-
Notifications
You must be signed in to change notification settings - Fork 15
chore: Update available modellist #384
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
foundation-models/openai/src/main/java/com/sap/ai/sdk/foundationmodels/openai/OpenAiModel.java
Show resolved
Hide resolved
| * @deprecated This model is deprecated on AI Core with a planned retirement on 2025-05-13. The | ||
| * suggested replacement model is {@link OrchestrationAiModel#GPT_4O}. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
(Question)
Just to confirm, we want to expose this dynamic information (deprecation date and replacement), rather than suggesting SAP Note directly? @jjtang1985?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This was initially proposed by Till.
From consumer perspective, it's convenient to have this information as Java annotation.
If it does not cost too much time, I would like to have them.
| /** Azure OpenAI GPT-4o-mini chat completions model */ | ||
| public static final OrchestrationAiModel GPT_4O_MINI = new OrchestrationAiModel("gpt-4o-mini"); | ||
|
|
||
| /** Azure OpenAI o1 chat completions model */ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
(Question)
Why do you remove "chat completion" from JavaDoc in other places but add it here?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
True, I believe I wasnt 100% consistent with this.
I initially noticed that some models had a chat completion or embedding in their JavaDoc, others not. As many of the newer models are generally multimodal, I found the chat completion a bit misleading. However, for our SDK, they can of course only generate text or cumpute embeddings (except from dall-e).
rpanackal
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
Context
AI/ai-sdk-java-backlog#206
OrchestrationAiModelandOpenAiModelreasoning effortof o-series in bruno and SDK (works well, with high effort ~double the token consumption of low effort)Feature scope:
Definition of Done
Tests cover the scope aboveError handling created / updated & covered by the tests aboveAligned changes with the JavaScript SDKRelease notes updated