microsoft/qlib · error · ValueError

Please give the search space of model.

Error message

Please give the search space of model.

What it means

QLibTuner.setup_space (qlib/contrib/tuner/tuner.py) requires the tuner config's 'model' section to name a search space class (key 'space'). That name is resolved via getattr on qlib.contrib.tuner.space, so a missing space key raises ValueError('Please give the search space of model.') before any tuning starts.

Source

Thrown at qlib/contrib/tuner/tuner.py:173

        estimator_config["strategy"].update({"args": params["strategy_space"]})
        if params.get("data_label_space", None) is not None:
            estimator_config["data"]["args"].update(params["data_label_space"])

        estimator_path = os.path.join(
            self.tuner_config["experiment"].get("dir", "../"),
            QLibTuner.ESTIMATOR_CONFIG_NAME,
        )

        with open(estimator_path, "w") as fp:
            yaml.dump(estimator_config, fp)

        return estimator_path

    def setup_space(self):
        # 1. Setup model space
        model_space_name = self.tuner_config["model"].get("space", None)
        if model_space_name is None:
            raise ValueError("Please give the search space of model.")
        model_space = getattr(
            importlib.import_module(".space", package="qlib.contrib.tuner"),
            model_space_name,
        )

        # 2. Setup strategy space
        strategy_space_name = self.tuner_config["strategy"].get("space", None)
        if strategy_space_name is None:
            raise ValueError("Please give the search space of strategy.")
        strategy_space = getattr(
            importlib.import_module(".space", package="qlib.contrib.tuner"),
            strategy_space_name,
        )

        # 3. Setup data label space if given
        if self.tuner_config.get("data_label", None) is not None:
            data_label_space_name = self.tuner_config["data_label"].get("space", None)
            if data_label_space_name is not None:

View on GitHub (pinned to 79633dd950)

Solutions

1. Add a space key under model in the tuner YAML pointing to a class in qlib.contrib.tuner.space, e.g. model: {space: LGBModelSpace}
2. Verify the named class exists in qlib/contrib/tuner/space.py (import errors surface as AttributeError next)
3. Base your config on the shipped tuner examples (examples/tuner or benchmarks workflow tuner yaml)

Example fix

# before (tuner_config.yaml)
model:
  class: LGBModel
  module_path: qlib.contrib.model.gbdt

# after
model:
  space: LGBModelSpace
  class: LGBModel
  module_path: qlib.contrib.model.gbdt

model_space = cfg.get('model', {}).get('space')
assert model_space, 'tuner config model section needs a space: entry'
from qlib.contrib.tuner import space as tuner_space
assert hasattr(tuner_space, model_space), f'{model_space} not found in qlib.contrib.tuner.space'

When it happens

Trigger: A tuner YAML whose model section lacks the space key (model: {class: ..., module: ...} with no space:) triggers the error when QLibTuner.setup_space() runs at tuner initialization.

Common situations: Reusing a plain workflow/model config (which has no search space) as a tuner config; trimming the example tuner YAML too aggressively; the space class name given also needs to exist in qlib/contrib/tuner/space.py or AttributeError follows.

Related errors

• Please give the search space of strategy.
• Config path is invalid.
• report_type should be one of pred_long, pred_long_short, pre
• report_factor should be one of annualized_return, informatio
• optim_type should be min, max or correlation

AI-assisted analysis of microsoft/qlib@79633dd950 (2026-08-15). Data as JSON: /api/errors/7d7f3e9c7c0e0578. Report an issue: GitHub.