Add approach to flexibly inject system_messages

[davidberenstein1957]

I saw the use_system_prompt argument was supposed to be removed in the 1.5 release and it seemed like a good excuse to allow flexible system prompt injection across all tasks.

For the synthetic data generator, I noticed this was a limitation for a more dynamic and diverse generation.

I am unsure if it is relevant for things like URIAL, and some system prompts seem to rely on .format, so we could disable it there too, but let's iterate a bit on this PR.

We can now always do.

task = RandomTask(
    system_prompt="I generally want you to focus on this"
)
task.load()
task.process(inputs=[
    [{"role": "system", "content": "focus more on this"}],
    [{"role": "system", "content": "focus more on that"}]
])

[github-actions]

Documentation for this PR has been built. You can view it at: https://distilabel.argilla.io/pr-1087/

[davidberenstein1957]

cc @davanstrien I believe you also vouched for something like this a while ago.

[codspeed-hq]

CodSpeed Performance Report

Merging #1087 will not alter performance

_{Comparing feat/align-usage-system-prompts-across-tasks (f88ded9) with develop (f1f7d77)}

Summary

✅ 1 untouched benchmarks