[Bug]: mistral-embed 'Extra inputs are not permitted'

[lolsborn]

What happened?

Related to: #1471

Currently I've tested open-mixtral-8x7b and everything works fine, but mistral-embed fails with a message that says 'Extra inputs are not permitted'

This looks like the same bug mentioned in #1471 but is effecting mistral-extra (and possibly other untested mistal models)

Relevant log output

Traceback (most recent call last):
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/proxy/proxy_server.py", line 3882, in embeddings
    response = await llm_router.aembedding(**data)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/router.py", line 1204, in aembedding
    raise e
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/router.py", line 1201, in aembedding
    response = await self.async_function_with_fallbacks(**kwargs)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/router.py", line 1386, in async_function_with_fallbacks
    raise original_exception
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/router.py", line 1307, in async_function_with_fallbacks
    response = await self.async_function_with_retries(*args, **kwargs)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/router.py", line 1447, in async_function_with_retries
    raise original_exception
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/router.py", line 1403, in async_function_with_retries
    response = await original_function(*args, **kwargs)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/router.py", line 1294, in _aembedding
    raise e
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/router.py", line 1281, in _aembedding
    response = await response
               ^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/utils.py", line 3465, in wrapper_async
    raise e
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/utils.py", line 3297, in wrapper_async
    result = await original_function(*args, **kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/main.py", line 2507, in aembedding
    raise exception_type(
          ^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/utils.py", line 8708, in exception_type
    raise e
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/utils.py", line 7461, in exception_type
    raise BadRequestError(
litellm.exceptions.BadRequestError: MistralException - Error code: 422 - {'object': 'error', 'message': {'detail': [{'type': 'extra_forbidden', 'loc': ['body', 'user'], 'msg': 'Extra inputs are not permitted', 'input': '', 'url': 'https://errors.pydantic.dev/2.5/v/extra_forbidden'}]}, 'type': 'invalid_request_error', 'param': None, 'code': None}
INFO:     127.0.0.1:61246 - "POST /embeddings HTTP/1.1" 422 Unprocessable Entity

Twitter / LinkedIn details

No response

[lolsborn]

The key bits here seem to be [{'type': 'extra_forbidden', 'loc': ['body', 'user'], 'msg': 'Extra inputs are not permitted' I think the body and user keys should be omitted

[krrishdholakia]

@lolsborn can you run the query with --detailed_debug if you're on the proxy (or litellm.set_verbose = True on the sdk)

and share what the curl request from litellm is

[lolsborn]

19:26:15 - LiteLLM Proxy:DEBUG: parallel_request_limiter.py:21 - Inside Max Parallel Request Pre-Call Hook
19:26:15 - LiteLLM:DEBUG: caching.py:22 - get cache: cache key: litellm::2024-05-18-19-26::request_count; local_only: False
19:26:15 - LiteLLM:DEBUG: caching.py:22 - get cache: cache result: {'current_requests': 0, 'current_tpm': 27819, 'current_rpm': 55}
19:26:15 - LiteLLM Proxy:DEBUG: parallel_request_limiter.py:21 - current: {'current_requests': 0, 'current_tpm': 27819, 'current_rpm': 55}
19:26:15 - LiteLLM Proxy:DEBUG: tpm_rpm_limiter.py:33 - Inside Max TPM/RPM Limiter Pre-Call Hook - token='123' key_name=None key_alias=None spend=0.0 max_budget=None expires=None models=[] aliases={} config={} user_id=None team_id=None max_parallel_requests=None metadata={} tpm_limit=None rpm_limit=None budget_duration=None budget_reset_at=None allowed_cache_controls=[] permissions={} model_spend={} model_max_budget={} soft_budget_cooldown=False litellm_budget_table=None org_id=None user_id_rate_limits=None team_id_rate_limits=None team_spend=None team_alias=None team_tpm_limit=None team_rpm_limit=None team_max_budget=None team_models=[] team_blocked=False soft_budget=None team_model_aliases=None api_key='litellm' user_role=None
19:26:15 - LiteLLM:DEBUG: caching.py:22 - get cache: cache key: litellm; local_only: False
19:26:15 - LiteLLM:DEBUG: caching.py:22 - get cache: cache result: None
19:26:15 - LiteLLM Proxy:DEBUG: tpm_rpm_limiter.py:33 - _set_limits: False
19:26:15 - LiteLLM:DEBUG: caching.py:22 - get cache: cache key: None_user_api_key_user_id; local_only: False
19:26:15 - LiteLLM:DEBUG: caching.py:22 - get cache: cache result: None
19:26:15 - LiteLLM Proxy:DEBUG: utils.py:37 - final data being sent to embeddings call: {'input': ['wall of text'], 'user': ''}'


