C1M3 - Weaviate Intro Lab - Fails 'Unable to access non-serverless model BAAI...'

I’m getting 2 error just running this Lab - Introduction to the Weaviate API. I have tried, Updating the Lab, Rebooting the Server, and Revert to Checkpoint all with same results.

Under adding elements to a collection, this code:

# Set up a batch process with specified fixed size and concurrency
with collection.batch.fixed_size(batch_size=1, concurrent_requests=1) as batch:
    
# Iterate over a subset of the dataset
    for document in tqdm(data): # tqdm is a library to show progress bars
    
# Generate a UUID based on the article_content text for unique identification
            uuid = generate_uuid5(document)

            # Add the object to the batch with properties and UUID. 
            # properties expects a dictionary with the keys being the properties.
            batch.add_object(
                properties=document,
                uuid=uuid,
            )

produces this error:

It does result in a collection of vectors with length 17.

Then, under section 3.2 Semantic Search it is producing a fatal error when trying to invoke the .near_text method:

result = collection.query.near_text(query = ‘I want suggestions to travel during Winter. I want cheap places.’, limit = 4)
---------------------------------------------------------------------------
_InactiveRpcError                         Traceback (most recent call last)
File /usr/local/lib/python3.10/dist-packages/weaviate/connect/v4.py:985, in ConnectionSync.grpc_search(self, request)
    984 assert self.grpc_stub is not None
--> 985 res = _Retry(4).with_exponential_backoff(
    986     0,
    987     f"Searching in collection {request.collection}",
    988     self.grpc_stub.Search,
    989     request,
    990     metadata=self.grpc_headers(),
    991     timeout=self.timeout_config.query,
    992 )
    993 return cast(search_get_pb2.SearchReply, res)

File /usr/local/lib/python3.10/dist-packages/weaviate/retry.py:54, in _Retry.with_exponential_backoff(self, count, error, f, *args, **kwargs)
     53 if err.code() != StatusCode.UNAVAILABLE:
---> 54     raise e
     55 logger.info(
     56     f"{error} received exception: {e}. Retrying with exponential backoff in {2**count} seconds"
     57 )

File /usr/local/lib/python3.10/dist-packages/weaviate/retry.py:50, in _Retry.with_exponential_backoff(self, count, error, f, *args, **kwargs)
     49 try:
---> 50     return f(*args, **kwargs)
     51 except RpcError as e:

File /usr/local/lib/python3.10/dist-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 /usr/local/lib/python3.10/dist-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.UNKNOWN
	details = "explorer: get class: concurrentTargetVectorSearch): explorer: get class: vectorize search vector: vectorize params: vectorize params: vectorize keywords: remote client vectorize: fail with status 500: Failed to get correct output from LLM call.
Exception: Error code: 400 - {'id': 'oZBJEha-2kFHot-9d4fbd771fc5df0a', 'error': {'message': 'Unable to access non-serverless model BAAI/bge-base-en-v1.5. Please visit https://api.together.ai/models/BAAI/bge-base-en-v1.5 to create and start a new dedicated endpoint for the model.', 'type': 'invalid_request_error', 'param': None, 'code': 'model_not_available'}}"
	debug_error_string = "UNKNOWN:Error received from peer  {grpc_status:2, grpc_message:"explorer: get class: concurrentTargetVectorSearch): explorer: get class: vectorize search vector: vectorize params: vectorize params: vectorize keywords: remote client vectorize: fail with status 500: Failed to get correct output from LLM call.\nException: Error code: 400 - {\'id\': \'oZBJEha-2kFHot-9d4fbd771fc5df0a\', \'error\': {\'message\': \'Unable to access non-serverless model BAAI/bge-base-en-v1.5. Please visit https://api.together.ai/models/BAAI/bge-base-en-v1.5 to create and start a new dedicated endpoint for the model.\', \'type\': \'invalid_request_error\', \'param\': None, \'code\': \'model_not_available\'}}"}"
>

During handling of the above exception, another exception occurred:

WeaviateQueryError                        Traceback (most recent call last)
Cell In[17], line 1
----> 1 result = collection.query.near_text(query = 'I want suggestions to travel during Winter. I want cheap places.', limit = 4)

