Quality scorer default structured output

[plaguss]

Description

Adds a default JSON schema to generate the scores in a structured manner.

from distilabel.steps.tasks import QualityScorer
from distilabel.llms.huggingface import InferenceEndpointsLLM

scorer = QualityScorer(
    llm=InferenceEndpointsLLM(
        model_id="meta-llama/Meta-Llama-3.1-70B-Instruct",
    ),
    use_default_structured_output=True
)

scorer.load()

result = next(
    scorer.process(
        [
            {
                "instruction": "instruction",
                "responses": ["good response", "weird response", "bad response"]
            }
        ]
    )
)

>>> result
[{'instruction': 'instruction',
  'responses': ['good response', 'weird response', 'bad response'],
  'scores': [1, 2, 3],
  'distilabel_metadata': {'raw_output_quality_scorer_0': '{  "scores": [1, 2, 3] }'},
  'model_name': 'meta-llama/Meta-Llama-3.1-70B-Instruct'}]

Closes #872, must be merged after #870

[github-actions]

Documentation for this PR has been built. You can view it at: https://distilabel.argilla.io/pr-873/