Track Embedding Model Costs in LlamaIndex Integration #7839
Nakshjainsonigara
started this conversation in
Ideas
Replies: 1 comment
-
|
I am also looking for support for Google Vertex AI embedding model: text-embedding-005 |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Describe the feature or potential improvement
Right now, when using Langfuse with LlamaIndex, the cost of embedding models for both data and query embeddings isn’t tracked properly.
It would be great if Langfuse could track embedding model usage separately, just like it does for LLM calls.
Additional information
I’ve especially been facing issues with tracking Cohere embedding costs.
Beta Was this translation helpful? Give feedback.
All reactions