agentscope-ai/agentscope · error · TypeError

f"AgentScopeEmbedding `model` must be an EmbeddingModelBase,

Error message

f"AgentScopeEmbedding `model` must be an EmbeddingModelBase, got {type(self.config.model).__name__}."

What it means

The embedding adapter type-checks config.model; anything that is not an AgentScope EmbeddingModelBase (string model name, raw OpenAI client, sentence-transformers model) raises this TypeError with the actual type name.

Source

Thrown at src/agentscope/middleware/_longterm_memory/_mem0/_agentscope_adapter.py:251

    ``EmbeddingModelBase``."""

    def __init__(
        self,
        config: BaseEmbedderConfig | dict | None = None,
    ) -> None:
        # mem0's EmbeddingBase (unlike LLMBase) does NOT auto-convert
        # dict configs — it stores whatever is passed. Normalize here
        # so callers can use the same dict-config style as the LLM.
        if isinstance(config, dict):
            config = BaseEmbedderConfig(**config)
        super().__init__(config)
        if self.config.model is None:
            raise ValueError(
                "AgentScopeEmbedding requires `model` in the config "
                "to be an AgentScope EmbeddingModelBase instance.",
            )
        if not isinstance(self.config.model, EmbeddingModelBase):
            raise TypeError(
                f"AgentScopeEmbedding `model` must be an "
                f"EmbeddingModelBase, got "
                f"{type(self.config.model).__name__}.",
            )
        self._agentscope_model: EmbeddingModelBase = self.config.model
        self._bridge = _AsyncBridge()

    # ----- EmbeddingBase interface -----
    # pylint: disable=unused-argument
    def embed(
        self,
        text: str | list[str],
        memory_action: str | None = None,  # mem0 contract — unused
    ) -> list[float]:
        """mem0 ``EmbeddingBase`` entry — runs the AgentScope embedding
        model synchronously and returns the first vector."""
        text_list = [text] if isinstance(text, str) else list(text)
        response = self._bridge.run(self._agentscope_model(text_list))

View on GitHub (pinned to e90f1c7592)

Solutions

1. Wrap the provider with an AgentScope embedding class and pass the instance
2. Verify the import came from agentscope.model, not the provider SDK
3. Delegate construction to build_mem0_config(embedding_model=...)

Example fix

// before
AgentScopeEmbedding({'model': 'text-embedding-3-small'})
// after
from agentscope.model import OpenAIEmbedding
AgentScopeEmbedding({'model': OpenAIEmbedding(model='text-embedding-3-small')})

from agentscope.model import EmbeddingModelBase
if not isinstance(config.get('model'), EmbeddingModelBase):
    raise TypeError('model must be an EmbeddingModelBase instance')

from agentscope.model import EmbeddingModelBase
def is_embedding_model_base(m) -> bool:
    return isinstance(m, EmbeddingModelBase)

try:
    emb = AgentScopeEmbedding(cfg)
except TypeError as e:
    raise SystemExit(f'Bad embedder config: {e}') from e

When it happens

Trigger: AgentScopeEmbedding({'model': 'text-embedding-3-small'}) or passing a SentenceTransformer/HuggingFace object as model.

Common situations: Assuming mem0's string-based embedder config style carries over; mixing HuggingFace locals with the AgentScope adapter.

Related errors

• f"AgentScopeLLM `model` must be a ChatModelBase, got {type(s
• "AgentScopeEmbedding requires `model` in the config to be an
• "AgentScope embedding model returned no embeddings."
• Path {path_file} exists but is not a file.
• "AgentScopeLLM requires `model` in the config to be an Agent

AI-assisted analysis of agentscope-ai/agentscope@e90f1c7592 (2026-08-28). Data as JSON: /api/errors/aaaf4fe9e4ab0053. Report an issue: GitHub.