[Bug] litellm.exceptions.BadRequestError: litellm.BadRequestError: Text-completion-openaiException - Error code: 400

[yury-gurevich]

What happened?

when i run this code i get:
(dspy) C:\Users\yury_\Downloads\project\dspy>C:/Users/yury_/miniconda3/envs/dspy/python.exe c:/Users/yury_/Downloads/project/dspy/dspy_direct.py
Traceback (most recent call last):
File "C:\Users\yury_\miniconda3\envs\dspy\Lib\site-packages\litellm\llms\openai\completion\handler.py", line 125, in completion
raw_response = openai_client.completions.with_raw_response.create(**data) # type: ignore
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\yury_\miniconda3\envs\dspy\Lib\site-packages\openai_legacy_response.py", line 364, in wrapped
return cast(LegacyAPIResponse[R], func(*args, **kwargs))
^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\yury_\miniconda3\envs\dspy\Lib\site-packages\openai_utils_utils.py", line 279, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\yury_\miniconda3\envs\dspy\Lib\site-packages\openai\resources\completions.py", line 539, in create
return self.post(
^^^^^^^^^^^
File "C:\Users\yury\miniconda3\envs\dspy\Lib\site-packages\openai_base_client.py", line 1296, in post
return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\yury_\miniconda3\envs\dspy\Lib\site-packages\openai_base_client.py", line 973, in request
return self.request(
^^^^^^^^^^^^^^
File "C:\Users\yury\miniconda3\envs\dspy\Lib\site-packages\openai_base_client.py", line 1077, in _request
raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'error': {'message': 'invalid model ID', 'type': 'invalid_request_error', 'param': None, 'code': None}}

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "C:\Users\yury_\miniconda3\envs\dspy\Lib\site-packages\litellm\main.py", line 1528, in completion
response = openai_text_completions.completion(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\yury\miniconda3\envs\dspy\Lib\site-packages\litellm\llms\openai\completion\handler.py", line 148, in completion
raise OpenAIError(
litellm.llms.openai.common_utils.OpenAIError: Error code: 400 - {'error': {'message': 'invalid model ID', 'type': 'invalid_request_error', 'param': None, 'code': None}}

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "c:\Users\yury_\Downloads\project\dspy\dspy_direct.py", line 19, in
print(lm("Translate English to French: 'Hello, how are you?'"))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\yury_\miniconda3\envs\dspy\Lib\site-packages\dspy\utils\callback.py", line 266, in wrapper
return fn(instance, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\yury_\miniconda3\envs\dspy\Lib\site-packages\dspy\clients\lm.py", line 115, in call
response = completion(
^^^^^^^^^^^
File "C:\Users\yury_\miniconda3\envs\dspy\Lib\site-packages\dspy\clients\lm.py", line 319, in wrapper
return func_cached(key, request, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\yury_\miniconda3\envs\dspy\Lib\site-packages\cachetools_init_.py", line 771, in wrapper
v = func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\yury_\miniconda3\envs\dspy\Lib\site-packages\dspy\clients\lm.py", line 309, in func_cached
return func(request, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\yury_\miniconda3\envs\dspy\Lib\site-packages\dspy\clients\lm.py", line 374, in cached_litellm_text_completion
return litellm_text_completion(
^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\yury_\miniconda3\envs\dspy\Lib\site-packages\dspy\clients\lm.py", line 394, in litellm_text_completion
return litellm.text_completion(
^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\yury_\miniconda3\envs\dspy\Lib\site-packages\litellm\utils.py", line 1212, in wrapper
raise e
File "C:\Users\yury_\miniconda3\envs\dspy\Lib\site-packages\litellm\utils.py", line 1090, in wrapper
result = original_function(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\yury_\miniconda3\envs\dspy\Lib\site-packages\litellm\main.py", line 4209, in text_completion
response = completion(
^^^^^^^^^^^
File "C:\Users\yury_\miniconda3\envs\dspy\Lib\site-packages\litellm\utils.py", line 1212, in wrapper
raise e
File "C:\Users\yury_\miniconda3\envs\dspy\Lib\site-packages\litellm\utils.py", line 1090, in wrapper
result = original_function(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\yury_\miniconda3\envs\dspy\Lib\site-packages\litellm\main.py", line 3093, in completion
raise exception_type(
^^^^^^^^^^^^^^^
File "C:\Users\yury_\miniconda3\envs\dspy\Lib\site-packages\litellm\litellm_core_utils\exception_mapping_utils.py", line 2210, in exception_type
raise e
File "C:\Users\yury_\miniconda3\envs\dspy\Lib\site-packages\litellm\litellm_core_utils\exception_mapping_utils.py", line 328, in exception_type
raise BadRequestError(
litellm.exceptions.BadRequestError: litellm.BadRequestError: Text-completion-openaiException - Error code: 400 - {'error': {'message': 'invalid model ID', 'type': 'invalid_request_error', 'param': None, 'code': None}}

(dspy) C:\Users\yury_\Downloads\project\dspy>

Steps to reproduce

`import dspy
import os
from dotenv import load_dotenv

load_dotenv() # Load environment variables from .env file

hf_token = os.environ.get("HF_TOKEN")

lm = dspy.LM(
model="huggingface/google-t5/t5-small", # Correct model name for Hugging Face client
max_tokens=100, # Added to fix potential issues
model_type="text",
provider="huggingface",
num_retries=1,
launch_kwargs={}, # Ensure no unused model_kwargs are passed
)
dspy.settings.configure(lm=lm)

print(lm("Translate English to French: 'Hello, how are you?'"))`

DSPy version

2.6.10