microsoft/autogen · error · ValueError

Unsupported embedding function config type: {type(config)}

Error message

Unsupported embedding function config type: {type(config)}

What it means

_create_embedding_function dispatches on the config type via isinstance checks against the known EmbeddingFunctionConfig subclasses; any config object outside that hierarchy falls through to the final else and raises ValueError naming the actual type.

Source

Thrown at python/packages/autogen-ext/src/autogen_ext/memory/chromadb/_chromadb.py:236

                ) from e

        elif isinstance(config, OpenAIEmbeddingFunctionConfig):
            try:
                return embedding_functions.OpenAIEmbeddingFunction(api_key=config.api_key, model_name=config.model_name)
            except Exception as e:
                raise ImportError(
                    f"Failed to create OpenAI embedding function with model '{config.model_name}'. "
                    f"Ensure openai is installed and API key is valid. Error: {e}"
                ) from e

        elif isinstance(config, CustomEmbeddingFunctionConfig):
            try:
                return config.function(**config.params)
            except Exception as e:
                raise ValueError(f"Failed to create custom embedding function. Error: {e}") from e

        else:
            raise ValueError(f"Unsupported embedding function config type: {type(config)}")

    def _ensure_initialized(self) -> None:
        """Ensure ChromaDB client and collection are initialized."""
        if self._client is None:
            try:
                from chromadb.config import Settings

                settings = Settings(allow_reset=self._config.allow_reset)

                if isinstance(self._config, PersistentChromaDBVectorMemoryConfig):
                    self._client = PersistentClient(
                        path=self._config.persistence_path,
                        settings=settings,
                        tenant=self._config.tenant,
                        database=self._config.database,
                    )
                elif isinstance(self._config, HttpChromaDBVectorMemoryConfig):
                    self._client = HttpClient(

View on GitHub (pinned to 027ecf0a37)

Solutions

1. Use one of the exported config classes: DefaultEmbeddingFunctionConfig, SentenceTransformerEmbeddingFunctionConfig, OpenAIEmbeddingFunctionConfig, or CustomEmbeddingFunctionConfig.
2. Ensure the config classes are imported from the same autogen_ext.memory.chromadb package/version as ChromaDBVectorMemory.
3. Rebuild the component config from its documented schema (e.g. via ComponentBase config loading) instead of ad-hoc objects.

Example fix

# before
config.embedding_function_config = {"type": "default"}
# after
from autogen_ext.memory.chromadb import DefaultEmbeddingFunctionConfig
config.embedding_function_config = DefaultEmbeddingFunctionConfig()

from autogen_ext.memory.chromadb import (
    DefaultEmbeddingFunctionConfig,
    SentenceTransformerEmbeddingFunctionConfig,
    OpenAIEmbeddingFunctionConfig,
    CustomEmbeddingFunctionConfig,
)
ALLOWED = (DefaultEmbeddingFunctionConfig, SentenceTransformerEmbeddingFunctionConfig,
           OpenAIEmbeddingFunctionConfig, CustomEmbeddingFunctionConfig)
assert isinstance(config.embedding_function_config, ALLOWED), "unknown embedding function config"

def is_supported_embedding_config(cfg) -> bool:
    return isinstance(cfg, (
        DefaultEmbeddingFunctionConfig,
        SentenceTransformerEmbeddingFunctionConfig,
        OpenAIEmbeddingFunctionConfig,
        CustomEmbeddingFunctionConfig,
    ))

When it happens

Trigger: Passing a hand-rolled config class (or a plain dict, or a config from a different autogen version) as embedding_function_config in ChromaDBVectorMemoryConfig, then initializing the memory.

Common situations: Copy/pasting a config dataclass from an older/newer autogen-ext version so isinstance checks fail; constructing the config dict manually instead of via the exported config classes; version drift between config classes and the memory implementation.

Related errors

• Unsupported config type: {type(self._config)}
• Failed to create custom embedding function. Error: {e}
• Please set OPENAI_API_KEY environment variable.
• Please set OPENAI_API_KEY environment variable.
• BING_API_KEY environment variable is not set

AI-assisted analysis of microsoft/autogen@027ecf0a37 (2026-08-15). Data as JSON: /api/errors/5e2f8c1d0bfddfe3. Report an issue: GitHub.