400 Request contains an invalid argument

[meganano202]

Description of the bug:

For some reason I got this error.

This is my traceback when trying to process a video:

Traceback (most recent call last):
  File "f:\Users\meganano202\Desktop\Python\test.py", line 25, in <module>
    result = model.generate_content(
  File "C:\Users\meganano202\AppData\Local\Programs\Python\Python310\lib\site-packages\google\generativeai\generative_models.py", line 331, in generate_content
    response = self._client.generate_content(
  File "C:\Users\meganano202\AppData\Local\Programs\Python\Python310\lib\site-packages\google\ai\generativelanguage_v1beta\services\generative_service\client.py", line 830, in generate_content
    response = rpc(
  File "C:\Users\meganano202\AppData\Local\Programs\Python\Python310\lib\site-packages\google\api_core\gapic_v1\method.py", line 131, in __call__
    return wrapped_func(*args, **kwargs)
  File "C:\Users\meganano202\AppData\Local\Programs\Python\Python310\lib\site-packages\google\api_core\retry\retry_unary.py", line 293, in retry_wrapped_func
    return retry_target(
  File "C:\Users\meganano202\AppData\Local\Programs\Python\Python310\lib\site-packages\google\api_core\retry\retry_unary.py", line 153, in retry_target
    _retry_error_helper(
  File "C:\Users\meganano202\AppData\Local\Programs\Python\Python310\lib\site-packages\google\api_core\retry\retry_base.py", line 212, in _retry_error_helper
    raise final_exc from source_exc
  File "C:\Users\meganano202\AppData\Local\Programs\Python\Python310\lib\site-packages\google\api_core\retry\retry_unary.py", line 144, in retry_target
    result = target()
  File "C:\Users\meganano202\AppData\Local\Programs\Python\Python310\lib\site-packages\google\api_core\timeout.py", line 120, in func_with_timeout
    return func(*args, **kwargs)
  File "C:\Users\meganano202\AppData\Local\Programs\Python\Python310\lib\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 Request contains an invalid argument.

I tested it proccessing a image and without upload anything and it worked. I searched in google but nobody knows anything about this error

I suppose that the error its here:

result = model.generate_content(
        contents=[myfile, query],  # The query is passed as text
        safety_settings={
            HarmCategory.HARM_CATEGORY_HATE_SPEECH: HarmBlockThreshold.BLOCK_NONE,
            HarmCategory.HARM_CATEGORY_HARASSMENT: HarmBlockThreshold.BLOCK_NONE,
            HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT: HarmBlockThreshold.BLOCK_NONE,
            HarmCategory.HARM_CATEGORY_SEXUALLY_EXPLICIT: HarmBlockThreshold.BLOCK_NONE
        },
    )

But it dont really know because it worked fine yesterday

Actual vs expected behavior:

It gives me an error 400 when generating the response but yesterday it did it all right everything

Any other information you'd like to share?

No response

[TS-development]

We just started seeing a 400 today as well, unsure if related but this is what we are getting:

