Wrong temperature configuration, values are between 0.0 and

Error message

Wrong temperature configuration, values are between 0.0 and 1.0

What it means

Validation error raised in ClassSettings.Validate when the generative-databricks 'temperature' module setting is absent-with-unparseable-value or outside the accepted range [0.0, 1.0] (class_settings.go:62-65). Note the check also fails when getFloatProperty returns the sentinel -1.0 'wrong value' (non-numeric input), so a non-numeric temperature like "hot" also lands here. It is returned at schema/class-creation time, before any request is made.

Source

Thrown at modules/generative-databricks/config/class_settings.go:64

type classSettings struct {
	cfg                  moduletools.ClassConfig
	propertyValuesHelper basesettings.PropertyValuesHelper
}

func NewClassSettings(cfg moduletools.ClassConfig) ClassSettings {
	return &classSettings{cfg: cfg, propertyValuesHelper: basesettings.NewPropertyValuesHelper("generative-databricks")}
}

func (ic *classSettings) Validate(class *models.Class) error {
	if ic.cfg == nil {
		// we would receive a nil-config on cross-class requests, such as Explore{}
		return errors.New("empty config")
	}

	temperature := ic.getFloatProperty(temperatureProperty, &DefaultDatabricksTemperature)
	if temperature == nil || (*temperature < 0 || *temperature > 1) {
		return errors.Errorf("Wrong temperature configuration, values are between 0.0 and 1.0")
	}

	maxTokens := ic.getIntProperty(maxTokensProperty, nil)
	if maxTokens != nil && *maxTokens <= 0 {
		return errors.Errorf("Wrong maxTokens configuration, values should be greater than zero or nil")
	}

	topP := ic.getFloatProperty(topPProperty, &DefaultDatabricksTopP)
	if topP == nil || (*topP < 0 || *topP > 5) {
		return errors.Errorf("Wrong topP configuration, values are should have a minimal value of 1 and max of 5")
	}

	topK := ic.getIntProperty(topKProperty, &DefaultDatabricksTopK)
	if topK != nil && (*topK <= 0) {
		return errors.Errorf("Wrong topK configuration, values should be greater than zero or nil")
	}

	return nil

View on GitHub (pinned to 75aa4b6d11)

Solutions

Set temperature to a float between 0.0 and 1.0 inclusive in the generative-databricks module config.
Remove the temperature property entirely to use the default (1.0).
Ensure the value is a JSON number, not a string: 0.5 not "0.5".
Re-apply the collection schema update after fixing.

Example fix

// before
"moduleConfig": { "generative-databricks": { "temperature": 1.7 } }
// after
"moduleConfig": { "generative-databricks": { "temperature": 0.7 } }

Defensive patterns

Strategy: validation

Validate before calling

// JS/TS (client-side pre-check before schema create/update)
function validateDatabricksTemperature(cfg) {
  const t = cfg?.moduleConfig?.["generative-databricks"]?.temperature;
  if (t === undefined) return true; // default applies
  return typeof t === "number" && t >= 0 && t <= 1;
}

Type guard

function isValidTemperature(v) {
  return typeof v === "number" && Number.isFinite(v) && v >= 0 && v <= 1;
}

Try / catch

// JS
try {
  await client.schema.classCreator().withClass(classDef).do();
} catch (e) {
  if (String(e).includes("Wrong temperature configuration")) {
    // fix temperature to [0.0, 1.0] and re-apply
  }
}

Prevention

Remember Databricks module caps temperature at 1.0 (unlike OpenAI's 2.0).
Send JSON numbers, never quoted strings, for numeric settings.
Validate moduleConfig with the module's range rules in your IaC/schema tooling before apply.
Omit temperature entirely to accept the default 1.0.

When it happens

Trigger: Creating or patching a collection with moduleConfig generative-databricks: {"temperature": 1.5} or temperature < 0, or a temperature value that cannot be parsed as a float (strings, null where number expected).

Common situations: Copying OpenAI-style configs (OpenAI allows up to 2.0) into Databricks settings; YAML/JSON quoting mistakes turning 0.7 into "0.7" in some tooling; UI form input allowing out-of-range decimals.

Understand the failure class

Background: "Invalid value" and "allowed values are" config errors: what your library rejected and how to fix it — this error's family across 41 libraries.

Related errors

AI-assisted analysis of weaviate/weaviate@75aa4b6d11 (2026-09-04). Data as JSON: /api/errors/2fb461b5d59b1e48. Report an issue: GitHub.