[Bug]: MethodNotImplemented: 501 Received http2 header with status: 404 - While creating Vertex Search Datastore

[sidoncloud]

File Name

https://github.com/GoogleCloudPlatform/generative-ai/blob/main/search/create_datastore_and_search.ipynb

What happened?

These guys can't be serious!! 50% of their code repository pertaining to Vertex AI/Gen AI with Python SDK is a large pile of junk and technical debt that wouldn't work. I really wonder how exactly do these guys work.

Error occurs while executing the below lines of code.

request = discoveryengine.CreateDataStoreRequest(
        parent=discoveryengine.DataStoreServiceClient.collection_path(
            project_id, location, "default_collection"
        ),
        data_store=data_store,
        data_store_id=data_store_id,
    )
    operation = client.create_data_store(request=request)

Relevant log output

---------------------------------------------------------------------------
_InactiveRpcError                         Traceback (most recent call last)
File /opt/conda/lib/python3.10/site-packages/google/api_core/grpc_helpers.py:76, in _wrap_unary_errors.<locals>.error_remapped_callable(*args, **kwargs)
     75 try:
---> 76     return callable_(*args, **kwargs)
     77 except grpc.RpcError as exc:

File /opt/conda/lib/python3.10/site-packages/grpc/_channel.py:1181, in _UnaryUnaryMultiCallable.__call__(self, request, timeout, metadata, credentials, wait_for_ready, compression)
   1175 (
   1176     state,
   1177     call,
   1178 ) = self._blocking(
   1179     request, timeout, metadata, credentials, wait_for_ready, compression
   1180 )
-> 1181 return _end_unary_response_blocking(state, call, False, None)

File /opt/conda/lib/python3.10/site-packages/grpc/_channel.py:1006, in _end_unary_response_blocking(state, call, with_call, deadline)
   1005 else:
-> 1006     raise _InactiveRpcError(state)

_InactiveRpcError: <_InactiveRpcError of RPC that terminated with:
	status = StatusCode.UNIMPLEMENTED
	details = "Received http2 header with status: 404"
	debug_error_string = "UNKNOWN:Error received from peer  {created_time:"2024-10-26T06:52:28.248496722+00:00", grpc_status:12, grpc_message:"Received http2 header with status: 404"}"
>

The above exception was the direct cause of the following exception:

MethodNotImplemented                      Traceback (most recent call last)
Cell In[10], line 1
----> 1 create_data_store(PROJECT_ID, LOCATION, DATASTORE_NAME, DATASTORE_ID)

Cell In[9], line 35, in create_data_store(project_id, location, data_store_name, data_store_id)
     22 data_store = discoveryengine.DataStore(
     23     display_name=data_store_name,
     24     industry_vertical="GENERIC",
     25     content_config="CONTENT_REQUIRED",
     26 )
     28 request = discoveryengine.CreateDataStoreRequest(
     29     parent=discoveryengine.DataStoreServiceClient.collection_path(
     30         project_id, location, "default_collection"
   (...)
     33     data_store_id=data_store_id,
     34 )
---> 35 operation = client.create_data_store(request=request)
     37 # Make the request
     38 # The try block is necessary to prevent execution from halting due to an error being thrown when the datastore takes a while to instantiate
     39 try:

File /opt/conda/lib/python3.10/site-packages/google/cloud/discoveryengine_v1beta/services/data_store_service/client.py:916, in DataStoreServiceClient.create_data_store(self, request, parent, data_store, data_store_id, retry, timeout, metadata)
    913 self._validate_universe_domain()
    915 # Send the request.
--> 916 response = rpc(
    917     request,
    918     retry=retry,
    919     timeout=timeout,
    920     metadata=metadata,
    921 )
    923 # Wrap the response in an operation future.
    924 response = operation.from_gapic(
    925     response,
    926     self._transport.operations_client,
    927     gcd_data_store.DataStore,
    928     metadata_type=data_store_service.CreateDataStoreMetadata,
    929 )

File /opt/conda/lib/python3.10/site-packages/google/api_core/gapic_v1/method.py:131, in _GapicCallable.__call__(self, timeout, retry, compression, *args, **kwargs)
    128 if self._compression is not None:
    129     kwargs["compression"] = compression
--> 131 return wrapped_func(*args, **kwargs)

File /opt/conda/lib/python3.10/site-packages/google/api_core/grpc_helpers.py:78, in _wrap_unary_errors.<locals>.error_remapped_callable(*args, **kwargs)
     76     return callable_(*args, **kwargs)
     77 except grpc.RpcError as exc:
---> 78     raise exceptions.from_grpc_error(exc) from exc

MethodNotImplemented: 501 Received http2 header with status: 404

Code of Conduct

• I agree to follow this project's Code of Conduct

[prattcmp]

I probably would have stated it more kindly, but yeah...

This is the response I get from the Vertex AI SDK for PHP:

[2024-10-26 16:23:49] local.ERROR: Google Vertex AI call exception  
[2024-10-26 16:23:49] local.ERROR: {
    "message": "Received http2 header with status: 404",
    "code": 12,
    "status": "UNIMPLEMENTED",
    "details": []
}  

Here's my code:

// Create a client.
        $prediction_service_client = new PredictionServiceClient();

        // Prepare the request message.
        $generation_config = (new GenerationConfig())
            ->setMaxOutputTokens(8192)
            ->setTemperature($parameters['temperature']);

        [$system_instructions, $contents] = self::openai_to_google_messages($parameters['messages']);
        $request = (new GenerateContentRequest())
            ->setModel($full_model_name)
            ->setSystemInstruction($system_instructions)
            ->setGenerationConfig($generation_config)
            ->setContents($contents);

        // Call the API and handle any network failures.
        try {
            if ($stream) {
                $response_stream = $prediction_service_client->streamGenerateContent($request);
                foreach ($response_stream->readAll() as $element) {
                    Log::debug('Element data: ' . $element->serializeToJsonString());
                    $stream(null, $element->serializeToJsonString());
                }
            } else {
                $response = $prediction_service_client->generateContent($request);
                Log::debug('Response data: ' . $response->serializeToJsonString());
            }
        } catch (ApiException $ex) {
            // Handle exception
            Log::error("Google Vertex AI call exception");
            Log::error($ex->getMessage());
            Log::error($ex->getTraceAsString());
            $response = null;
        }