feat: support gpt-4o-audio-preview #895
Conversation
|
@WqyJh thank you for the PR! Please the latest changes from |
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## master #895 +/- ##
==========================================
+ Coverage 98.46% 98.84% +0.38%
==========================================
Files 24 26 +2
Lines 1364 1725 +361
==========================================
+ Hits 1343 1705 +362
+ Misses 15 14 -1
Partials 6 6 ☔ View full report in Codecov by Sentry. 🚨 Try these New Features:
|
|
Fixed @sashabaranov |
| type TestingT interface { | ||
| Fatalf(format string, args ...any) | ||
| Errorf(format string, args ...any) | ||
| } |
There was a problem hiding this comment.
Do we even need to abstract it as an interface, or can we use *testing.T?
There was a problem hiding this comment.
This works for both unittest and benchmark.
| // Pointer variable equality is determined based on the equality of the | ||
| // referenced values (as opposed to the memory addresses). Function equality | ||
| // cannot be determined and will always fail. | ||
| func Equal(t TestingT, expected, actual interface{}) bool { |
There was a problem hiding this comment.
Could you please change interface{} to any across the PR?
| checks.NoError(t, err) | ||
| checks.Equal(t, c.response, expected) | ||
| } | ||
| } |
There was a problem hiding this comment.
Could you please add an integration test? It's pretty hard to review new things these days!
OpenAI has released a new model
gpt-4o-audio-previewwhich is an end-to-end model for audio input/output. It can be used by chat completion api.Reference: