Developer documentation > API reference > Generative Syftr search.

Generative Syftr search.¶

syftr is an optimizer that helps to find the best LLM blueprints for your data.¶

SearchStudy¶

class datarobot.models.genai.syftr_search.SearchStudy

Metadata for a DataRobot syftr search study.

Parameters

Parameter	Type	Description
`search_space`	`Optional[Dict[str`, `Any]]`	Search space configuration used for the study.
`use_case_id`	`str`	The ID of the use case the search study is linked to.
`grounding_dataset_id`	`str`	The ID of the dataset used to build vector databases.
`eval_dataset_id`	`str`	The ID of the evaluation dataset.
`grounding_dataset_name`	`str`	The name of the grounding dataset.
`eval_dataset_name`	`str`	The name of the evaluation dataset.
`user_id`	`str`	The ID of the user.
`user_name`	`str`	The name of the user who ran the study.
`num_trials`	`int`	The number of search trials to sample.
`num_concurrent_trials`	`int`	The number of simultaneously running trials.
`optimization_objectives`	`List[Tuple[str`, `str]]`	Optimization objectives of the study, defined as (objective, direction) pairs.
`playground_id`	`str`	The ID of the associated playground.
`temp_playground_id`	`Optional[str]`	The ID of the temporary playground.
`pareto_front`	`Optional[List[Dict[str`, `Any]]]`	Pareto frontier of the study.
`datetime_start`	`str`	Study start time.
`datetime_end`	`Optional[str]`	Study end time.
`study_status`	`str`	Status of the study (e.g., RUNNING, COMPLETED, FAILED).
`search_study_id`	`str`	The ID of the search study.
`name`	`str`	Name of the search study.
`job_id`	`Optional[str]`	The ID of the worker job (UUID4).
`trials_running`	`Optional[int]`	Number of currently running trials.
`trials_failed`	`Optional[int]`	Number of failed trials.
`trials_success`	`Optional[int]`	Number of completed trials.
`all_trials`	`Optional[List[Dict[str`, `Any]]]`	Trials history.
`existing_blueprint_ids`	`Optional[List[str]]`	IDs of existing LLM blueprints for comparative evaluation.
`eval_results`	`Optional[List[Any]]`	Results of the comparative evaluation.
`error_message`	`Optional[str]`	Error message if the study fails.
`max_timeout`	`Optional[int]`	Maximal running time of the search.
`prune_pareto`	`bool`	Whether to use Pareto pruner for the search.
`max_cost`	`Optional[float]`	Maximal cost of the search.

create()¶

classmethod create()

Create a new search search study with the specified parameters.

Parameters

Parameter	Type	Description
`use_case_id`	`str`	The ID of the use case the search study is linked to.
`playground_id`	`str`	The ID of the existing playground associated with the search.
`grounding_dataset_id`	`str`	The ID of the dataset used to build vector databases.
`eval_dataset_id`	`str`	The ID of the evaluation dataset.
`num_trials`	`int`	The number of search trials to sample.
`num_concurrent_trials`	`int`	The number of simultaneously running trials.
`optimization_objectives`	`List[Tuple[ObjectiveType`, `DirectionType]]`	Optimization objectives of the study, defined as (objective, direction) pairs.
`search_space`	`SearchSpaceDict`	Search space configuration for the search.
`name`	`str`	Name of the search study.
`max_timeout`	`Optional[int]`	Maximal running time of the search.
`max_cost`	`Optional[float]`	Maximal cost of the search.
`prune_pareto`	`bool`	Whether to use Pareto pruner for the search.
`wait_for_completion`	`bool`, optional	If `True`, block until the study reaches `COMPLETED` or `FAILED` and return the final `SearchStudy`. If `False` (default), return immediately with the study in `RUNNING` state. Use `wait_for_completion()` on the returned object to wait later.
`max_wait`	`int`, optional	Maximum number of seconds to wait when `wait_for_completion=True`. Defaults to 10800 (3 hours). Raises `AsyncTimeoutError` if exceeded.

Returns

Returns	Description
search study	The created search study.

Return type: SearchStudy

wait_for_completion()¶

method wait_for_completion()

Block until the study reaches COMPLETED or FAILED and return the updated object.

Uses the same async resolution path as create(wait_for_completion=True). The status URL is derived from the job_id field, so this method works on any SearchStudy instance that has a job_id — including those fetched via get().

Parameters

Parameter	Type	Description
`max_wait`	`int`, optional	Maximum number of seconds to wait. Defaults to 10800 (3 hours).

Returns

Returns	Description
search study	The updated study object once the study has finished.

Return type: SearchStudy

Raises

Exception	Description
ValueError	If `job_id` is `None` (the study has no associated async job).
AsyncTimeoutError	If the study does not finish within `max_wait` seconds.

get()¶

classmethod get()

Read an existing search study.

Parameters

Parameter	Type	Description
`search_study_id`	`str`	ID of the search study used for creation.

Returns

Returns	Description
search study	The created search study database.

Return type: SearchStudy

list()¶

classmethod list()

List all syftr search studies associated with a specific use case available to the user.

Parameters

Parameter	Type	Description
`use_case`	`UseCaseLike`	The returned search studies are filtered to those associated with a specific Use Case(s) if specified or can be inferred from the context. Accepts either the entity or the ID.
`playground`	`Optional[Union[Playground`, `str]]`, optional	The returned search studies are filtered to those associated with a specific playground if it is specified. Accepts either the entity or the ID.
`search`	`Optional[str]`	String for filtering search studies. Search studies that contain the string in name will be returned. If not specified, all search studies will be returned.
`sort`	`Optional[str]`	Property to sort search studies by. Prefix the attribute name with a dash to sort in descending order, e.g., sort=’-creationDate’. Currently supported options are “name”.

Returns

Returns	Description
search studies	A list of search studies available to the user.

Return type: list[SearchStudy]

delete()¶

method delete()

Delete the search study and all its related artifacts.

Return type: None