Handling non-OpenAI APIs #490
Draft
Conversation
This file contains hidden or 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
…ude the `output[].content[].annotations` path
There was a problem hiding this comment.
Pull request overview
This PR improves compatibility with non-OpenAI APIs that implement OpenAI-compatible interfaces (such as LM Studio) by making the annotations field in OutputTextContent optional during deserialization. The change uses the #[serde(default)] attribute to ensure that if the field is missing in the API response, it will default to an empty vector instead of causing a deserialization error.
Key Changes
- Added
#[serde(default)]attribute to theannotationsfield in theOutputTextContentstruct to allow it to be missing from API responses while defaulting to an empty Vec
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
Non-OpenAI APIs that implement a similar interface don't always include the
output[].content[].annotationsJSON path. Specifically, I ran into this issue with LM Studio, which doesn't include that attribute.This pull request makes a minor change to the
OutputTextContentstruct inasync-openai/src/types/responses/response.rs. The change ensures that theannotationsfield will now default to an empty vector if it is missing during deserialization, which improves robustness when handling API responses for non-OpenAI APIs.