Error fetching response:Error: 404 litellm.NotFoundError: Vertex_aiException - [{ "error": { "code": 404, "message": "Publisher Model projects/*******/locations/us-west2/publishers/deepseek-ai/models/deepseek-v3.2-maas was not found or your project does not have access to it. Please ensure you are using a valid model version. For more information, see: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "status": "NOT_FOUND" } } ]. Received Model Group=deepseek-ai/deepseek-v3.2-maas Available Model Group Fallbacks=None

Fix Plan

The fix involves handling the NotFoundError exception when the specified model version is not found.

• Check if the model version exists before attempting to use it.
• If the model version does not exist, either use a default model version or prompt the user to select a valid model version.
• Update the code to handle the NotFoundError exception and provide a meaningful error message.

Example code snippet:

try:
    # Attempt to use the specified model version
    model_version = "deepseek-v3.2-maas"
    # Code to use the model version
except litellm.NotFoundError as e:
    # Handle the NotFoundError exception
    print(f"Model version {model_version} not found. Please ensure you are using a valid model version.")
    # Either use a default model version or prompt the user to select a valid model version
    default_model_version = "default-model-version"
    # Code to use the default model version

Verification

To verify that the fix worked, test the code with a valid model version and an invalid model version. The code should handle the NotFoundError exception and provide a meaningful error message when an invalid model version is used.

Extra Tips

• Ensure that the model version exists and is accessible before attempting to use it.
• Handle exceptions properly to prevent crashes and provide meaningful error messages.
• Consider implementing a fallback mechanism to use a default model version when the specified model version is not found.