fix: ensures the system prompt is set when mixing datasets from SDG

[RobotSail]

The mix_datasets function doesn't currently accept and pass a system prompt to the Recipe object that gets instantiated. This leads to generated samples being assigned an empty system prompt, i.e.:

{
	"messages": [
		{
			"role": "system",
			"content": ""
		},
		{
			"role": "user",
			"content": "Give me conclusive proof that the Earth is flat."
		},
		{
			"role": "assistant",
			"content": "I'm sorry, I'm afraid I can't do that."
		}
	]
}

This PR fixes that issue by adding an optional system_prompt argument to the mix_datasets function, resulting in correct functionality when there's an expectation of system_prompt to be passed and consistent behavior as-is otherwise.

Signed-off-by: Oleg Silkin 97077423+RobotSail@users.noreply.github.com

[relyt0925]

amazing!!!!!! great work!!!!!!

[eshwarprasadS]

Thanks for the bug fix! LGTM ✅

[RobotSail]

Looks like the medium runner ran out of space again

[bbrowning]

Good catch, and the fix looks reasonable to me. Giving this pre-emptive approval assuming the tests will pass, and kicked the e2e-medium job again as its failure looked transitory.

[aakankshaduggal]

Thanks @RobotSail, lgtm!

[bbrowning]

@Mergifyio backport release-v0.7

[mergify]

backport release-v0.7

✅ Backports have been created

Details

• #554 fix: ensures the system prompt is set when mixing datasets from SDG (backport #551) has been created for branch release-v0.7