the appropriate Fabric capacity. 4. **Workspace configured with Fabric Capacity**: From bb58e971ecaef43403ebd1c4ac39754480f9ff18 Mon Sep 17 00:00:00 2001 From: Timna Brown <24630902+brown9804@users.noreply.github.com> Date: Fri, 2 May 2025 11:10:41 -0600 Subject: [PATCH 7/8] adding visual guidance --- Workloads-Specific/DataScience/Data_Agents.md | 20 ++++++++----------- 1 file changed, 8 insertions(+), 12 deletions(-) diff --git a/Workloads-Specific/DataScience/Data_Agents.md b/Workloads-Specific/DataScience/Data_Agents.md index 945f6f1..b905f94 100644 --- a/Workloads-Specific/DataScience/Data_Agents.md +++ b/Workloads-Specific/DataScience/Data_Agents.md @@ -57,25 +57,21 @@ Key Features: ## How it works -1. Go to Data Science space: - - image +1. Go to the `workspace`, click on `+ New item`, search for `Data agent`, and select it. + + image -2. Choose the name for the AI Skill instance: +2. Choose the name for the Data agent instance: - image + https://github.com/user-attachments/assets/752734e4-f7f6-44a3-8ccb-069ac005a410 3. Add data: - image - -4. If new, choose the source/connection: - - image + https://github.com/user-attachments/assets/9800e74e-cbca-45ff-a712-bb2e8a095bb5 -5. Relate tables, and start asking! +4. Relate tables, and start asking! - image + image ## Examples of what to ask From ca813b0b212d9162735853d7ef2d111726ec1c94 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Fri, 2 May 2025 17:10:59 +0000 Subject: [PATCH 8/8] Fix Markdown syntax issues --- Workloads-Specific/DataScience/Data_Agents.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Workloads-Specific/DataScience/Data_Agents.md b/Workloads-Specific/DataScience/Data_Agents.md index b905f94..b9a895e 100644 --- a/Workloads-Specific/DataScience/Data_Agents.md +++ b/Workloads-Specific/DataScience/Data_Agents.md @@ -63,11 +63,11 @@ Key Features: 2. Choose the name for the Data agent instance: - https://github.com/user-attachments/assets/752734e4-f7f6-44a3-8ccb-069ac005a410 + 3. Add data: - https://github.com/user-attachments/assets/9800e74e-cbca-45ff-a712-bb2e8a095bb5 + 4. Relate tables, and start asking!