19:26:15 - LiteLLM:DEBUG: utils.py:958 - Async Wrapper: Completed Call, calling async_success_handler: <bound method Logging.async_success_handler of <litellm.utils.Logging object at 0x109a37170>>
19:26:15 - LiteLLM:DEBUG: utils.py:958 - Logging Details LiteLLM-Success Call: None
19:26:15 - LiteLLM:DEBUG: utils.py:1309 - Model=dataroom-mvp-gpt35;
19:26:15 - LiteLLM:DEBUG: utils.py:4052 - completion_response response ms: 996.063 
19:26:15 - LiteLLM:DEBUG: utils.py:958 - Looking up model=azure/gpt-35-turbo in model_cost_map
19:26:15 - LiteLLM:DEBUG: utils.py:958 - Success: model=azure/gpt-35-turbo in model_cost_map
19:26:15 - LiteLLM:DEBUG: utils.py:958 - prompt_tokens=499; completion_tokens=1
19:26:15 - LiteLLM:DEBUG: utils.py:958 - Returned custom cost for model=azure/gpt-35-turbo - prompt_tokens_cost_usd_dollar: 0.0007485, completion_tokens_cost_usd_dollar: 2e-06
19:26:15 - LiteLLM:DEBUG: utils.py:958 - final cost: 0.0007505000000000001; prompt_tokens_cost_usd_dollar: 0.0007485; completion_tokens_cost_usd_dollar: 2e-06
19:26:15 - LiteLLM:DEBUG: utils.py:958 - success callbacks: [<litellm.proxy.hooks.parallel_request_limiter._PROXY_MaxParallelRequestsHandler object at 0x1093e9d60>, <litellm.proxy.hooks.tpm_rpm_limiter._PROXY_MaxTPMRPMLimiter object at 0x1093e9d90>, <litellm.proxy.hooks.max_budget_limiter._PROXY_MaxBudgetLimiter object at 0x1093e9dc0>, <litellm.proxy.hooks.cache_control_check._PROXY_CacheControlCheck object at 0x1093e9df0>, <litellm._service_logger.ServiceLogging object at 0x109792930>]
19:26:15 - LiteLLM Router:INFO: router.py:529 - litellm.acompletion(model=azure/dataroom-mvp-gpt35)�[32m 200 OK
19:26:15 - LiteLLM Router:DEBUG: router.py:1308 - Async Response: ModelResponse(id='chatcmpl-9QQXXXTOuRrSJznUiDjqaYMzDbxxd', choices=[Choices(finish_reason='stop', index=0, message=Message(content='100', role='assistant'))], created=1716085575, model='gpt-35-turbo', object='chat.completion', system_fingerprint=None, usage=Usage(completion_tokens=1, prompt_tokens=499, total_tokens=500))
19:26:15 - LiteLLM:DEBUG: utils.py:958 - Logging Details LiteLLM-Async Success Call: None
19:26:15 - LiteLLM:DEBUG: utils.py:1309 - Model=dataroom-mvp-gpt35;
19:26:15 - LiteLLM:DEBUG: utils.py:4052 - completion_response response ms: 996.063 
19:26:15 - LiteLLM:DEBUG: utils.py:958 - Looking up model=azure/gpt-35-turbo in model_cost_map
19:26:15 - LiteLLM:DEBUG: utils.py:958 - Success: model=azure/gpt-35-turbo in model_cost_map