File /usr/local/lib/python3.10/dist-packages/weaviate/collections/queries/near_text/query/executor.py:424, in _NearTextQueryExecutor.near_text(self, query, certainty, distance, move_to, move_away, limit, offset, auto_limit, filters, group_by, rerank, target_vector, include_vector, return_metadata, return_properties, return_references)
    391     return cast(
    392         Any,
    393         self._result_to_query_or_groupby_return(
   (...)
    404         ),
    405     )
    407 request = self._query.near_text(
    408     near_text=query,
    409     certainty=certainty,
   (...)
    422     return_references=self._parse_return_references(return_references),
    423 )
--> 424 return executor.execute(
    425     response_callback=resp,
    426     method=self._connection.grpc_search,
    427     request=request,
    428 )

File /usr/local/lib/python3.10/dist-packages/weaviate/connect/executor.py:99, in execute(method, response_callback, exception_callback, *args, **kwargs)
     97     return resp_call
     98 except Exception as e:
---> 99     return cast(T, exception_callback(e))

File /usr/local/lib/python3.10/dist-packages/weaviate/connect/executor.py:38, in raise_exception(e)
     37 def raise_exception(e: Exception) -> Any:
---> 38     raise e

File /usr/local/lib/python3.10/dist-packages/weaviate/connect/executor.py:80, in execute(method, response_callback, exception_callback, *args, **kwargs)
     71 def execute(
     72     method: SyncOrAsyncMethod[P, R],
     73     response_callback: SyncOrAsyncCallback[R, T, A],
   (...)
     77 ) -> Union[T, Awaitable[T], Awaitable[A]]:
     78     # wrap method call in try-except to catch exceptions for sync method
     79     try:
---> 80         call = method(*args, **kwargs)
     81         if isinstance(call, Awaitable):
     83             async def _execute() -> T:
     84                 # wrap await in try-except to catch exceptions for async method

File /usr/local/lib/python3.10/dist-packages/weaviate/connect/v4.py:998, in ConnectionSync.grpc_search(self, request)
    996     if error.code() == StatusCode.PERMISSION_DENIED:
    997         raise InsufficientPermissionsError(error)
--> 998     raise WeaviateQueryError(str(error.details()), "GRPC search")  # pyright: ignore
    999 except WeaviateRetryError as e:
   1000     raise WeaviateQueryError(str(e), "GRPC search")

WeaviateQueryError: Query call with protocol GRPC search failed with message explorer: get class: concurrentTargetVectorSearch): explorer: get class: vectorize search vector: vectorize params: vectorize params: vectorize keywords: remote client vectorize: fail with status 500: Failed to get correct output from LLM call.
Exception: Error code: 400 - {'id': 'oZBJEha-2kFHot-9d4fbd771fc5df0a', 'error': {'message': 'Unable to access non-serverless model BAAI/bge-base-en-v1.5. Please visit https://api.together.ai/models/BAAI/bge-base-en-v1.5 to create and start a new dedicated endpoint for the model.', 'type': 'invalid_request_error', 'param': None, 'code': 'model_not_available'}}.
1 Like

I have similar error in Programming assignments Module 3. All semantic search related unit test failed with similar error. (unit test 3.2, 3.4 and 3.5). Can somone please point to how to resolve this.

_InactiveRpcError: <_InactiveRpcError of RPC that terminated with:
	status = StatusCode.UNKNOWN
	details = "remote client vectorize: fail with status 500: Failed to get correct output from LLM call.
Exception: Error code: 400 - {'id': 'oZJiJAh-2kFHot-9d57be0bdfc82083', 'error': {'message': 'Unable to access non-serverless model BAAI/bge-base-en-v1.5. Please visit https://api.together.ai/models/BAAI/bge-base-en-v1.5 to create and start a new dedicated endpoint for the model.', 'type': 'invalid_request_error', 'param': None, 'code': 'model_not_available'}}"
1 Like

hi @mjplevasseur

are you running the codes in course provided platform or locally?

if you encountered this in platform, try first clearing your cache and. browsing history.

Relogin with your ID, then open the notebook.

Clear out or delete the kernel. output.

Reconnect the kernel

re-run each cell individuallly.

