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

feat: Support Response Format in Playground #5259

Merged
merged 13 commits into from
Nov 8, 2024

Conversation

cephalization
Copy link
Contributor

@cephalization cephalization commented Nov 1, 2024

  • Add configuration editor for response_format when using openai models
  • Parse and load response_format from incoming spans to playground store
response.format.mov

Resolves #5247
Resolves #5233

@cephalization cephalization force-pushed the cephalization/5247-5233-parse-response-format branch 3 times, most recently from 9d2dbbe to 89aa45d Compare November 7, 2024 00:22
@cephalization cephalization marked this pull request as ready for review November 7, 2024 01:15
@dosubot dosubot bot added the size:L This PR changes 100-499 lines, ignoring generated files. label Nov 7, 2024
@@ -219,3 +257,23 @@ export const llmToolSchema = z
.optional();

export type LlmToolSchema = z.infer<typeof llmToolSchema>;

export const openAIResponseFormatSchema = z.lazy(() =>
Copy link
Contributor

Choose a reason for hiding this comment

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

does this work with anthropic? Is the "strict" the only thing that is openai specific here? Just thinking about the naming and the unraveling we had to do before, anyway we can be a little more agnostic and allow for anthropic and openai in the same go in this pr?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

anthropic does not have response format as of now. this was intended to be the "hub" schema that we would add spokes off of, like anthropic in the future if necessary

@cephalization cephalization force-pushed the cephalization/5247-5233-parse-response-format branch from e5945ee to 7a7aba0 Compare November 7, 2024 23:49
@dosubot dosubot bot removed the size:L This PR changes 100-499 lines, ignoring generated files. label Nov 8, 2024
@dosubot dosubot bot added the size:XL This PR changes 500-999 lines, ignoring generated files. label Nov 8, 2024
@cephalization cephalization merged commit d2ff57a into main Nov 8, 2024
7 checks passed
@cephalization cephalization deleted the cephalization/5247-5233-parse-response-format branch November 8, 2024 00:29
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
size:XL This PR changes 500-999 lines, ignoring generated files.
Projects
Status: Done
2 participants