Hey @arnab-photon! 👋 I'm Dosu, your friendly bot here to help you solve bugs, answer questions, and become a contributor. I'm ready to assist you while we wait for a human maintainer. Let's tackle this together! 🤖

To resolve the issue with adding a key for google-ai-studio due to the unsupported model gemini-2.5-pro-exp-03-25, you need to update the model version in the Langfuse codebase. Here's how you can do it:

1. Update the Model Version: Modify the vertexAIModels array in the packages/shared/src/server/llm/types.ts file to replace the old model version with the new one:

   export const vertexAIModels = [
     "gemini-2.5-pro-preview-03-25", // Updated model version
     "gemini-2.0-pro-exp-02-05",
     "gemini-2.0-flash",
     "gemini-2.0-flash-001",
     "gemini-2.0-flash-lite-preview-02-05",
     "gemini-2.0-flash-exp",
     "gemini-1.5-pro",
     "gemini-1.5-flash",
     "gemini-1.0-pro",
   ] as const;

2. Update Configuration Files: Ensure that the worker/src/constants/default-model-prices.json file is updated with the new model version and the updated_at field is set to the current date in ISO 8601 format. If the V3 release has not yet occurred, create a migration to update both the models and prices tables accordingly ^[1][2].

These changes should allow you to add the key for google-ai-studio and run experiments using the latest Gemini models.

To continue talking to Dosu, mention @dosu.

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other}

I have this issue as well, but i cannot fix it myself because i'm running the langfuse cloud.