[Feature Request] Add support for OpenAI text-embedding-3-small and text-embedding-3-large models in Vector Search with Firestore #747
Description
[READ] Step 1: Are you in the right place?
Issues filed here should be about a feature request for a specific extension in this repository. To file a feature request that affects multiple extensions or the Firebase Extensions platform, please reach out to
Firebase support directly.
[REQUIRED] Step 2: Extension name
This feature request is for extension: Vector Search with Firestore
What feature would you like to see?
Currently, when OpenAI is selected as the embedding provider, the extension uses the older model text-embedding-ada-002.
OpenAI has since released improved models (text-embedding-3-small and text-embedding-3-large) that provide better performance, efficiency, and cost-effectiveness.
I would like to request the ability to configure which embedding model is used within the extension settings. Ideally, the options should include the newer text-embedding-3-small and text-embedding-3-large models, while keeping backwards compatibility with text-embedding-ada-002.
How would you use it?
Allowing the selection of newer embedding models would:
- Improve embedding quality and retrieval accuracy.
- Provide cost optimization (developers can choose between the small and large models based on their use case).
- Future-proof apps using this extension by aligning with OpenAI’s recommended embedding models.
In my app, this would directly enhance the performance of semantic search and retrieval-augmented generation (RAG) workflows, leading to better end-user experience.