alt Hacker NewsGood luck to anyone using it. We used it for embedding about 6k documents.
The API constantly gives you quota errors when you reach about 150 requests/min eventhough the quota should allow about 50_000 requests/min.
We’d like to use the Batch API, but the model isn’t available yet.
Quite a nice model though. Being able to get embeddings for a specific task type [1] is very interesting. We used classification specific embeddings and noticed a meaningful improvment when we used the embeddings as input for a classifier.
1: https://ai.google.dev/gemini-api/docs/embeddings#supported-t...
Same here.
I tested gemini embeddings api for 1 to 5,000ish social media comments. It filled up the quota almost immediately.
Since then, I’m just using qwen embeddings locally. Open source, free and relatively comparable.