{"timestamp": "2025-01-08T19:55:35.279861", "logger": "api.main", "level": "ERROR", "message": "(CLOUD) true, 2025-01-08T19:55:35.279869, Uncaught Error in Ecomm Chat!!!: 400 Developer instruction is not enabled for models/gemini-1.5-flash-latest. Traceback: Traceback (most recent call last):\n  File \"/app/api/main.py\", line 196, in ecommerce_ws\n    chat_success = await _ecomm_chat_ws(\n  File \"/app/api/main.py\", line 174, in _ecomm_chat_ws\n    success, error_msg = await ecomm_chat.handle_chat_interaction()\n  File \"/app/api/chatting/ecommerce/ecommerce_chat.py\", line 303, in handle_chat_interaction\n    ai_resp = await self.second_stage_conversation(\n  File \"/app/api/chatting/ecommerce/ecommerce_chat.py\", line 217, in second_stage_conversation\n    ai_resp = await self.send_llm_text_response()\n  File \"/app/api/chatting/base_chat_interface.py\", line 125, in send_llm_text_response\n    async for token in self.get_llm_resp_ws():\n  File \"/app/api/chatting/base_chat_interface.py\", line 72, in get_llm_resp_ws\n    async for text in model_func(\n  File \"/app/api/llm_clients/_gemini.py\", line 100, in chat_stream\n    async for token in await model.generate_content_async(\n  File \"/usr/local/lib/python3.10/site-packages/google/generativeai/generative_models.py\", line 379, in generate_content_async\n    iterator = await self._async_client.stream_generate_content(\n  File \"/usr/local/lib/python3.10/site-packages/google/api_core/retry/retry_unary_async.py\", line 230, in retry_wrapped_func\n    return await retry_target(\n  File \"/usr/local/lib/python3.10/site-packages/google/api_core/retry/retry_unary_async.py\", line 160, in retry_target\n    _retry_error_helper(\n  File \"/usr/local/lib/python3.10/site-packages/google/api_core/retry/retry_base.py\", line 212, in _retry_error_helper\n    raise final_exc from source_exc\n  File \"/usr/local/lib/python3.10/site-packages/google/api_core/retry/retry_unary_async.py\", line 155, in retry_target\n    return await target()\n  File \"/usr/local/lib/python3.10/site-packages/google/api_core/grpc_helpers_async.py\", line 178, in error_remapped_callable\n    await call.wait_for_connection()\n  File \"/usr/local/lib/python3.10/site-packages/google/api_core/grpc_helpers_async.py\", line 79, in wait_for_connection\n    raise exceptions.from_grpc_error(rpc_error) from rpc_error\ngoogle.api_core.exceptions.InvalidArgument: 400 Developer instruction is not enabled for models/gemini-1.5-flash-latest\n", "labels": {"request_id": "1de404ef-9b67-4f8c-a557-4a505b1c5e1b", "tenant": "default", "project": "device-heaven"}}

[meganano202]

We just started seeing a 400 today as well, unsure if related but this is what we are getting:

{"timestamp": "2025-01-08T19:55:35.279861", "logger": "api.main", "level": "ERROR", "message": "(CLOUD) true, 2025-01-08T19:55:35.279869, Uncaught Error in Ecomm Chat!!!: 400 Developer instruction is not enabled for models/gemini-1.5-flash-latest. Traceback: Traceback (most recent call last):\n  File \"/app/api/main.py\", line 196, in ecommerce_ws\n    chat_success = await _ecomm_chat_ws(\n  File \"/app/api/main.py\", line 174, in _ecomm_chat_ws\n    success, error_msg = await ecomm_chat.handle_chat_interaction()\n  File \"/app/api/chatting/ecommerce/ecommerce_chat.py\", line 303, in handle_chat_interaction\n    ai_resp = await self.second_stage_conversation(\n  File \"/app/api/chatting/ecommerce/ecommerce_chat.py\", line 217, in second_stage_conversation\n    ai_resp = await self.send_llm_text_response()\n  File \"/app/api/chatting/base_chat_interface.py\", line 125, in send_llm_text_response\n    async for token in self.get_llm_resp_ws():\n  File \"/app/api/chatting/base_chat_interface.py\", line 72, in get_llm_resp_ws\n    async for text in model_func(\n  File \"/app/api/llm_clients/_gemini.py\", line 100, in chat_stream\n    async for token in await model.generate_content_async(\n  File \"/usr/local/lib/python3.10/site-packages/google/generativeai/generative_models.py\", line 379, in generate_content_async\n    iterator = await self._async_client.stream_generate_content(\n  File \"/usr/local/lib/python3.10/site-packages/google/api_core/retry/retry_unary_async.py\", line 230, in retry_wrapped_func\n    return await retry_target(\n  File \"/usr/local/lib/python3.10/site-packages/google/api_core/retry/retry_unary_async.py\", line 160, in retry_target\n    _retry_error_helper(\n  File \"/usr/local/lib/python3.10/site-packages/google/api_core/retry/retry_base.py\", line 212, in _retry_error_helper\n    raise final_exc from source_exc\n  File \"/usr/local/lib/python3.10/site-packages/google/api_core/retry/retry_unary_async.py\", line 155, in retry_target\n    return await target()\n  File \"/usr/local/lib/python3.10/site-packages/google/api_core/grpc_helpers_async.py\", line 178, in error_remapped_callable\n    await call.wait_for_connection()\n  File \"/usr/local/lib/python3.10/site-packages/google/api_core/grpc_helpers_async.py\", line 79, in wait_for_connection\n    raise exceptions.from_grpc_error(rpc_error) from rpc_error\ngoogle.api_core.exceptions.InvalidArgument: 400 Developer instruction is not enabled for models/gemini-1.5-flash-latest\n", "labels": {"request_id": "1de404ef-9b67-4f8c-a557-4a505b1c5e1b", "tenant": "default", "project": "device-heaven"}}