19:26:15 - LiteLLM:DEBUG: utils.py:958 - prompt_tokens=499; completion_tokens=1
19:26:15 - LiteLLM:DEBUG: utils.py:958 - Returned custom cost for model=azure/gpt-35-turbo - prompt_tokens_cost_usd_dollar: 0.0007485, completion_tokens_cost_usd_dollar: 2e-06
19:26:15 - LiteLLM:DEBUG: utils.py:958 - final cost: 0.0007505000000000001; prompt_tokens_cost_usd_dollar: 0.0007485; completion_tokens_cost_usd_dollar: 2e-06
19:26:15 - LiteLLM:DEBUG: utils.py:958 - Async success callbacks: [<litellm.proxy.hooks.parallel_request_limiter._PROXY_MaxParallelRequestsHandler object at 0x1093e9d60>, <litellm.proxy.hooks.tpm_rpm_limiter._PROXY_MaxTPMRPMLimiter object at 0x1093e9d90>, <litellm.proxy.hooks.max_budget_limiter._PROXY_MaxBudgetLimiter object at 0x1093e9dc0>, <litellm.proxy.hooks.cache_control_check._PROXY_CacheControlCheck object at 0x1093e9df0>, <litellm._service_logger.ServiceLogging object at 0x109792930>, <bound method ProxyLogging.response_taking_too_long_callback of <litellm.proxy.utils.ProxyLogging object at 0x1093e99a0>>]
19:26:15 - LiteLLM Proxy:DEBUG: parallel_request_limiter.py:21 - INSIDE parallel request limiter ASYNC SUCCESS LOGGING
19:26:15 - LiteLLM:DEBUG: caching.py:22 - get cache: cache key: litellm::2024-05-18-19-26::request_count; local_only: False
19:26:15 - LiteLLM:DEBUG: caching.py:22 - get cache: cache result: {'current_requests': 0, 'current_tpm': 27819, 'current_rpm': 55}
19:26:15 - LiteLLM Proxy:DEBUG: parallel_request_limiter.py:21 - updated_value in success call: {'current_requests': 0, 'current_tpm': 28319, 'current_rpm': 56}, precise_minute: 2024-05-18-19-26
19:26:15 - LiteLLM:DEBUG: caching.py:22 - set cache: key: litellm::2024-05-18-19-26::request_count; value: {'current_requests': 0, 'current_tpm': 28319, 'current_rpm': 56}
19:26:15 - LiteLLM:DEBUG: caching.py:22 - InMemoryCache: set_cache
19:26:15 - LiteLLM Proxy:DEBUG: tpm_rpm_limiter.py:33 - INSIDE TPM RPM Limiter ASYNC SUCCESS LOGGING
19:26:15 - LiteLLM:DEBUG: caching.py:22 - get cache: cache key: litellm; local_only: False
19:26:15 - LiteLLM:DEBUG: caching.py:22 - get cache: cache result: None
INFO:     127.0.0.1:60313 - "POST /chat/completions HTTP/1.1" 200 OK
19:26:16 - LiteLLM:DEBUG: utils.py:958 - RAW RESPONSE:
Error code: 422 - {'object': 'error', 'message': {'detail': [{'type': 'extra_forbidden', 'loc': ['body', 'user'], 'msg': 'Extra inputs are not permitted', 'input': '', 'url': 'https://errors.pydantic.dev/2.5/v/extra_forbidden'}]}, 'type': 'invalid_request_error', 'param': None, 'code': None}


