gateway icon indicating copy to clipboard operation
gateway copied to clipboard

[Feature] Support mistral models in google vertex ai

Open narengogi opened this issue 11 months ago • 0 comments

What Would You Like to See with the Gateway?

some mistral models are supported in vertex openai compliant endpoint,

whereas some of them like mistral-large need the request body to be transformed to mistral format for invoking with the rawPredict endpoint (url="https://$GOOGLE_REGION-aiplatform.googleapis.com/v1/projects/$GOOGLE_PROJECT_ID/locations/$GOOGLE_REGION/publishers/mistralai/models/$MODEL:rawPredict")

check this documentation for reference: https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/call-vertex-using-openai-library

Changes needed to be done:

  1. The self deployed models which are openai compliant are already supported with the endpoints.endpointId format of specifying model id, no changes need to be done here
  2. use existing mistral integration transformers for transforming request and response for the larger mistral models

Context for your Request

No response

Your Twitter/LinkedIn

No response

narengogi avatar Dec 23 '24 08:12 narengogi