Unable to use OPENAILLM class with docker hosted vllm

[akshaypn]

Wrote the according to the following example at https://distilabel.argilla.io/latest/sections/how_to_guides/advanced/serving_an_llm_for_reuse/#serving-llms-using-vllm:

from distilabel.llms import OpenAILLM
from distilabel.pipeline import Pipeline
from distilabel.steps import LoadDataFromDicts
from distilabel.steps.tasks import TextGeneration, UltraFeedback

with Pipeline(name="serving-llm") as pipeline:
    load_data = LoadDataFromDicts(
        data=[{"instruction": "Write a poem about the sun and moon."}]
    )

    # `base_url` points to the address of the `vLLM` serving the LLM
    llm = OpenAILLM(base_url="http://192.168.1.138:8000", model="")

    text_generation = TextGeneration(
        llm=llm,
        num_generations=3,
        group_generations=True,
        output_mappings={"generation": "generations"},
    )

    ultrafeedback = UltraFeedback(aspect="overall-rating", llm=llm)

    load_data >> text_generation >> ultrafeedback

Running in to the following error :

    WARNING  ['distilabel.step.paraphrase_validation'] Subprocess traceback:                                                                                                                             step_wrapper.py:245
                                                                                                                                                                                                                                            
                             Traceback (most recent call last):                                                                                                                                                                             
                               File "/home/gpuwork/LLM-Postraining-Synthetic-data-generation/venv/lib/python3.10/site-packages/distilabel/pipeline/step_wrapper.py", line 229, in _non_generator_process_loop                               
                                 result = next(step.process_applying_mappings(*batch.data))                                                                                                                                                 
                               File "/home/gpuwork/LLM-Postraining-Synthetic-data-generation/venv/lib/python3.10/site-packages/distilabel/steps/base.py", line 642, in process_applying_mappings                                            
                                 for output_rows in generator:                                                                                                                                                                              
                               File "/home/gpuwork/LLM-Postraining-Synthetic-data-generation/venv/lib/python3.10/site-packages/distilabel/steps/tasks/base.py", line 267, in process                                                        
                                 outputs = self.llm.generate(                                                                                                                                                                               
                               File "/home/gpuwork/LLM-Postraining-Synthetic-data-generation/venv/lib/python3.10/site-packages/distilabel/llms/base.py", line 358, in generate                                                              
                                 return self.event_loop.run_until_complete(                                                                                                                                                                 
                               File "/usr/lib/python3.10/asyncio/base_events.py", line 649, in run_until_complete                                                                                                                           
                                 return future.result()                                                                                                                                                                                     
                               File "/home/gpuwork/LLM-Postraining-Synthetic-data-generation/venv/lib/python3.10/site-packages/distilabel/llms/base.py", line 328, in _agenerate                                                            
                                 return await asyncio.gather(*tasks)                                                                                                                                                                        
                               File "/home/gpuwork/LLM-Postraining-Synthetic-data-generation/venv/lib/python3.10/site-packages/distilabel/llms/openai.py", line 268, in agenerate                                                           
                                 completion = await self._aclient.chat.completions.create(**kwargs)  # type: ignore                                                                                                                         
                               File "/home/gpuwork/LLM-Postraining-Synthetic-data-generation/venv/lib/python3.10/site-packages/openai/resources/chat/completions.py", line 1339, in create                                                  
                                 return await self._post(                                                                                                                                                                                   
                               File "/home/gpuwork/LLM-Postraining-Synthetic-data-generation/venv/lib/python3.10/site-packages/openai/_base_client.py", line 1816, in post                                                                  
                                 return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)                                                                                                                             
                               File "/home/gpuwork/LLM-Postraining-Synthetic-data-generation/venv/lib/python3.10/site-packages/openai/_base_client.py", line 1510, in request                                                               
                                 return await self._request(                                                                                                                                                                                
                               File "/home/gpuwork/LLM-Postraining-Synthetic-data-generation/venv/lib/python3.10/site-packages/openai/_base_client.py", line 1611, in _request                                                              
                                 raise self._make_status_error_from_response(err.response) from None                                                                                                                                        
                             openai.NotFoundError: Error code: 404 - {'object': 'error', 'message': 'The model `` does not exist.', 'type': 'NotFoundError', 'param': None, 'code': 404}    

    The example explicitly mentions to keep the model name blank as ''