Let me. know if you still encountered the error.

API related error could be because you must of tried to re-run particular codes consistently within a short period of time.

@Deepti_Prasad

Not the original poster but also having the same issue. I had tried you recommendation and the error persists. Any other suggestions/recommendations? Thanks

where are you running codes? because on course platform i didn’t encounter this error

I’m running it on coursera platform.

I am also facing the same problem and the same error.

When I run this line of code -:

result = collection.query.near_text(query = ‘I want suggestions to travel during Winter. I want cheap places.’, limit = 4)

I get this error -:

WeaviateQueryError: Query call with protocol GRPC search failed with message explorer: get class: concurrentTargetVectorSearch): explorer: get class: vectorize search vector: vectorize params: vectorize params: vectorize keywords: remote client vectorize: fail with status 500: Failed to get correct output from LLM call.

Exception: Error code: 400 - {‘id’: ‘oZJ8KmT-2kFHot-9d571c37fc8fcce5’, ‘error’: {‘message’: ‘Unable to access non-serverless model BAAI/bge-base-en-v1.5. Please visit https:/api.together.ai/models/BAAI/bge-base-en-v1.5 to create and start a new dedicated endpoint for the model.’, ‘type’: ‘invalid_request_error’, ‘param’: None, ‘code’: ‘model_not_available’}}.

I am running it on Coursera platform.

Thanks,

Ramesh Rangarajan

I am facing this problem, too.

Running the code from C1M3…Lab2 on Coursera Platform:

search_string = “history of git”  # Or “available git remote commands”

for chunking_strategy in chunk_obj_sets.keys():
where_filter = Filter.by_property(‘chunking_strategy’).equal(chunking_strategy)
response = collection.query.near_text(search_string, filters = where_filter, limit = 2)
print(f"RETRIEVED OBJECTS FOR CHUNKING STRATEGY {chunking_strategy.upper()}:\n")
for i, obj in enumerate(response.objects):
print(f"===== Object {i} =====“)
print(f”{obj.properties[‘chunk’]}")
print()

Gives the following errors:

_InactiveRpcError: <_InactiveRpcError of RPC that terminated with:
	status = StatusCode.UNKNOWN
	details = "explorer: get class: concurrentTargetVectorSearch): explorer: get class: vectorize search vector: vectorize params: vectorize params: vectorize keywords: remote client vectorize: fail with status 500: Failed to get correct output from LLM call.
Exception: Error code: 400 - {'id': 'oZTpVrL-2kFHot-9d61921eafbd2402', 'error': {'message': 'Unable to access non-serverless model BAAI/bge-base-en-v1.5. Please visit https://api.together.ai/models/BAAI/bge-base-en-v1.5 to create and start a new dedicated endpoint for the model.', 'type': 'invalid_request_error', 'param': None, 'code': 'model_not_available'}}"
	debug_error_string = "UNKNOWN:Error received from peer  {grpc_status:2, grpc_message:"explorer: get class: concurrentTargetVectorSearch): explorer: get class: vectorize search vector: vectorize params: vectorize params: vectorize keywords: remote client vectorize: fail with status 500: Failed to get correct output from LLM call.\nException: Error code: 400 - {\'id\': \'oZTpVrL-2kFHot-9d61921eafbd2402\', \'error\': {\'message\': \'Unable to access non-serverless model BAAI/bge-base-en-v1.5. Please visit https://api.together.ai/models/BAAI/bge-base-en-v1.5 to create and start a new dedicated endpoint for the model.\', \'type\': \'invalid_request_error\', \'param\': None, \'code\': \'model_not_available\'}}"}"
>

Not the original poster but I am also facing the same issue. Issues also occur in the ungraded lab. I am running the code on the coursera environment

Deepti, can you please check that the model is indeed still available on together.ai and is still serverless? It is not appearing in their list of models on api.together.ai

Without this model being available and serverless, the graded assignment cannot be completed without trying to stand all this up locally. Thanks.

1 Like

why are you trying to run codes locally if you want to pass the graded assignment, do the assignment on course platform

@PatrickS

please share the assignment top header name

is this ungraded lab??

I didn’t encounter any such error with c1M3