Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Feature] Support mistral models in google vertex ai #839

Open
narengogi opened this issue Dec 23, 2024 · 0 comments
Open

[Feature] Support mistral models in google vertex ai #839

narengogi opened this issue Dec 23, 2024 · 0 comments
Labels
enhancement New feature or request good first issue Good for newcomers triage

Comments

@narengogi
Copy link
Collaborator

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 narengogi added the enhancement New feature or request label Dec 23, 2024
@narengogi narengogi added the good first issue Good for newcomers label Dec 31, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request good first issue Good for newcomers triage
Projects
None yet
Development

No branches or pull requests

1 participant