You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This advanced guide covers how the semantic index powers Retrieval-Augmented Generation (RAG) to provide accurate, context-aware AI responses. We’ll explore how these concepts work together to ensure your copilot retrieves relevant information from your data and returns grounded answers.
11
11
12
12
## Advanced Topics
13
13
14
-
Talk about RAG, Grounding, semantic index
15
-
16
14
### Semantic index
17
15
18
16
[Learn more about semantic index for Microsoft 365 Copilot here](/microsoftsearch/semantic-index-for-copilot)
@@ -33,7 +31,7 @@ The data is used by the LLM to inform and construct the response
33
31
34
32
### Grounding
35
33
36
-
Grounding in the context of SPE copilot refers to the process of providing input sources to the large language model (LLM) related to the user's prompt. This helps improve the specificity of the prompt and ensures that the responses are relevant and actionable to the user's specific task. The data the copilot is grounded on will be on the contents of the container type in the copilot copilot application. Behind the scenes SPE copilot uses M365 Copilot, [learn more about it's architecture here](/copilot/microsoft-365/microsoft-365-copilot-architecture)
34
+
Grounding in the context of SPE copilot refers to the process of providing input sources to the large language model (LLM) related to the user's prompt. This helps improve the specificity of the prompt and ensures that the responses are relevant and actionable to the user's specific task. The data the copilot is grounded on will be on the contents of the container type in the copilot application. Behind the scenes SPE copilot uses M365 Copilot, [learn more about it's architecture here](/copilot/microsoft-365/microsoft-365-copilot-architecture)
Copy file name to clipboardexpand all lines: docs/embedded/concepts/declarative-agent/spe-da.md
+5-5
Original file line number
Diff line number
Diff line change
@@ -39,7 +39,7 @@ Files in SharePoint Embedded are naturally [semantic indexed](spe-da-adv.md#sema
39
39
40
40

41
41
42
-
With SharPoint Embedded copilots , you can further ground the LLMs reponses on [specific files or drive items.](spe-da-adv.md#scoping-your-declarative-agent-to-specific-content).
42
+
With SharPoint Embedded copilots , you can further ground the LLMs reponses on [specific files or drive items.](spe-da-adv.md#scoping-your-copilot-to-specific-content).
43
43
44
44
### Microsoft 365 Boundary
45
45
@@ -57,7 +57,7 @@ Currently, we offer a way to incorporate this feature into your custom applicati
57
57
58
58
#### SPE TypeScript React Application
59
59
60
-
Follow the [quick start guide](/embedded/tutorials/spe-da-vscode.md) to get started with a prebuilt sample application.
60
+
Follow the [quick start guide](../../tutorials/spe-da-vscode.md) to get started with a prebuilt sample application.
61
61
62
62
### API Documentation
63
63
@@ -73,7 +73,7 @@ Currently you need a M365 Copilot license enabled for your user to use SharePoin
73
73
74
74
### Should I use a standard or trial container type?
75
75
76
-
Once consumption-based billing is enabled, we will be disabling using this feature with Trial Container types and it will only be enabled on Standard container types going forward. Please follow this [guide](../concepts/app-concepts/containertypes.md) to get started on creating your Standard Container type.
76
+
Once consumption-based billing is enabled, we will be disabling using this feature with Trial Container types and it will only be enabled on Standard container types going forward. Please follow this [guide](../app-concepts/containertypes.md) to get started on creating your Standard Container type.
77
77
78
78
## SharePoint Embedded copilot Support
79
79
@@ -93,7 +93,7 @@ When you click the thumbs down button, a feedback dialog will appear. Please inc
93
93
94
94
##### DiscoverabilityDisabled
95
95
96
-
This [flag](admin-exp/developer-admin/dev-admin.md#container-type-configuration-properties) prevents copilot from discovering [drive items](/graph/api/resources/driveitem) in the specified container type. If you have an existing container type and are setting this value to false, please wait 24 hours to ensure the container type configuration is fully propagated before creating a new container, uploading files there, and trying out copilot on folders/files of that new container.
96
+
This [flag](../admin-exp/developer-admin/dev-admin.md#container-type-configuration-properties) prevents copilot from discovering [drive items](/graph/api/resources/driveitem) in the specified container type. If you have an existing container type and are setting this value to false, please wait 24 hours to ensure the container type configuration is fully propagated before creating a new container, uploading files there, and trying out copilot on folders/files of that new container.
