microsoft/autogen · error · ValueError

File search is not enabled for this assistant. Add a file_se

Error message

File search is not enabled for this assistant. Add a file_search tool when creating the assistant.

What it means

on_upload_for_file_search uploads files into an OpenAI vector store and attaches it to the assistant. It requires that a file_search tool be part of the assistant's tool configuration (checked against self._api_tools); without file_search enabled the upload has nothing to attach to, so it refuses with this ValueError.

Source

Thrown at python/packages/autogen-ext/src/autogen_ext/agents/openai/_openai_assistant_agent.py:633

        await cancellation_token.link_future(
            asyncio.ensure_future(
                self._client.beta.threads.update(  # type: ignore[reportDeprecated]
                    thread_id=self._thread_id,
                    tool_resources=cast(thread_update_params.ToolResources, tool_resources.model_dump()),
                )
            )
        )

    async def on_upload_for_file_search(
        self, file_paths: str | Iterable[str], cancellation_token: CancellationToken
    ) -> None:
        """Handle file uploads for file search."""
        await self._ensure_initialized()

        # Check if file_search is enabled in tools
        if not any(tool.get("type") == "file_search" for tool in self._api_tools):
            raise ValueError(
                "File search is not enabled for this assistant. Add a file_search tool when creating the assistant."
            )

        # Create vector store if not already created
        if self._vector_store_id is None:
            vector_store: VectorStore = await cancellation_token.link_future(
                asyncio.ensure_future(self._client.vector_stores.create())
            )
            self._vector_store_id = vector_store.id

            # Update assistant with vector store ID
            await cancellation_token.link_future(
                asyncio.ensure_future(
                    self._client.beta.assistants.update(
                        assistant_id=self._get_assistant_id,
                        tool_resources={"file_search": {"vector_store_ids": [self._vector_store_id]}},
                    )
                )

View on GitHub (pinned to 027ecf0a37)

Solutions

1. Include file_search when creating the agent: tools=["file_search", ...] (string form works for the assistant agent).
2. If using tool_resources/file search resources, ensure the file_search tool itself is registered too.
3. Recreate the assistant with the updated tool set rather than uploading to a non-file-search assistant.

Example fix

# before
agent = OpenAIAssistantAgent(
    name="docs", instructions="...", model="gpt-4o", client=cl, tools=[]
)
await agent.on_upload_for_file_search("report.pdf", ct)  # raises

# after
agent = OpenAIAssistantAgent(
    name="docs", instructions="...", model="gpt-4o", client=cl,
    tools=["file_search"],
)
await agent.on_upload_for_file_search("report.pdf", ct)

file_search_enabled = any(
    (t.get("type") if isinstance(t, dict) else t) == "file_search" for t in tools
)
if not file_search_enabled:
    raise ConfigError("add 'file_search' to tools before uploading files")

When it happens

Trigger: Creating OpenAIAssistantAgent(..., tools=[...]) without a file_search tool entry (or without tool_resources containing file_search), then calling await agent.on_upload_for_file_search(paths, ct).

Common situations: Adding file upload to an existing agent that was configured for function tools only; forgetting that file_search must be declared at assistant creation, not at upload time.

Related errors

• No tools are available.
• Please set OPENAI_API_KEY environment variable.
• Please set OPENAI_API_KEY environment variable.
• Please set OPENAI_API_KEY environment variable.
• Please set OPENAI_API_KEY environment variable.

AI-assisted analysis of microsoft/autogen@027ecf0a37 (2026-08-15). Data as JSON: /api/errors/e2c09f1c59a8e84d. Report an issue: GitHub.