untested fix: make .models() call not crash if created or owned_by are missing in some endpoints (openrouter) #332
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Outdated suggestions cannot be applied.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.
Describe your change
This change was suggested by GPT-4 as I don't know Kotlin. Moreover I don't know how openai-kotlin was engineered so I don't know if that breaks backward compatibility or if some parts of the lib rely on the fields
created
andowned-by
to exist.What problem is this fixing?
In issue #331 I reported that listing models fails with the endpoint of openrouter because those two keys are missing. To me supporting openrouter.ai would really be awesome because they support many many many models including from OpenAI, Anthropic, Cohere, Mistral, Google, etc. So even the bare minimum amount of compatibility (listing models, calling completion etc) would go a really long way in terms of how much flexibility that would give to your lib!
Edit: here's a typical output from
curl https://openrouter.ai/api/v1/models |jq
:So indeed the owned_by and created fields don't exist, but I don't know if those extra fields like "pricing" would cause a crash or not.