deepset-ai/haystack · error

'chat_generators' must be a non-empty list

Error message

'chat_generators' must be a non-empty list

What it means

FallbackChatGenerator wraps a list of chat generators to try in order, so it requires at least one. An empty (or falsy) `chat_generators` list makes the component useless, and __init__ raises ValueError immediately rather than failing later at run time.

Source

Thrown at haystack/components/generators/chat/fallback.py:60

    Fail over is automatically triggered when a generator raises any exception, including:
    - Timeout errors (if the generator implements and raises them)
    - Rate limit errors (429)
    - Authentication errors (401)
    - Context length errors (400)
    - Server errors (500+)
    - Any other exception
    """

    def __init__(self, chat_generators: list[ChatGenerator]) -> None:
        """
        Creates an instance of FallbackChatGenerator.

        :param chat_generators: A non-empty list of chat generator components to try in order.
        """
        if not chat_generators:
            msg = "'chat_generators' must be a non-empty list"
            raise ValueError(msg)

        self.chat_generators = list(chat_generators)

    def to_dict(self) -> dict[str, Any]:
        """Serialize the component, including nested chat generators."""
        return default_to_dict(
            self,
            chat_generators=[
                component_to_dict(gen, name=f"chat_generator_{idx}") for idx, gen in enumerate(self.chat_generators)
            ],
        )

    @classmethod
    def from_dict(cls, data: dict[str, Any]) -> FallbackChatGenerator:
        """Rebuild the component from a serialized representation, restoring nested chat generators."""
        # Reconstruct nested chat generators from their serialized dicts
        init_params = data.get("init_parameters", {})
        serialized = init_params.get("chat_generators") or []

View on GitHub (pinned to e318778c9b)

Solutions

1. Pass at least one chat generator, e.g. FallbackChatGenerator([OpenAIChatGenerator()])
2. Validate the candidate list is non-empty before constructing the component
3. Guard the construction site: skip creating the fallback if the list is empty or raise a clearer domain error

Example fix

// before
gen = FallbackChatGenerator([])
// after
if not candidates:
    raise ValueError("no chat generators configured")
gen = FallbackChatGenerator(candidates)

if not chat_generators:
    raise ValueError("chat_generators must contain at least one generator")
generator = FallbackChatGenerator(chat_generators)

When it happens

Trigger: Calling `FallbackChatGenerator([])` or `FallbackChatGenerator()` with no generators, or with an empty list produced by an expression (e.g. [g for g in gen_list] that matched nothing).

Common situations: Building the generator list dynamically from configuration where no candidates matched; YAML pipelines with an empty list literal; filtering out generators by model availability and ending up with none.

Related errors

• Hook of type '{type(h).__name__}' is registered under hook p
• 'dimension' must be a positive integer.
• 'dimension' must be a positive integer.
• required_variables must not be empty. Set it to '*' to requi
• 'responses' must not be an empty list.

AI-assisted analysis of deepset-ai/haystack@e318778c9b (2026-08-30). Data as JSON: /api/errors/6c57b41930f96487. Report an issue: GitHub.