Update limitations and usage notes for Deep Research tool #587
Conversation
Clarified limitations of the Deep Research tool regarding streaming scenarios and provided guidance for using non-streaming mode.
|
@AhmadAbdullah91 : Thanks for your contribution! The author(s) and reviewer(s) have been notified to review your proposed change. |
|
Learn Build status updates of commit bd15c71: ✅ Validation status: passed
For more details, please refer to the build report. |
|
Can you review the proposed changes? IMPORTANT: When the changes are ready for publication, adding a #label:"aq-pr-triaged" |
There was a problem hiding this comment.
Pull Request Overview
This PR enhances the limitation note for the Deep Research tool by converting it from a single-item note to a bulleted list and adding a second limitation regarding the Azure AI Foundry Agent Playground UI.
Key changes:
- Converts the existing limitation about nonstreaming scenarios to a bulleted list item
- Adds a new limitation explaining that the Playground UI only supports streaming mode, which may cause connection drops and timeouts
| > [!NOTE] | ||
| > Limitation: The Deep Research tool is currently recommended only in nonstreaming scenarios. Using it with streaming can work, but it might occasionally time out and is therefore not recommended. | ||
| > * Limitation: The Deep Research tool is currently recommended only in nonstreaming scenarios. Using it with streaming can work, but it might occasionally time out and is therefore not recommended. | ||
| > * Currently, Azure AI Foundry Agent Playground UI only supports starting runs in streaming mode, and as a result, users might expect connection drops and timeouts. Use the supported methods above through code which uses runs in non-streaming mode. |
There was a problem hiding this comment.
Grammatical issue: 'users might expect' should be 'users might experience' - users don't expect problems, they experience them.
| > * Currently, Azure AI Foundry Agent Playground UI only supports starting runs in streaming mode, and as a result, users might expect connection drops and timeouts. Use the supported methods above through code which uses runs in non-streaming mode. | |
| > * Currently, Azure AI Foundry Agent Playground UI only supports starting runs in streaming mode, and as a result, users might experience connection drops and timeouts. Use the supported methods above through code which uses runs in non-streaming mode. |
| > [!NOTE] | ||
| > Limitation: The Deep Research tool is currently recommended only in nonstreaming scenarios. Using it with streaming can work, but it might occasionally time out and is therefore not recommended. | ||
| > * Limitation: The Deep Research tool is currently recommended only in nonstreaming scenarios. Using it with streaming can work, but it might occasionally time out and is therefore not recommended. | ||
| > * Currently, Azure AI Foundry Agent Playground UI only supports starting runs in streaming mode, and as a result, users might expect connection drops and timeouts. Use the supported methods above through code which uses runs in non-streaming mode. |
There was a problem hiding this comment.
[nitpick] The phrase 'through code which uses runs' is awkward. Consider rephrasing to 'Use the code-based methods shown above, which use runs in non-streaming mode.' for better clarity.
| > * Currently, Azure AI Foundry Agent Playground UI only supports starting runs in streaming mode, and as a result, users might expect connection drops and timeouts. Use the supported methods above through code which uses runs in non-streaming mode. | |
| > * Currently, Azure AI Foundry Agent Playground UI only supports starting runs in streaming mode, and as a result, users might expect connection drops and timeouts. Use the code-based methods shown above, which use runs in non-streaming mode. |
|
Merged in #8133 internally #please-close |
4 participants
Clarified limitations of the Deep Research tool regarding streaming scenarios and provided guidance for using non-streaming mode.