infiniflow/ragflow · error · LookupError

Model {model_name} cannot be used as {model_type_val} model.

Error message

Model {model_name} cannot be used as {model_type_val} model.

What it means

Error "Model {model_name} cannot be used as {model_type_val} model." thrown in infiniflow/ragflow.

Source

Thrown at api/db/joint_services/tenant_model_service.py:294

            "llm_name": pure_model_name,
            "api_base": embedding_cfg["base_url"],
            "model_type": LLMType.EMBEDDING.value,
        }

    provider_obj = TenantModelProviderService.get_by_tenant_id_and_provider_name(tenant_id, provider_name)
    if not provider_obj:
        raise LookupError(f"Provider {provider_name} not found for model {model_name}.")
    instance_obj = _resolve_instance_for_model(provider_obj, instance_name, model_name)
    model_obj = TenantModelService.get_by_provider_id_and_instance_id_and_model_type_and_model_name(provider_obj.id, instance_obj.id, model_type_val, pure_model_name)

    api_key, is_tool, api_key_payload = _decode_api_key_config(instance_obj.api_key)
    extra_fields = json.loads(instance_obj.extra) if instance_obj.extra else {}

    if model_obj:
        if model_obj.status == ActiveStatusEnum.INACTIVE.value:
            raise LookupError(f"Model {model_name} is disabled.")
        if model_obj.status == ActiveStatusEnum.UNSUPPORTED.value:
            raise LookupError(f"Model {model_name} cannot be used as {model_type_val} model.")

        model_extra = json.loads(model_obj.extra) if model_obj.extra else {}
        llm_info = _lookup_factory_llm_info(provider_obj.provider_name, pure_model_name, extra_fields)
        if "max_tokens" in model_extra:
            max_tokens = model_extra["max_tokens"]
        else:
            max_tokens = (llm_info or {}).get("max_tokens", 8192)
        model_config = {
            "llm_factory": provider_obj.provider_name,
            "api_key": api_key,
            "llm_name": model_obj.model_name,
            "api_base": extra_fields.get("base_url", ""),
            "model_type": model_type_val,
            "is_tools": model_extra.get("is_tools", is_tool),
            "max_tokens": max_tokens,
        }
        if provider_name.lower() == "somark":
            # SoMark/OCR factories read parser config (somark_*, parse_method, ...)

View on GitHub (pinned to 554fb1133a)

Solutions

1. Use the model only for its declared model type.
2. Configure a model that supports the requested type.

Example fix

# do not use a chat llm where an embedding model is required

When it happens

Trigger: Thrown at api/db/joint_services/tenant_model_service.py:294 when the library encounters an invalid state.

Common situations: A model is requested for a purpose (e.g. embedding) that its configuration does not allow; matching model type to usage prevents this error.

AI-assisted analysis of infiniflow/ragflow@554fb1133a (2026-08-15). Data as JSON: /api/errors/6bde3e867066116c. Report an issue: GitHub.