Start Job
Starts a Generation Data job
Authorizations
Body
The application description for which the inputs would be applicable.
"Write a children's story communicating a simple life lesson."
The number of new LLM inputs to generate
50
The list of LLM inputs to be used as seeds
[
"The quick brown fox jumped over the lazy dog",
"The lazy dog was jumped over by the quick brown fox"
]
Number of inputs to generate in one LLM call. Must be <= 125. Generally it could be same as num_shots
.
10
The exloration mode for input generation. Defaults to BALANCED
CONSERVATIVE
, BALANCED
, CREATIVE
, ADVENTUROUS
Number of inputs to be included in the prompt for generation. Must be <= 50. Generally it could be same as batch_size
.
5
If true, multiple batches of generation and critique run concurrently.
true
Response
DataGenerationStatus is the result of a data generation job.
Detailed status of the job
["Downloading model", "Tuning prompt"]
The job id
"1234abcd"
Current state of the job
QUEUED
, RUNNING
, DONE
, ERROR
, CANCELLED
The generated data. Can be present even if the state is not done/error as it is streamed.
[
"The quick brown fox jumped over the lazy dog",
"The lazy dog was jumped over by the quick brown fox"
]