add more built-in tools #40697
add more built-in tools #40697
Conversation
|
Thank you for your contribution @stevepon! We will review the pull request and get back to you soon. |
There was a problem hiding this comment.
Pull Request Overview
This pull request adds support for two new built-in tools ("azure_ai_search" and "fabric_dataagent") by updating the tool call conversion logic and the corresponding service definitions.
- Extended the break_tool_call_into_messages function to handle the new tool types for both input arguments and output conversion.
- Updated built-in tool constants, tool descriptions, and parameter definitions accordingly in _ai_services.py.
Reviewed Changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
| sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_converters/_models.py | Added branches for handling azure_ai_search and fabric_dataagent tool calls. |
| sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_converters/_ai_services.py | Registered new tool constants, descriptions, and parameter definitions for the new tools. |
| @@ -191,6 +191,10 @@ def break_tool_call_into_messages(tool_call: ToolCall, run_id: str) -> List[Mess | |||
| arguments = { | |||
| "ranking_options": {"ranker": options["ranker"], "score_threshold": options["score_threshold"]} | |||
| } | |||
| elif tool_call.details["type"] == "azure_ai_search": | |||
There was a problem hiding this comment.
There is an inconsistent access pattern when retrieving the tool type value. In this branch, the code uses subscript access (tool_call.details["type"]) while later branches use attribute access (tool_call.details.type). Standardizing the access method would enhance clarity and reduce the risk of runtime issues.
Copilot uses AI. Check for mistakes.
| elif tool_call.details.type == "azure_ai_search": | ||
| output = tool_call.details.azure_ai_search["output"] | ||
| elif tool_call.details.type == "fabric_dataagent": |
There was a problem hiding this comment.
The use of attribute access for obtaining the tool type here contrasts with the subscript access used earlier. Consider unifying this pattern across all branches for consistency in handling tool details.
| elif tool_call.details.type == "azure_ai_search": | |
| output = tool_call.details.azure_ai_search["output"] | |
| elif tool_call.details.type == "fabric_dataagent": | |
| elif tool_call.details["type"] == "azure_ai_search": | |
| output = tool_call.details.azure_ai_search["output"] | |
| elif tool_call.details["type"] == "fabric_dataagent": |
Copilot uses AI. Check for mistakes.
|
API change check API changes are not detected in this pull request. |
sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_converters/_ai_services.py
Show resolved
Hide resolved
| elif tool_call.details["type"] == "azure_ai_search": | ||
| arguments = {"input": tool_call.details["azure_ai_search"]["input"]} | ||
| elif tool_call.details["type"] == "fabric_dataagent": | ||
| arguments = {"input": tool_call.details["fabric_dataagent"]["input"]} |
There was a problem hiding this comment.
You can use the new constants here?
|
Hi @stevepon. Thank you for your interest in helping to improve the Azure SDK experience and for your contribution. We've noticed that there hasn't been recent engagement on this pull request. If this is still an active work stream, please let us know by pushing some changes or leaving a comment. Otherwise, we'll close this out in 7 days. |
|
Hi @stevepon. Thank you for your contribution. Since there hasn't been recent engagement, we're going to close this out. Feel free to respond with a comment containing |
Description
Please add an informative description that covers that changes made by the pull request and link all relevant issues.
If an SDK is being regenerated based on a new swagger spec, a link to the pull request containing these swagger spec changes has been included above.
All SDK Contribution checklist:
General Guidelines and Best Practices
Testing Guidelines