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
Copy file name to clipboardExpand all lines: articles/ai-services/agents/concepts/standard-agent-setup.md
+10-11Lines changed: 10 additions & 11 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -27,18 +27,17 @@ Both standard setup configurations are designed to give you complete control ove
27
27
28
28
By bundling these BYO features (file storage, search, and thread storage), the standard setup guarantees that your deployment is secure by default. All data processed by Azure AI Foundry Agent Service is automatically stored at rest in your own Azure resources, helping you meet internal policies, compliance requirements, and enterprise security standards.
29
29
30
-
## Project-Level Data Isolation
30
+
### Azure Cosmos DB for NoSQL
31
+
32
+
Your existing Azure Cosmos DB for NoSQL Account used in standard setup must have a total throughput limit of at least **3000 RU/s**. Both **Provisioned Throughput** and **Serverless** modes are supported.
31
33
32
-
Azure AI Foundry enforces project-level data isolation by default. When you configure your own resources in the project capability host:
33
-
***Azure Storage**: Two Blob containers are automatically provisioned:
34
-
* One for uploaded files
35
-
* One for intermediate system data (for example, chunks, embeddings)
36
-
***Azure Cosmos DB**: Three containers are provisioned under a dedicated enterprise_memory database:
37
-
* thread-message-store: End-user conversations
38
-
* system-thread-message-store: Internal system messages
39
-
* agent-entity-store: Model inputs and outputs
34
+
When you use standard setup, **three containers** will be provisioned in your existing Cosmos DB account, and **each container requires 1000 RU/s**.
35
+
* thread-message-store: End-user conversations
36
+
* system-thread-message-store: Internal system messages
37
+
* agent-entity-store: Agent metadata including their instructions, tools, name, etc.
40
38
41
-
This default behavior was chosen to reduce configuration complexity while still enforcing strict data boundaries—ensuring each project has a clean, isolated storage footprint without requiring manual setup.
39
+
## Project-Level Data Isolation
40
+
Standard setup enforces project-level data isolation by default. Two blob storage containers will automatically be provisioned in your storage account, one for files and one for intermediate system data (chunks, embeddings) and three containers will be provisioned in your Cosmos DB, one for user systems, one for system messages, and one for user inputs related to created agents such as their instructions, tools, name, etc. This default behavior was chosen to reduce setup complexity while still enforcing strict data boundaries between projects.
42
41
43
42
## Capability hosts
44
43
**Capability hosts** are sub-resources on both the Account and Project, enabling interaction with the Azure AI Foundry Agent Service.
@@ -85,4 +84,4 @@ This default behavior was chosen to reduce configuration complexity while still
85
84
* Assign role: Cosmos DB Built-in Data Contributor
86
85
* Cosmos DB for NoSQL container: `<'${projectWorkspaceId}>-agent-entity-store'`
87
86
* Assign role: Cosmos DB Built-in Data Contributor
88
-
11. Once all resources are provisioned, all developers who want to create/edit agents in the project should be assigned the role: Azure AI User on the project scope.
87
+
11. Once all resources are provisioned, all developers who want to create/edit agents in the project should be assigned the role: Azure AI User on the project scope.
| Create an account and project | Azure AI Account Owner |
28
-
|**Standard Setup Only:** Assign RBAC for required resources (Cosmos DB, Search, Storage, etc.) | Role Based Access Administrator |
28
+
|**Standard Setup Only:** Assign RBAC for required resources (Cosmos DB, Search, Storage, etc.) | Role Based Access Control Administrator |
29
29
| Create and edit agents | Azure AI User |
30
30
31
31
## Set up your agent environment
@@ -37,7 +37,7 @@ Agents are scoped at the project level, which ensures data isolation—agents wi
37
37
* An Azure subscription - [Create one for free](https://azure.microsoft.com/free/cognitive-services).
38
38
* Ensure that the individual creating the account and project has the **Azure AI Account Owner** role at the subscription scope
39
39
* If configuring **Standard Setup**, the same individual must also have permissions to assign roles to required resources (Cosmos DB, Search, Storage).
40
-
* The built-in role needed is **Role Based Access Administrator**.
40
+
* The built-in role needed is **Role Based Access Control Administrator**.
41
41
* Alternatively, having the **Owner** role at the subscription level also satisfies this requirement.
42
42
* The key permission needed is: `Microsoft.Authorization/roleAssignments/write`
Copy file name to clipboardExpand all lines: articles/ai-services/agents/how-to/use-your-own-resources.md
+3Lines changed: 3 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -85,6 +85,9 @@ Use an existing AI Services / Azure OpenAI, Azure Storage account, Azure Cosmos
85
85
```
86
86
87
87
### Use an existing Azure Cosmos DB for NoSQL account for thread storage
88
+
**Azure Cosmos DB for NoSQL**
89
+
- Your existing Azure Cosmos DB for NoSQL Account used in standard setup must have at least a total throughput limit of at least 3000 RU/s. Both Provisioned Thoughtput and Serverless are supported.
90
+
- 3 containers will be provisioned in your existing Cosmos DB account and each need 1000 RU/s
88
91
89
92
1. To get your Azure Cosmos DB account resource ID, sign in to the Azure CLI and select the subscription with your account:
0 commit comments