I tried to search in my logs but didnt find anything. Am I searching in the right website?

Edit:

I finally found the logs:

{"protoPayload":{"@type":"type.googleapis.com/google.cloud.audit.AuditLog","status":{"code":5,"message":"Cannot find metric(s) that match type = \"generativelanguage.googleapis.com/quota/predict_requests_per_model/usage\" label = limit_name. If a metric was created recently, it could take up to 10 minutes to become available. Please try again soon."},"requestMetadata":{"callerSuppliedUserAgent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36,gzip(gfe),gzip(gfe)"},"serviceName":"monitoring.googleapis.com","methodName":"google.monitoring.v3.MetricService.ListTimeSeries","authorizationInfo":[{"permission":"monitoring.timeSeries.list","granted":true}],"request":{"interval":{"startTime":"2025-01-09T06:57:44.900934Z","endTime":"2025-01-09T07:07:44.900934Z"},"@type":"type.googleapis.com/google.monitoring.v3.ListTimeSeriesRequest","filter":"resource.type=\"generativelanguage.googleapis.com/Location\" AND metric.type=\"generativelanguage.googleapis.com/quota/predict_requests_per_model/usage\" AND metric.label.limit_name=\"PredictRequestsPerMinutePerProjectPerModel\""}},"resource":{"type":"audited_resource","labels":{"method":"google.monitoring.v3.MetricService.ListTimeSeries","service":"monitoring.googleapis.com"}},"timestamp":"2025-01-09T07:07:44.912385502Z","severity":"ERROR"}

The error message is "Cannot find metric(s) that match type = \"generativelanguage.googleapis.com/quota/predict_requests_per_model/usage\" label = limit_name. If a metric was created recently, it could take up to 10 minutes to become available. Please try again soon."

Edit 2:

If you need more information, I'm using the model gemini-1.5-flash in Python 3.10.6 and google-generativeai version is 0.8.3

[popov-ig]

I faced the same error, although for text requests.

Behavior:

1. Created a cache,
2. Instantiated a model,
3. Call of model with generate_content method caused error

InvalidArgument: 400 CachedContent can not be used with GenerateContent request setting system_instruction, tools or tool_config. Proposed fix: move those values to CachedContent from GenerateContent request.

I have checked all the possible reason:
✅ Does app's code have recent changes? Yes, BUT I rolled back those changes and still have the same error.
✅ Does client package have recent changes? Nope, the last one was made in Oct 2024, see here
✅ Does app's data same? Yes, I have tried with different test payloads, and can easily reproduce error.

🤔 So, it smells like a bug on a server-side (Gemini API).

✍️ I also submitted a comment in corresponding Dev's forum branch.

❗Waiting for developer's response, because this error reproduce for 100% requests, so, it actually blocks our app 🛑.