Skip to content

Batch embedding sample does not work after update to gemini-embedding-001 #13393

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

Closed
zeevox opened this issue May 29, 2025 · 0 comments
Closed
Assignees
Labels
priority: p2 Moderately-important priority. Fix may not be included in next release. samples Issues that are directly related to samples. triage me I really want to be triaged. type: bug Error or flaw in code with unintended results or allowing sub-optimal usage patterns.

Comments

@zeevox
Copy link

zeevox commented May 29, 2025

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.

@zeevox zeevox added triage me I really want to be triaged. priority: p2 Moderately-important priority. Fix may not be included in next release. type: bug Error or flaw in code with unintended results or allowing sub-optimal usage patterns. labels May 29, 2025
@product-auto-label product-auto-label bot added the samples Issues that are directly related to samples. label May 29, 2025
@glasnt glasnt closed this as completed Jun 11, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
priority: p2 Moderately-important priority. Fix may not be included in next release. samples Issues that are directly related to samples. triage me I really want to be triaged. type: bug Error or flaw in code with unintended results or allowing sub-optimal usage patterns.
Projects
None yet
Development

No branches or pull requests

2 participants