AI Agent Fails to Retrieve Data from Fabric Data Agent – "Error in information retrieving"

Question

AI Agent Fails to Retrieve Data from Fabric Data Agent – "Error in information retrieving"

Yasiru Randika 5

I'm running into an issue while trying to integrate an AI Agent with a Microsoft Fabric Data Agent, and I’d appreciate any help or insights from the community.

Setup Details

Tenant: Both Microsoft Fabric and AI Foundry are within the same tenant.

User Account: I’m using the same user account to access both services.

Data Agent: During setup, the Fabric Data Agent was created without any errors, and the connection appeared to be established successfully at that stage (i.e., no issues were raised during the creation process).

Knowledge Source: The AI Agent is configured to use the Fabric Data Agent as a knowledge source.

The Problem

When I query the AI Agent, it doesn’t return any response based on data from the Fabric Data Agent.

Even when I explicitly instruct the agent to use the Fabric Data Agent, it fails and returns an error message like:

"error in information retrieving."

What I’ve Checked

The Data Agent connection setup did not show any issues during creation.

The AI Agent recognizes the Fabric Data Agent as a knowledge source.

I’m using a Lakehouse as the backing data source in Fabric.

My Question

Are there any specific permissions, role assignments, or workspace/data-level configurations required to enable the AI Agent to successfully query and retrieve data from a Fabric Data Agent?

For instance:

Does the AI Agent need explicit access to the workspace or the Lakehouse?

Is there a way to validate or simulate queries from the AI Agent to ensure it can see the data?

Could this be related to metadata exposure, indexing issues, or a schema-related mismatch?

Any guidance or pointers from those who’ve successfully set this up would be greatly appreciated. Thanks!I'm running into an issue while trying to integrate an AI Agent with a Microsoft Fabric Data Agent, and I’d appreciate any help or insights from the community.

Setup Details

Tenant: Both Microsoft Fabric and AI Foundry are within the same tenant.

User Account: I’m using the same user account to access both services.

Data Agent: During setup, the Fabric Data Agent was created without any errors, and the connection appeared to be established successfully at that stage (i.e., no issues were raised during the creation process).

Knowledge Source: The AI Agent is configured to use the Fabric Data Agent as a knowledge source.

The Problem

When I query the AI Agent, it doesn’t return any response based on data from the Fabric Data Agent.

Even when I explicitly instruct the agent to use the Fabric Data Agent, it fails and returns an error message like:

"error in information retrieving."

What I’ve Checked

The Data Agent connection setup did not show any issues during creation.

The AI Agent recognizes the Fabric Data Agent as a knowledge source.

I’m using a Lakehouse as the backing data source in Fabric.

My Question

Are there any specific permissions, role assignments, or workspace/data-level configurations required to enable the AI Agent to successfully query and retrieve data from a Fabric Data Agent?

Any guidance or pointers from those who’ve successfully set this up would be greatly appreciated. Thanks!

Saideep Anchuri 6,690 Reputation points Microsoft External Staff

2025-04-28T15:06:40.2733333+00:00

HI Yasiru Randika

Just checking in to see if the below answer provided by @Sina Salam helped.

Thank You.
Zain Baquar 0 Reputation points

2025-05-01T18:23:00.52+00:00

Did you ever find a solution for this? I am facing the same issue

1 answer

Your answer

Saideep Anchuri 6,690 Reputation points Microsoft External Staff

2025-04-28T15:06:40.2733333+00:00

HI Yasiru Randika

Just checking in to see if the below answer provided by @Sina Salam helped.

Thank You.
Zain Baquar 0 Reputation points

2025-05-01T18:23:00.52+00:00

Did you ever find a solution for this? I am facing the same issue

Answer 1

Sina Salam 19,616

Hello Yasiru Randika,

Welcome to the Microsoft Q&A and thank you for lucid explanatory and posting your questions here.

I understand that you are having multiple issues regarding your explanations.