97
97
98
98
Here is an example of setting the flag to false with [Set-SPOContainerTypeConfiguration](/powershell/module/SharePoint-online/set-spocontainertypeconfiguration#examples)
99
99
@@ -152,4 +152,4 @@ The iFrame used by SharePoint Embedded copilots attempts to authenticate using t
152
152
153
153
## Advanced Topics Overview
154
154
155
-
The [advanced topics](/embedded/concepts/declarative-agent/spe-da-adv.md) delve into how SharePoint Embedded copilots use a semantic index to facilitate Retrieval-Augmented Generation (RAG), ensuring responses are accurately grounded in your stored content. You’ll also learn how to scope your copilot to specific data sources, set up various file formats, and configure locale options to tailor the copilot experience. By exploring concepts like grounding, semantic indexing, and RAG workflows, you can optimize your copilot’s effectiveness and maintain security within the Microsoft 365 boundary.
155
+
The [advanced topics](spe-da-adv.md) delve into how SharePoint Embedded copilots use a semantic index to facilitate Retrieval-Augmented Generation (RAG), ensuring responses are accurately grounded in your stored content. You’ll also learn how to scope your copilot to specific data sources, set up various file formats, and configure locale options to tailor the copilot experience. By exploring concepts like grounding, semantic indexing, and RAG workflows, you can optimize your copilot’s effectiveness and maintain security within the Microsoft 365 boundary.
Copy file name to clipboardexpand all lines: docs/embedded/tutorials/spe-da-vscode.md
+4-4
Original file line number
Diff line number
Diff line change
@@ -14,8 +14,8 @@ ms.localizationpriority: high
14
14
> 1. You must specify a standard container type at creation time. Depending on the purpose, you may or may not need to provide your Azure Subscription ID. A container type set for trial purposes can't be converted for production; or vice versa.
15
15
> 1. You must use the latest version of SharePoint PowerShell to configure a container type. For permissions and the most current information about Windows PowerShell for SharePoint Embedded, see the documentation at [Intro to SharePoint Embedded Management Shell](/powershell/SharePoint/SharePoint-online/introduction-SharePoint-online-management-shell)
16
16
>
17
-
> - Set the **ChatEmbeddedHosts** property of your container type configuration to `http://localhost:8080` to be able to work through the quick start below, refer to [the CSP section above for more information](/embedded/concepts/spe-da.md#csp-policies)
18
-
> - Set the **DiscoverabilityDisabled** property of your container type configuration to `false` so that copilot can find the files in your created container refer to the [Discoverability Disabled section above for more information](/embedded/concepts/spe-da.md#discoverabilitydisabled)
17
+
> - Set the **ChatEmbeddedHosts** property of your container type configuration to `http://localhost:8080` to be able to work through the quick start below, refer to [the CSP section above for more information](../concepts/declarative-agent/spe-da.md#csp-policies)
18
+
> - Set the **DiscoverabilityDisabled** property of your container type configuration to `false` so that copilot can find the files in your created container refer to the [Discoverability Disabled section above for more information](../concepts/declarative-agent/spe-da.md#discoverabilitydisabled)
19
19
> - Ensure that copilot for Microsoft 365 is available for your organization. You have two ways to get a developer environment for copilot:
20
20
> - A sandbox Microsoft 365 tenant with M365 Copilot (available in limited preview through [TAP membership](https://developer.microsoft.com/microsoft-365/tap)).
21
21
> - An [eligible Microsoft 365 or Office 365 production environment](/microsoft-365-copilot/extensibility/prerequisites#customers-with-existing-microsoft-365-and-copilot-licenses) with a M365 Copilot license.
@@ -295,9 +295,9 @@ function App() {
295
295
### Quick Start
296
296
297
297
> [!NOTE]
298
-
> When using standard container types with the VS Code extension, [DisableDiscoverability](../concepts/spe-da.md#discoverabilitydisabled) and [Grant admin consent](/entra/identity/enterprise-apps/grant-admin-consent?pivots=portal) features are currently not supported. This will need to be done using the [SPO Admin Powershell](/powershell/sharepoint/sharepoint-online/connect-sharepoint-online).
298
+
> When using standard container types with the VS Code extension, [DisableDiscoverability](../concepts/declarative-agent/spe-da.md#discoverabilitydisabled) and [Grant admin consent](/entra/identity/enterprise-apps/grant-admin-consent?pivots=portal) features are currently not supported. This will need to be done using the [SPO Admin Powershell](/powershell/sharepoint/sharepoint-online/connect-sharepoint-online).
299
299
300
-
1. Follow this guide up to the [Load Sample App section](/embedded/getting-started/spembedded-for-vscode#load-sample-app) with the Visual Studio Code Extension
300
+
1. Follow this guide up to the [Load Sample App section](../getting-started/spembedded-for-vscode.md#load-sample-app) with the Visual Studio Code Extension
301
301
302
302
2. Within the extension, right click on the owning application, and select `Run sample apps -> Typescript + React + Azure Functions`
0 commit comments