19:26:16 - LiteLLM:DEBUG: utils.py:958 - Logging Details: logger_fn - None | callable(logger_fn) - False
19:26:16 - LiteLLM:DEBUG: utils.py:958 - Logging Details LiteLLM-Failure Call
19:26:16 - LiteLLM Router:DEBUG: router.py:1775 - Attempting to add 123444 to cooldown list. updated_fails: 1; self.allowed_fails: 0
19:26:16 - LiteLLM:DEBUG: caching.py:22 - get cache: cache key: 02-26:cooldown_models; local_only: False
19:26:16 - LiteLLM:DEBUG: caching.py:22 - get cache: cache result: None
19:26:16 - LiteLLM Router:DEBUG: router.py:1784 - adding 123444 to cooldown models
19:26:16 - LiteLLM:DEBUG: caching.py:22 - set cache: key: 02-26:cooldown_models; value: ['123444']
19:26:16 - LiteLLM:DEBUG: caching.py:22 - InMemoryCache: set_cache
19:26:16 - LiteLLM Proxy:DEBUG: parallel_request_limiter.py:21 - Inside Max Parallel Request Failure Hook
19:26:16 - LiteLLM Proxy:DEBUG: parallel_request_limiter.py:21 - user_api_key: litellm
19:26:16 - LiteLLM:DEBUG: caching.py:22 - get cache: cache key: litellm::2024-05-18-19-26::request_count; local_only: False
19:26:16 - LiteLLM:DEBUG: caching.py:22 - get cache: cache result: {'current_requests': 0, 'current_tpm': 28319, 'current_rpm': 56}
19:26:16 - LiteLLM Proxy:DEBUG: parallel_request_limiter.py:21 - updated_value in failure call: {'current_requests': 0, 'current_tpm': 28319, 'current_rpm': 56}
19:26:16 - LiteLLM:DEBUG: caching.py:22 - set cache: key: litellm::2024-05-18-19-26::request_count; value: {'current_requests': 0, 'current_tpm': 28319, 'current_rpm': 56}
19:26:16 - LiteLLM:DEBUG: caching.py:22 - InMemoryCache: set_cache
19:26:16 - LiteLLM Router:INFO: router.py:1289 - litellm.aembedding(model=mistral/mistral-embed) Exception MistralException - Error code: 422 - {'object': 'error', 'message': {'detail': [{'type': 'extra_forbidden', 'loc': ['body', 'user'], 'msg': 'Extra inputs are not permitted', 'input': '', 'url': 'https://errors.pydantic.dev/2.5/v/extra_forbidden'}]}, 'type': 'invalid_request_error', 'param': None, 'code': None}
19:26:16 - LiteLLM Router:DEBUG: router.py:1311 - TracebackTraceback (most recent call last):
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/main.py", line 2498, in aembedding
    response = await init_response
               ^^^^^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/llms/openai.py", line 628, in aembedding
    raise e
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/llms/openai.py", line 611, in aembedding
    response = await openai_aclient.embeddings.create(**data, timeout=timeout)  # type: ignore
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/openai/resources/embeddings.py", line 214, in create
    return await self._post(
           ^^^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/openai/_base_client.py", line 1782, in post
    return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/openai/_base_client.py", line 1485, in request
    return await self._request(
           ^^^^^^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/openai/_base_client.py", line 1576, in _request
    raise self._make_status_error_from_response(err.response) from None
openai.UnprocessableEntityError: Error code: 422 - {'object': 'error', 'message': {'detail': [{'type': 'extra_forbidden', 'loc': ['body', 'user'], 'msg': 'Extra inputs are not permitted', 'input': '', 'url': 'https://errors.pydantic.dev/2.5/v/extra_forbidden'}]}, 'type': 'invalid_request_error', 'param': None, 'code': None}