Since you're knowledgeable in what you're doing and to prevent long answer, I will recommend the below checklist to troubleshoot those issues:

About Workspace access, even though you're using the same user account, make sure AI Agent has access to the Fabric workspace and Lakehouse. The AI Agent's service principal or your user has must have read permissions to both the workspace and the Lakehouse. Also, if the agent uses a managed identity or application registration, ensure it has data reader roles.
About Lakehouse access, make sure row/table-level permissions are intact. Have simple, flat schemas initially (avoid complex types during testing.
In your table configuration, make sure tables are loaded, and flat-structured.
About Data Agent config, check right tables are exposed, reindex if needed.
In your Logs, check for query logs or diagnostics from the AI Agent for more detail information about the issue.
Review Microsoft documentation for known issues - https://learn.microsoft.com/en-us/fabric/known-issues/known-issue-1047-ai-skill-creation-fails-tenant-settings-restricted-security-groups?source=recommendations

I hope this is helpful! Do not hesitate to let me know if you have any other questions or clarifications.

Please don't forget to close up the thread here by upvoting and accept it as an answer if it is helpful.

Yasiru Randika 5 Reputation points

2025-05-04T11:15:19.7566667+00:00
Hi @Sina Salam , Sorry for the delayed response, and thank you for your detailed guidance.

Based on your inputs, I’ve gone through and verified that all the suggested criteria have been met:

The service principal has been granted access to both the workspace and the Lakehouse.

The Lakehouse table is loaded and has a simple, flat structure with no row-level or column-level security applied.

The relevant tables have been exposed in the Data Agent configuration.

I’ll also be collecting and sharing the logs from the AI Agent via the AI Foundry for further insights.

Thanks again for your support, and I’ll keep you posted with the log details.

CC - @saideep anchuri

Error from Log:

"step_details": { 48 "type": "tool_calls", 49 "tool_calls": [ 50 { 51 "id": "call_4WiIM16llRKIpdjgXog5y0OO", 52 "type": "fabric_dataagent", 53 "fabric_dataagent": { 54 "input": "fact_Class details", 55 "output": "Failed to retrieve data from conversational data retrieval service." 56 } 57 } 58 ] 59 }
Sina Salam 19,616 Reputation points

2025-05-04T15:39:00.24+00:00
Hello Yasiru Randika,

Thank you for your feedback.

From your response and logs, the following new and implicit issues arise:

“fact_Class details” appears to be a malformed or ambiguous query which lacks natural language format. This could confuse the AI pipeline’s semantic parsing or schema matching engine.

You haven't confirmed semantic model creation, without this, conversational agents won't work.

Lastly, the tool_call block suggests low-level failure in Fabric tool pipeline this may require re-registration of the Fabric Data Agent or a specific retrigger of the AI knowledge indexing pipeline.

NOTE: Kindly note the followings and best approach:

Microsoft Fabric requires a semantic model (created in Power BI Desktop or via Lakehouse tables using DirectLake or import mode) to enable AI Foundry agents to query structured data. - https://learn.microsoft.com/en-us/fabric/data-warehouse/semantic-model-overview

In the Data Agent configuration pane, ensure:

Tables are added explicitly.

Metadata extraction is successful (via Preview).

Ensure “Enable for query” is toggled.

Use a test SQL query in the Fabric workspace to validate. - https://learn.microsoft.com/en-us/fabric/data-activator/data-agent-overview

Data Agent to Retrieval Pipeline Misconfiguration

Check if the table is visible in AI Foundry's data preview.

Rebuild or republish the Lakehouse.

Use the Diagnostic feature from Fabric AI integration to simulate a test query.

Validate if Fabric Data Agent’s connector status shows as “Healthy”. - https://learn.microsoft.com/en-us/fabric/known-issues/known-issue-1047-ai-skill-creation-fails-tenant-settings-restricted-security-groups and https://learn.microsoft.com/en-us/fabric/data-activator/data-agent-ai

Use the checklist below to ascertain your progress and my explanation, also check detailed steps in the associated links:

Create and Publish a Semantic Model - https://learn.microsoft.com/en-us/fabric/data-warehouse/semantic-model-overview

Reconfigure Fabric Data Agent - https://learn.microsoft.com/en-us/fabric/data-activator/data-agent-ai

Validate Permissions. Because, if using same user, the agent may operate under a service principal. - https://learn.microsoft.com/en-us/fabric/security/workspace-permissions

Test with a Natural Language Query - Avoid structured phrases like "fact_Class details" as they don't align with LLM-based interpretation.

Use Logs to Debug Further - https://learn.microsoft.com/en-us/fabric/monitor/

Looking forward to reading about your progress and success.

Share via

AI Agent Fails to Retrieve Data from Fabric Data Agent – "Error in information retrieving"

1 answer

Your answer