issue: ThrottlingException with AWS Bedrock embed models

[dirkpetersen]

I am seeing this after increasing my file limits:

2025-08-17 14:19:57,627 - root - INFO - Request POST http://rag_api:8000/embed - 200
2025-08-17 14:20:09,376 - root - ERROR - Error raised by inference endpoint: An error occurred (ThrottlingException) when calling the InvokeModel operation (reached max retries: 4): Too many requests, please wait before trying again.
2025-08-17 14:20:09,379 - root - ERROR - Failed to store data in vector DB | File ID: 4f44f71d-d92c-4153-8c47-9b9c76f83e65 | User ID: 68684314100753e9715c68ca | Error: An error occurred (ThrottlingException) when calling the InvokeModel operation (reached max retries: 4): Too many requests, please wait before trying again. | Traceback: Traceback (most recent call last):
  File "/app/app/routes/document_routes.py", line 289, in store_data_in_vector_db
    ids = await vector_store.aadd_documents(
  File "/app/app/services/vector_store/async_pg_vector.py", line 69, in aadd_documents
    return await run_in_executor(
  File "/usr/local/lib/python3.10/site-packages/langchain_core/runnables/config.py", line 593, in run_in_executor
    return await asyncio.get_running_loop().run_in_executor(executor_or_config, wrapper)
  File "/usr/local/lib/python3.10/concurrent/futures/thread.py", line 58, in run
    result = self.fn(*self.args, **self.kwargs)
  File "/usr/local/lib/python3.10/site-packages/langchain_core/runnables/config.py", line 579, in wrapper
    return func(*args, **kwargs)
  File "/usr/local/lib/python3.10/site-packages/langchain_core/vectorstores/base.py", line 287, in add_documents
    return self.add_texts(texts, metadatas, **kwargs)
  File "/usr/local/lib/python3.10/site-packages/langchain_community/vectorstores/pgvector.py", line 561, in add_texts
    embeddings = self.embedding_function.embed_documents(list(texts))
  File "/usr/local/lib/python3.10/site-packages/langchain_aws/embeddings/bedrock.py", line 178, in embed_documents
    response = self._embedding_func(text)
  File "/usr/local/lib/python3.10/site-packages/langchain_aws/embeddings/bedrock.py", line 159, in _embedding_func
    raise e
  File "/usr/local/lib/python3.10/site-packages/langchain_aws/embeddings/bedrock.py", line 144, in _embedding_func
    response = self.client.invoke_model(
  File "/usr/local/lib/python3.10/site-packages/botocore/client.py", line 565, in _api_call
    return self._make_api_call(operation_name, kwargs)
  File "/usr/local/lib/python3.10/site-packages/botocore/client.py", line 1017, in _make_api_call
    raise error_class(parsed_response, operation_name)
botocore.errorfactory.ThrottlingException: An error occurred (ThrottlingException) when calling the InvokeModel operation (reached max retries: 4): Too many requests, please wait before trying again.

2025-08-17 14:20:09,381 - root - INFO - Request POST http://rag_api:8000/embed - 200
2025-08-17 14:20:17,565 - root - INFO - Request POST http://rag_api:8000/embed - 200

from librechat.yaml

fileConfig:
  endpoints:
    default:
      fileLimit: 100
      fileSizeLimit: 100
      totalSizeLimit: 1000
    google:
      fileLimit: 100
      fileSizeLimit: 100
      totalSizeLimit: 1000
    openAI:
      fileLimit: 100
      fileSizeLimit: 100
      totalSizeLimit: 1000
    bedrock:
      fileLimit: 100
      fileSizeLimit: 100
      totalSizeLimit: 1000
    xai:
      fileLimit: 100
      fileSizeLimit: 100
      totalSizeLimit: 1000
    agents:
      fileLimit: 100
      fileSizeLimit: 100
      totalSizeLimit: 1000
  serverFileSizeLimit: 4000

[dirkpetersen]

Thanks that would be useful and i can add it to the docs of a larger PR I am working on: dirkpetersen@c3e234b that allows me to attach more than 200 pdf files in one go with lots more error checking

[dirkpetersen]

Yes, I would appreciate such an example, this this specific problem claude already found a workaround but I use bedrock a lot so it would be useful for the next thing, Thanks !