openai: use gpt-4o-mini by default
As of July 2024, gpt-4o-mini should be used in place of gpt-3.5-turbo, as it is cheaper, more capable, multimodal, and just as fast.
https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4
PR Checklist
- [x] Read the Contributing documentation.
- [x] Read the Code of conduct documentation.
- [x] Name your Pull Request title clearly, concisely, and prefixed with the name of the primarily affected package you changed according to Good commit messages (such as
memory: add interfaces for X, Yorutil: add whizzbang helpers). - [x] Check that there isn't already a PR that solves the problem the same way to avoid creating a duplicate.
- [x] Provide a description in this PR that addresses what the PR is solving, or reference the issue that it solves (e.g.
Fixes #123). - [ ] Describes the source of new concepts.
- [ ] References existing implementations as appropriate.
- [ ] Contains test coverage for new functions.
- [x] Passes all
golangci-lintchecks.
@tmc Could you take a look?
@eliben Could you take a look?
@AkihiroSuda thanks for tagging, but I think this is something @tmc will have to approve
@tmc Do you still prefer gpt-3.5-turbo to remain as the default?
OpenAI says "As of July 2024, gpt-4o-mini should be used in place of gpt-3.5-turbo, as it is cheaper, more capable, multimodal, and just as fast." https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4
gpt-3.5-turbo-0301, gpt-3.5-turbo-0613, and gpt-3.5-turbo-16k-0613 will be shutdown on Sept 13th 2024.
I got notice from OpenAI after using the defaults in this library. There's a week from today to update the default to gpt-4o-mini (or something newer)
@tmc May I hear your opinion on this? Is there any reason to keep using gpt-3.5-turbo?