zylon-ai/private-gpt · error · ValueError

Model '{target_model}' not found. Available: {available}

Error message

Model '{target_model}' not found. Available: {available}

What it means

ValueError from LLMComponent.get_llm: target_model (the passed model_id or the default) is not in the registry, and the error lists all registered aliases so you can see valid values. Registry keys are model ids plus registered aliases; anything else is rejected.

Source

Thrown at private_gpt/components/llm/llm_component.py:135

                raise ValueError(
                    f"Default model '{self._default_model_id}' not found in registered models"
                )

            if not self.registry.get(LLMRegistry.default()):
                self.registry.register(LLMRegistry.default(), default_instance)

            logger.info("Set default model to '%s'", self._default_model_id)

    def get_llm(self, model_id: str | None = None) -> LLM:
        target_model = model_id or self._default_model_id

        if not target_model:
            raise ValueError("No model specified and no models are configured")

        llm_instance = self.registry.get(target_model)
        if not llm_instance:
            available = self.registry.get_all_aliases()
            raise ValueError(
                f"Model '{target_model}' not found. Available: {available}"
            )

        return llm_instance.llm

    def get_alias(self, model_id: str | None = None) -> str | None:
        target_model = model_id or self._default_model_id
        if not target_model:
            return None
        aliases = self.registry.get_aliases(target_model)
        return aliases.pop() if aliases else None

    def get_config(self, model_id: str | None = None) -> LLMModelConfig:
        target_model = model_id or self._default_model_id

        if not target_model:
            raise ValueError("No model specified and no models are configured")

View on GitHub (pinned to 4a030776a3)

Solutions

1. Use one of the ids/aliases from the error's Available list.
2. If the model should exist, check startup logs for 'Skipping unavailable LLM model' and fix its init failure.
3. Add the requested id/alias to llm.models in settings if it's genuinely missing.

Example fix

# before
llm = component.get_llm("gpt4o")

# after (exact registered id)
llm = component.get_llm("gpt-4o")

def model_is_available(component, model_id: str) -> bool:
    return component.registry.get(model_id) is not None

def is_registered_model(component, model_id: object) -> bool:
    return isinstance(model_id, str) and component.registry.get(model_id) is not None

try:
    llm = component.get_llm(model_id)
except ValueError as e:
    if 'not found. Available' in str(e):
        available = component.registry.get_all_aliases()
        raise ModelNotFoundError(f'{model_id} not in {available}') from e
    raise

When it happens

Trigger: Calling get_llm("foo") with an unregistered id; requesting a model whose registration was skipped at startup due to init failure; using an alias that was never registered for the model.

Common situations: API/CLI consumers passing an arbitrary model name; typos in model ids; models that failed to register (check startup warnings) but are still requested.

Related errors

• LLM mode '{mode}' is not supported. Available: {available}
• No model specified and no models are configured
• Model config '{target_model}' not found. Available: {availab
• Unknown memory type: {type}
• Audio blocks found but no audio-capable LLM provided.

AI-assisted analysis of zylon-ai/private-gpt@4a030776a3 (2026-08-15). Data as JSON: /api/errors/5a665a85ff775071. Report an issue: GitHub.