add gemini embeddings to proxy#781
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 0833c5cff9
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "Codex (@codex) review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "Codex (@codex) address that feedback".
| "format": "google", | ||
| "flavor": "embedding", |
There was a problem hiding this comment.
These new embedding entries make the models selectable for the standard /embeddings path, but format: "google" currently routes non-native Google URLs through fetchGoogleChatCompletions; that code expects messages and calls oaiMessages.find(...), while embedding requests send input, so /embeddings requests for gemini-embedding-2/gemini-embedding-001 fail locally instead of reaching Google's embed endpoint. Please either implement the Google embedding translation path or avoid advertising these models as usable embeddings until that route exists.
Useful? React with 👍 / 👎.
There was a problem hiding this comment.
don't worry codex, i have a PR to resolve ur worries
2 participants
No description provided.