Skip to content
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

Update Ai Model Logic #197

Open
Ferdinand737 opened this issue Feb 5, 2024 · 0 comments
Open

Update Ai Model Logic #197

Ferdinand737 opened this issue Feb 5, 2024 · 0 comments

Comments

@Ferdinand737
Copy link
Contributor

Ferdinand737 commented Feb 5, 2024

We need to dynamically choose the AI model to optimize for cost and output quality.

When a user selects GPT-3.5 or GPT-4 that should mean they have selected that family of model, not just one specific model.

We should adjust what model we use based on the input length. We should choose the shortest context window model from models that will get the job done.

We should always use a "dumb" model for generating image search queries.

@Ferdinand737 Ferdinand737 added this to the Peer Testing 2 milestone Feb 5, 2024
@PatchFact PatchFact modified the milestones: Peer Testing 2, Post Peer Testing, Major Features Done Feb 26, 2024
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

No branches or pull requests

2 participants