Add support for passing safety settings to Google AI #186
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
|
Nice! Thanks! ❤️💛💙💜 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
This implements a new field on ChatGoogleAI for setting the safety settings for content filtering, following the documentation at https://ai.google.dev/gemini-api/docs/safety-settings#web and https://ai.google.dev/api/generate-content#v1beta.SafetySetting
Based on your comment at #142 (comment) I kept this as a simple list of maps, rather than introducing a struct and associated changesets, on the basis that the LLM will validate the settings.
I've added support for serializing the config, which should be backwards compatible as deserializing maps without the safety settings field will construct a model with the safety settings set to an empty list, which then wouldn't be added to the request as the list is empty.