cancel
Showing results forย 
Search instead forย 
Did you mean:ย 
Generative AI
Explore discussions on generative artificial intelligence techniques and applications within the Databricks Community. Share ideas, challenges, and breakthroughs in this cutting-edge field.
cancel
Showing results forย 
Search instead forย 
Did you mean:ย 

Genie Agents citation (bug)

haaland
Databricks Partner

Agent reponses are showing this kind of plain text at the end of its text reponses: 

:citation[genie_sql.01f1b7e5-18d5-196a-90f2-2601ef936192]

I think it is meant to be a clickable link. 
Will this be fixed soon?

1 ACCEPTED SOLUTION

Accepted Solutions

Ashwin_DSA
Databricks Employee
Databricks Employee

Hi @haaland,

Thanks for flagging this. The :citation[genie_sql...] text is supposed to render as a clickable reference link that lets you trace the answer back to the underlying SQL query. What you're seeing is a known rendering bug in which the citation markup passes through as raw text instead of being rendered as a clickable chip.

 
The Databricks engineering team is aware of this issue and is actively working on a fix. The bug is in the citation resolution layer, not in the answer generation itself, so the actual data and SQL behind the response are still correct. It's just the visual link that fails to render properly.
 
There is no workaround on the user side to fix this, since it's a platform-level rendering issue. In the meantime, you can still verify the SQL behind any Genie Agent response by clicking "Show generated code" in the response to inspect the query directly.
 
A fix is in progress and should be deployed soon. If you want to track the status, you can open a support ticket referencing this symptom so your workspace is flagged for follow-up once the fix rolls out.
 

If this answer resolves your question, could you mark it as โ€œAccept as Solutionโ€? That helps other users quickly find the correct fix.

Regards,
Ashwin | Delivery Solution Architect @ Databricks
Helping you build and scale the Data Intelligence Platform.
***Opinions are my own***

View solution in original post

3 REPLIES 3

Ashwin_DSA
Databricks Employee
Databricks Employee

Hi @haaland,

Thanks for flagging this. The :citation[genie_sql...] text is supposed to render as a clickable reference link that lets you trace the answer back to the underlying SQL query. What you're seeing is a known rendering bug in which the citation markup passes through as raw text instead of being rendered as a clickable chip.

 
The Databricks engineering team is aware of this issue and is actively working on a fix. The bug is in the citation resolution layer, not in the answer generation itself, so the actual data and SQL behind the response are still correct. It's just the visual link that fails to render properly.
 
There is no workaround on the user side to fix this, since it's a platform-level rendering issue. In the meantime, you can still verify the SQL behind any Genie Agent response by clicking "Show generated code" in the response to inspect the query directly.
 
A fix is in progress and should be deployed soon. If you want to track the status, you can open a support ticket referencing this symptom so your workspace is flagged for follow-up once the fix rolls out.
 

If this answer resolves your question, could you mark it as โ€œAccept as Solutionโ€? That helps other users quickly find the correct fix.

Regards,
Ashwin | Delivery Solution Architect @ Databricks
Helping you build and scale the Data Intelligence Platform.
***Opinions are my own***

ThiamLee
Contributor

Yeah, Iโ€™ve seen this too. Looks like the citation/link is being exposed as raw text instead of rendering properly. Hopefully itโ€™s just a UI/rendering bug and gets fixed soon.

Ashwin_DSA
Databricks Employee
Databricks Employee

Hi @haaland - I believe the fix has now been rolled out, and I have tested my sandbox workspace where citations are working correctly. Please check and let me know if you still face issues. Happy to follow up internally. 

 

Regards,
Ashwin | Delivery Solution Architect @ Databricks
Helping you build and scale the Data Intelligence Platform.
***Opinions are my own***