[Vertex AI] Remove format for double() Schema
#13990
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
cc: @rlazo @davidmotson |
andrewheard
force-pushed
the
ah/vertex-float-workaround
branch
from
ff258bc to
2419ec3
Compare
rlazo
approved these changes
Nov 5, 2024
ncooke3
approved these changes
Nov 5, 2024
|
See firebase/firebase-android-sdk#6432 for the equivalent change in Kotlin. |
andrewheard
changed the title
format for floating-point Schema typesformat for double() Schema
rlazo
added a commit
to firebase/firebase-android-sdk
that referenced
this pull request
Nov 6, 2024
We can omit the format for the double-precision floating point type See firebase/firebase-ios-sdk#13990 for further context
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Removed the
"double"format hint inSchema.double()since it is not enforced by the model. Developers should continue to decode the data produced intoDoublevalues to avoid losing precision where available.Additionally, this works around a temporary backend issue where
formatis not accepted for numeric types.Unable to submit request because one or more response schemas specified incorrect schema type field. For schema with format, schema type should be STRING. Learn more: https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/control-generated-output(see #13977 for more details).Note: This PR does not resolve the issue for
float(); consider usingdouble()until #13977 is resolved in the backend.