Skip to content

chat: add configure openai api base and model #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

Merged
merged 8 commits into from
Aug 19, 2024

Conversation

lroolle
Copy link
Contributor

@lroolle lroolle commented Aug 15, 2024

Add support to configure OPENAI_API_BASE & OPENAI_MODEL in env local

Copy link
Collaborator

@gregnr gregnr left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks @lroolle! Would you mind adding some docs for this in the apps/postgres-new README? We should also add a disclaimer that says that the current prompts/tools were designed around GPT-4o, so expect other models to behave differently and produce different results. And also that you will need to choose a model that supports tool (function) call capabilities.

@lroolle
Copy link
Contributor Author

lroolle commented Aug 19, 2024

Thanks @lroolle! Would you mind adding some docs for this in the apps/postgres-new README? We should also add a disclaimer that says that the current prompts/tools were designed around GPT-4o, so expect other models to behave differently and produce different results. And also that you will need to choose a model that supports tool (function) call capabilities.


hi @gregnr, README updated

Copy link
Collaborator

@gregnr gregnr left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks @lroolle!

@gregnr gregnr merged commit 358ad8b into supabase-community:main Aug 19, 2024
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants