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
Confirm this is a feature request for the Python library and not the underlying OpenAI API.
This is a feature request for the Python library
Describe the feature or improvement you're requesting
There are good 3rd tools, e.g. firecrawl, that I hope to integrate to AgentSDK. Although I could use @tool to integrate in my repository, but I found it repetitive if I need to use the tool in multiple repositories.
I see in crewai, they have a separate python dependency: "tool" aside from the main crewai. The "tool" contains much more 3rd party tools, which comes handy.
If official integration with 3rd party is not supported, could you provide documentation about best practice integrating with 3rd party tools? (Not just basic functional integration, I also want to understand how to properly utilize guardrail, tracing...)
Additional context
No response
The text was updated successfully, but these errors were encountered:
Thanks for the suggestion! Since the openai-agents-python repo is specifically for agent workflows and related integrations, it’d be best to open this issue there. Could you please move the discussion to that repository?
Confirm this is a feature request for the Python library and not the underlying OpenAI API.
Describe the feature or improvement you're requesting
There are good 3rd tools, e.g. firecrawl, that I hope to integrate to AgentSDK. Although I could use @tool to integrate in my repository, but I found it repetitive if I need to use the tool in multiple repositories.
I see in crewai, they have a separate python dependency: "tool" aside from the main crewai. The "tool" contains much more 3rd party tools, which comes handy.
If official integration with 3rd party is not supported, could you provide documentation about best practice integrating with 3rd party tools? (Not just basic functional integration, I also want to understand how to properly utilize guardrail, tracing...)
Additional context
No response
The text was updated successfully, but these errors were encountered: