-
Notifications
You must be signed in to change notification settings - Fork 75
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
Introduce the ability to use inject models #258
Conversation
cc @cescoffier @maxandersen @dandreadis @edeandrea @andreadimaio @sarxos who have all mentioned something similar. |
@cescoffier can you have a look at this when you get some time, as I would like to get a new release out including this? Thanks! |
...tests/openai/src/main/java/org/acme/example/openai/chat/QuarkusOpenAiClientChatResource.java
Show resolved
Hide resolved
core/runtime/src/main/java/io/quarkiverse/langchain4j/ModelName.java
Outdated
Show resolved
Hide resolved
@RegisterAiService( | ||
chatLanguageModelSupplier = MyChatModelSupplier.class | ||
) | ||
@RegisterAiService(modelName="m1") |
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.
Now that we have the qualifier, should it be used there instead of a parameter? Or allow both?
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.
I don't really like having multiple unless we really have to
This now allows models to be named and usable via CDI with the
@ModelName
qualifier.Furthermore,
@RegisterAiService
now has themodelName
attribute that can be used to select which model should be used for that service in question.Relates to: #246, #237, #210, #42, #41, #10