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/router.py", line 1307, in async_function_with_fallbacks
    response = await self.async_function_with_retries(*args, **kwargs)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/router.py", line 1447, in async_function_with_retries
    raise original_exception
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/router.py", line 1403, in async_function_with_retries
    response = await original_function(*args, **kwargs)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/router.py", line 1294, in _aembedding
    raise e
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/router.py", line 1281, in _aembedding
    response = await response
               ^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/utils.py", line 3465, in wrapper_async
    raise e
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/utils.py", line 3297, in wrapper_async
    result = await original_function(*args, **kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/main.py", line 2507, in aembedding
    raise exception_type(
          ^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/utils.py", line 8708, in exception_type
    raise e
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/utils.py", line 7461, in exception_type
    raise BadRequestError(
litellm.exceptions.BadRequestError: MistralException - Error code: 422 - {'object': 'error', 'message': {'detail': [{'type': 'extra_forbidden', 'loc': ['body', 'user'], 'msg': 'Extra inputs are not permitted', 'input': '', 'url': 'https://errors.pydantic.dev/2.5/v/extra_forbidden'}]}, 'type': 'invalid_request_error', 'param': None, 'code': None}

19:26:16 - LiteLLM Router:DEBUG: router.py:1315 - Trying to fallback b/w models
Traceback (most recent call last):
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/main.py", line 2498, in aembedding
    response = await init_response
               ^^^^^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/llms/openai.py", line 628, in aembedding
    raise e
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/llms/openai.py", line 611, in aembedding
    response = await openai_aclient.embeddings.create(**data, timeout=timeout)  # type: ignore
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/openai/resources/embeddings.py", line 214, in create
    return await self._post(
           ^^^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/openai/_base_client.py", line 1782, in post
    return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/openai/_base_client.py", line 1485, in request
    return await self._request(
           ^^^^^^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/openai/_base_client.py", line 1576, in _request
    raise self._make_status_error_from_response(err.response) from None
openai.UnprocessableEntityError: Error code: 422 - {'object': 'error', 'message': {'detail': [{'type': 'extra_forbidden', 'loc': ['body', 'user'], 'msg': 'Extra inputs are not permitted', 'input': '', 'url': 'https://errors.pydantic.dev/2.5/v/extra_forbidden'}]}, 'type': 'invalid_request_error', 'param': None, 'code': None}

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/proxy/proxy_server.py", line 3882, in embeddings
    response = await llm_router.aembedding(**data)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/router.py", line 1204, in aembedding
    raise e
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/router.py", line 1201, in aembedding
    response = await self.async_function_with_fallbacks(**kwargs)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/router.py", line 1386, in async_function_with_fallbacks
    raise original_exception
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/router.py", line 1307, in async_function_with_fallbacks
    response = await self.async_function_with_retries(*args, **kwargs)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/router.py", line 1447, in async_function_with_retries
    raise original_exception
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/router.py", line 1403, in async_function_with_retries
    response = await original_function(*args, **kwargs)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/router.py", line 1294, in _aembedding
    raise e
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/router.py", line 1281, in _aembedding
    response = await response
               ^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/utils.py", line 3465, in wrapper_async
    raise e
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/utils.py", line 3297, in wrapper_async
    result = await original_function(*args, **kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/main.py", line 2507, in aembedding
    raise exception_type(
          ^^^^^^^^^^^^^^^
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/utils.py", line 8708, in exception_type
    raise e
  File "/opt/casemark/litellm/lib/python3.12/site-packages/litellm/utils.py", line 7461, in exception_type
    raise BadRequestError(
litellm.exceptions.BadRequestError: MistralException - Error code: 422 - {'object': 'error', 'message': {'detail': [{'type': 'extra_forbidden', 'loc': ['body', 'user'], 'msg': 'Extra inputs are not permitted', 'input': '', 'url': 'https://errors.pydantic.dev/2.5/v/extra_forbidden'}]}, 'type': 'invalid_request_error', 'param': None, 'code': None}
INFO:     127.0.0.1:60288 - "POST /embeddings HTTP/1.1" 422 Unprocessable Entity
INFO:     Shutting down
INFO:     Waiting for application shutdown.
INFO:     Application shutdown complete.
INFO:     Finished server process [55640]```

[lolsborn]

I realize this is not a real solution, but adding line 4253 is solving this issue for me on Mistral at the moment

[lolsborn]

Actually do we ever need the user field for embed creation?