Batch embedding sample does not work after update to gemini-embedding-001

[zeevox]

TL;DR: The recently updated batch text embedding sample throws an error due to unsupported model gemini-embedding-001.

Introduced in: #13388

In which file did you encounter the issue?

generative_ai/embeddings/batch_example.py

Did you change the file? If so, how?

Only to set the project ID and output bucket.

-PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")
-OUTPUT_URI = os.getenv("GCS_OUTPUT_URI")
+PROJECT_ID = "gen-lang-client-0000171954"
+OUTPUT_URI = "gs://felixplore/"

Describe the issue

1. Installed google-cloud-aiplatform v1.95 into a Python 3.13 virtual environment.
2. Ran python3 batch_example.py and received the error message
   400 Do not support publisher model gemini-embedding-001

Full error traceback

Creating BatchPredictionJob
Traceback (most recent call last):
  File "/home/zeevox/Projects/gemini-embed-debug/.venv/lib/python3.13/site-packages/google/api_core/grpc_helpers.py", line 76, in error_remapped_callable
    return callable_(*args, **kwargs)
  File "/home/zeevox/Projects/gemini-embed-debug/.venv/lib/python3.13/site-packages/grpc/_interceptor.py", line 277, in __call__
    response, ignored_call = self._with_call(
                             ~~~~~~~~~~~~~~~^
        request,
        ^^^^^^^^
    ...<4 lines>...
        compression=compression,
        ^^^^^^^^^^^^^^^^^^^^^^^^
    )
    ^
  File "/home/zeevox/Projects/gemini-embed-debug/.venv/lib/python3.13/site-packages/grpc/_interceptor.py", line 332, in _with_call
    return call.result(), call
           ~~~~~~~~~~~^^
  File "/home/zeevox/Projects/gemini-embed-debug/.venv/lib/python3.13/site-packages/grpc/_channel.py", line 440, in result
    raise self
  File "/home/zeevox/Projects/gemini-embed-debug/.venv/lib/python3.13/site-packages/grpc/_interceptor.py", line 315, in continuation
    response, call = self._thunk(new_method).with_call(
                     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
        request,
        ^^^^^^^^
    ...<4 lines>...
        compression=new_compression,
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    )
    ^
  File "/home/zeevox/Projects/gemini-embed-debug/.venv/lib/python3.13/site-packages/grpc/_channel.py", line 1198, in with_call
    return _end_unary_response_blocking(state, call, True, None)
  File "/home/zeevox/Projects/gemini-embed-debug/.venv/lib/python3.13/site-packages/grpc/_channel.py", line 1006, in _end_unary_response_blocking
    raise _InactiveRpcError(state)  # pytype: disable=not-instantiable
    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
grpc._channel._InactiveRpcError: <_InactiveRpcError of RPC that terminated with:
	status = StatusCode.INVALID_ARGUMENT
	details = "Do not support publisher model gemini-embedding-001"
	debug_error_string = "UNKNOWN:Error received from peer ipv6:%5B2a00:1450:4009:81f::200a%5D:443 {grpc_message:"Do not support publisher model gemini-embedding-001", grpc_status:3, created_time:"2025-05-29T12:11:57.38838994+01:00"}"
>
The above exception was the direct cause of the following exception:
Traceback (most recent call last):

File "/home/zeevox/Projects/gemini-embed-debug/batch_example.py", line 63, in 

embed_text_batch()

~~~~~~~~~~~~~~~~^^

File "/home/zeevox/Projects/gemini-embed-debug/batch_example.py", line 47, in embed_text_batch

batch_prediction_job = textembedding_model.batch_predict(

dataset=[input_uri],

destination_uri_prefix=output_uri,

)

File "/home/zeevox/Projects/gemini-embed-debug/.venv/lib/python3.13/site-packages/vertexai/language_models/_language_models.py", line 1904, in batch_predict

job = aiplatform.BatchPredictionJob.create(

model_name=model_name,

...<2 lines>...

model_parameters=model_parameters,

)

File "/home/zeevox/Projects/gemini-embed-debug/.venv/lib/python3.13/site-packages/google/cloud/aiplatform/jobs.py", line 620, in create

return cls._submit_impl(

~~~~~~~~~~~~~~~~^

job_display_name=job_display_name,

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

...<29 lines>...

wait_for_completion=True,

^^^^^^^^^^^^^^^^^^^^^^^^^

)

^

File "/home/zeevox/Projects/gemini-embed-debug/.venv/lib/python3.13/site-packages/google/cloud/aiplatform/jobs.py", line 1337, in _submit_impl

return cls._submit_and_optionally_wait_with_sync_support(

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^

empty_batch_prediction_job=empty_batch_prediction_job,

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

...<5 lines>...

wait_for_completion=wait_for_completion,

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

)

^

File "/home/zeevox/Projects/gemini-embed-debug/.venv/lib/python3.13/site-packages/google/cloud/aiplatform/base.py", line 863, in wrapper

return method(*args, **kwargs)

File "/home/zeevox/Projects/gemini-embed-debug/.venv/lib/python3.13/site-packages/google/cloud/aiplatform/jobs.py", line 1406, in _submit_and_optionally_wait_with_sync_support

gca_batch_prediction_job = api_client.create_batch_prediction_job(

parent=parent,

batch_prediction_job=gca_batch_prediction_job,

timeout=create_request_timeout,

)

File "/home/zeevox/Projects/gemini-embed-debug/.venv/lib/python3.13/site-packages/google/cloud/aiplatform_v1/services/job_service/client.py", line 3926, in create_batch_prediction_job

response = rpc(

request,

...<2 lines>...

metadata=metadata,

)

File "/home/zeevox/Projects/gemini-embed-debug/.venv/lib/python3.13/site-packages/google/api_core/gapic_v1/method.py", line 131, in call

return wrapped_func(*args, **kwargs)

File "/home/zeevox/Projects/gemini-embed-debug/.venv/lib/python3.13/site-packages/google/api_core/grpc_helpers.py", line 78, in error_remapped_callable

raise exceptions.from_grpc_error(exc) from exc

google.api_core.exceptions.InvalidArgument: 400 Do not support publisher model gemini-embedding-001

To establish whether this is an issue with the model or something in my setup, I tried changing the model name to a previous model, text-embedding-005 with

textembedding_model = language_models.TextEmbeddingModel.from_pretrained(
-    "gemini-embedding-001"
+    "text-embedding-005"
)

And the batch prediction job completed successfully as expected. Therefore, I conclude it is something to do with the model gemini-embedding-001.