[Bug]: Passing in Bedrock application inference profile broken with embedding

[btemplep]

What happened?

Error when calling embedding with an application inference profile.

import litellm
litellm._turn_on_debug()

resp = litellm.embedding(
    custom_llm_provider="bedrock",
    model="amazon.titan-embed-text-v1",
    model_id="arn:aws:bedrock:us-east-1:123412341234:application-inference-profile/abc123123",
    input=["testing"],
    aws_region_name="us-east-1"
)
print(resp)

Relevant log output

18:39:41 - LiteLLM:DEBUG: utils.py:324 - 

18:39:41 - LiteLLM:DEBUG: utils.py:324 - Request to litellm:
18:39:41 - LiteLLM:DEBUG: utils.py:324 - litellm.embedding(custom_llm_provider='bedrock', model='amazon.titan-embed-text-v1', model_id='arn:aws:bedrock:us-east-1:123412341234:application-inference-profile/abc123123', input=['hererer'], aws_region_name='us-east-1')
18:39:41 - LiteLLM:DEBUG: utils.py:324 - 

18:39:41 - LiteLLM:DEBUG: litellm_logging.py:422 - self.optional_params: {}
18:39:41 - LiteLLM:DEBUG: utils.py:324 - SYNC kwargs[caching]: False; litellm.cache: None; kwargs.get('cache')['no-cache']: False
18:39:41 - LiteLLM:DEBUG: litellm_logging.py:422 - self.optional_params: {'model_id': 'arn:aws:bedrock:us-east-1:123412341234:application-inference-profile/abc123123', 'aws_region_name': 'us-east-1'}
18:39:41 - LiteLLM:DEBUG: base_aws_llm.py:121 - in get credentials
aws_access_key_id=None
aws_secret_access_key=None
aws_session_token=None
aws_region_name=us-east-1
aws_session_name=None
aws_profile_name=None
aws_role_name=None
aws_web_identity_token=None
aws_sts_endpoint=None
18:39:41 - LiteLLM:DEBUG: litellm_logging.py:746 - 

POST Request Sent from LiteLLM:
curl -X POST \
https://bedrock-runtime.us-east-1.amazonaws.com/model/arn:aws:bedrock:us-east-1:123412341234:application-inference-profile/abc123123/invoke \
-H 'Content-Type: ap****on' -H 'X-Amz-Date: 20****1Z' -H 'X-Amz-Security-Token: Fw****==' -H 'Authorization: AW****f3' -H 'Content-Length: *****' \
-d '{'inputText': 'hererer'}'


18:39:41 - LiteLLM:DEBUG: utils.py:324 - RAW RESPONSE:
{"Output": {"__type": "com.amazon.coral.service#UnknownOperationException"}, "Version": "1.0"}


18:39:41 - LiteLLM:DEBUG: utils.py:324 - RAW RESPONSE:
'embedding'



Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
LiteLLM.Info: If you need to debug this error, use `litellm._turn_on_debug()'.

18:39:41 - LiteLLM:DEBUG: exception_mapping_utils.py:2243 - Logging Details: logger_fn - None | callable(logger_fn) - False
18:39:41 - LiteLLM:DEBUG: litellm_logging.py:2018 - Logging Details LiteLLM-Failure Call: []
Traceback (most recent call last):
  File "/home/tester/venv_test/lib/python3.12/site-packages/litellm/main.py", line 3626, in embedding
    response = bedrock_embedding.embeddings(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/tester/venv_test/lib/python3.12/site-packages/litellm/llms/bedrock/embed/embedding.py", line 432, in embeddings
    return self._single_func_embeddings(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/tester/venv_test/lib/python3.12/site-packages/litellm/llms/bedrock/embed/embedding.py", line 220, in _single_func_embeddings
    returned_response = AmazonTitanG1Config()._transform_response(
                        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/tester/venv_test/lib/python3.12/site-packages/litellm/llms/bedrock/embed/amazon_titan_g1_transformation.py", line 76, in _transform_response
    embedding=_parsed_response["embedding"],
              ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^
KeyError: 'embedding'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/tester/tmp/litellm_fix.py", line 52, in <module>
    resp = litellm.embedding(
           ^^^^^^^^^^^^^^^^^^
  File "/home/tester/venv_test/lib/python3.12/site-packages/litellm/utils.py", line 1247, in wrapper
    raise e
  File "/home/tester/venv_test/lib/python3.12/site-packages/litellm/utils.py", line 1125, in wrapper
    result = original_function(*args, **kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/tester/venv_test/lib/python3.12/site-packages/litellm/main.py", line 3954, in embedding
    raise exception_type(
          ^^^^^^^^^^^^^^^
  File "/home/tester/venv_test/lib/python3.12/site-packages/litellm/litellm_core_utils/exception_mapping_utils.py", line 2214, in exception_type
    raise e
  File "/home/tester/venv_test/lib/python3.12/site-packages/litellm/litellm_core_utils/exception_mapping_utils.py", line 2190, in exception_type
    raise APIConnectionError(
litellm.exceptions.APIConnectionError: litellm.APIConnectionError: 'embedding'
Traceback (most recent call last):
  File "/home/tester/venv_test/lib/python3.12/site-packages/litellm/main.py", line 3626, in embedding
    response = bedrock_embedding.embeddings(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/tester/venv_test/lib/python3.12/site-packages/litellm/llms/bedrock/embed/embedding.py", line 432, in embeddings
    return self._single_func_embeddings(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/tester/venv_test/lib/python3.12/site-packages/litellm/llms/bedrock/embed/embedding.py", line 220, in _single_func_embeddings
    returned_response = AmazonTitanG1Config()._transform_response(
                        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/tester/venv_test/lib/python3.12/site-packages/litellm/llms/bedrock/embed/amazon_titan_g1_transformation.py", line 76, in _transform_response
    embedding=_parsed_response["embedding"],
              ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^
KeyError: 'embedding'

Are you a ML Ops Team?

No

What LiteLLM version are you on ?

1.65.6

Twitter / LinkedIn details

No response