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
However, it would be really useful to be able to specify credentials by other means, for example using a GCP service account. The vertex AI google cloud SDK supports this by passing an instance of com.google.auth.Credentials to com.google.api.gax.rpc.ClientContext used in PredictionServiceSettings. Builder. But in org.springframework.ai.vertexai.embedding.VertexAiEmbeddigConnectionDetails the predictionServiceSettings is hardcoded to:
In 1.0.0-M2, the documentation for vertexai says to do this as part of the prerequisites:
However, it would be really useful to be able to specify credentials by other means, for example using a GCP service account. The vertex AI google cloud SDK supports this by passing an instance of
com.google.auth.Credentials
tocom.google.api.gax.rpc.ClientContext
used inPredictionServiceSettings. Builder
. But inorg.springframework.ai.vertexai.embedding.VertexAiEmbeddigConnectionDetails
thepredictionServiceSettings
is hardcoded to:making it very difficult to use a service account with spring ai.
The text was updated successfully, but these errors were encountered: