microsoft/autogen · error · ValueError

Unsupported content type: {mime_type}

Error message

Unsupported content type: {mime_type}

What it means

The teachability text converter handles TEXT, MARKDOWN, JSON (dict), and Image; any other mime_type falls into the terminal else branch and raises with the unsupported value embedded in the message.

Source

Thrown at python/packages/autogen-ext/src/autogen_ext/experimental/task_centric_memory/utils/teachability.py:53

    def _extract_text(self, content_item: str | MemoryContent) -> str:
        """Extract searchable text from content."""
        if isinstance(content_item, str):
            return content_item

        content = content_item.content
        mime_type = content_item.mime_type

        if mime_type in [MemoryMimeType.TEXT, MemoryMimeType.MARKDOWN]:
            return str(content)
        elif mime_type == MemoryMimeType.JSON:
            if isinstance(content, dict):
                # Store original JSON string representation
                return str(content).lower()
            raise ValueError("JSON content must be a dict")
        elif isinstance(content, Image):
            raise ValueError("Image content cannot be converted to text")
        else:
            raise ValueError(f"Unsupported content type: {mime_type}")

    async def update_context(
        self,
        model_context: ChatCompletionContext,
    ) -> UpdateContextResult:
        """
        Extracts any advice from the last user turn to be stored in memory,
        and adds any relevant memories to the model context.
        """
        self._logger.enter_function()

        # Extract text from the user's last message
        messages = await model_context.get_messages()
        if not messages:
            self._logger.leave_function()
            return UpdateContextResult(memories=MemoryQueryResult(results=[]))
        last_message = messages[-1]
        last_user_text = last_message.content if isinstance(last_message.content, str) else str(last_message)

View on GitHub (pinned to 027ecf0a37)

Solutions

1. Check the mime_type printed in the message and convert to TEXT/MARKDOWN before storage.
2. Add a branch for that mime type (if contributing upstream) or bypass teachability for that content type.
3. Gate memory additions: only add contents whose mime_type is in {TEXT, MARKDOWN, JSON-with-dict}.

Example fix

# before
await memory.add(MemoryContent(content=b"...", mime_type=MemoryMimeType.BINARY))
# after
await memory.add(MemoryContent(content="summary of binary blob", mime_type=MemoryMimeType.TEXT))

from autogen_core.memory import MemoryMimeType
SUPPORTED = {MemoryMimeType.TEXT, MemoryMimeType.MARKDOWN, MemoryMimeType.JSON}
assert c.mime_type in SUPPORTED, f"teachability cannot process {c.mime_type}"

def is_supported_teachability_mime(mime_type) -> bool:
    return mime_type in {MemoryMimeType.TEXT, MemoryMimeType.MARKDOWN, MemoryMimeType.JSON}

When it happens

Trigger: Creating MemoryContent with a mime_type outside the supported set (e.g. MemoryMimeType.IMAGE binary, AUDIO, VIDEO, or a custom enum value) and routing it through teachability's update_context/query.

Common situations: New MemoryMimeType enum members added in newer autogen versions not yet handled here; mixing generic memory contents into the teachable memory; custom mime types.

Related errors

• JSON content must be a dict
• Image content cannot be converted to text
• JSON content must be a dict
• Unsupported content type: {mime_type}
• Error: {content.mime_type} is not supported. Only MemoryMime

AI-assisted analysis of microsoft/autogen@027ecf0a37 (2026-08-15). Data as JSON: /api/errors/648958858588a2f6. Report an issue: GitHub.