Is this the right way to pass in sampling/generation parameters using the API?

[arnavgarg1]

import openllm
client = openllm.client.HTTPClient('http://localhost:3000')

# Setup Generation Parameters
generation_parameters = {
	'temperature': 0.1,
	'max_new_tokens': 512
}

client.query("What is the meaning of life?", **generation_parameters)

[arnavgarg1]

It does look like it is doing the right thing, but just want to confirm

[aarnphm]

Yes, you can just pass in the generation configuration into query