You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Apparently this can optimize the cost, performance whilst still out performing ada and small gpt models. Adding this will bake in flexibility for future.
Not all embedding models support dynamic dimensions. I have added it to the OpenAi3LargeEmbeddings model. Simply set the optional parameter dynamicDimension in the constructor. We can also add it to any other embedding model that supports this.
Apparently this can optimize the cost, performance whilst still out performing ada and small gpt models. Adding this will bake in flexibility for future.
See note below
https://platform.openai.com/docs/guides/embeddings/use-cases
The text was updated successfully, but these errors were encountered: