autogen_ext.agents.openai#

class OpenAIAgent(name: str, description: str, client: AsyncOpenAI | AsyncAzureOpenAI, model: str, instructions: str, tools: List[Tool] | None = None, temperature: float | None = 1, max_output_tokens: int | None = None, json_mode: bool = False, store: bool = True, truncation: str = 'disabled')[source]#

Bases: BaseChatAgent, Component[OpenAIAgentConfig]

An agent implementation that uses the OpenAI Responses API to generate responses.

Installation:

pip install "autogen-ext[openai]"
# pip install "autogen-ext[openai,azure]"  # For Azure OpenAI Assistant

This agent leverages the Responses API to generate responses with capabilities like:

  • Custom function calling

  • Multi-turn conversations

Example

from openai import AsyncOpenAI
from autogen_core import CancellationToken
from autogen_ext.agents.openai import OpenAIAgent
from autogen_agentchat.messages import TextMessage


async def example():
    cancellation_token = CancellationToken()
    client = AsyncOpenAI()
    agent = OpenAIAgent(
        name="Simple Agent",
        description="A simple OpenAI agent using the Responses API",
        client=client,
        model="gpt-4.1",
        instructions="You are a helpful assistant.",
    )
    response = await agent.on_messages([TextMessage(source="user", content="Hello!")], cancellation_token)
    print(response)

asyncio.run(example())

TODO: Add support for advanced features (vector store, multimodal, etc.) in future PRs.

component_config_schema#

alias of OpenAIAgentConfig

component_provider_override: ClassVar[str | None] = 'autogen_ext.agents.openai.OpenAIAgent'#

Override the provider string for the component. This should be used to prevent internal module names being a part of the module name.

async delete_assistant(assistant_id: str) → Dict[str, Any][source]#

Delete an assistant by its ID using the OpenAI API.

Parameters:

assistant_id (str) – The ID of the assistant to delete.

Returns:

Dict[str, Any] – The deletion status object (e.g., {“id”: …, “object”: “assistant.deleted”, “deleted”: true}).

Example

import asyncio
from typing import Dict, Any
from autogen_ext.agents.openai import OpenAIAgent
from openai import AsyncOpenAI


async def example() -> None:
    client = AsyncOpenAI()
    agent = OpenAIAgent(
        name="test_agent",
        description="Test agent",
        client=client,
        model="gpt-4",
        instructions="You are a helpful assistant.",
    )
    result: Dict[str, Any] = await agent.delete_assistant("asst_abc123")
    print(result)


asyncio.run(example())
async list_assistants(after: str | None = None, before: str | None = None, limit: int | None = 20, order: str | None = 'desc') → Dict[str, Any][source]#

List all assistants using the OpenAI API.

Parameters:

  • after (Optional[str]) – Cursor for pagination (fetch after this assistant ID).

  • before (Optional[str]) – Cursor for pagination (fetch before this assistant ID).

  • limit (Optional[int]) – Number of assistants to return (1-100, default 20).

  • order (Optional[str]) – ‘asc’ or ‘desc’ by created_at (default ‘desc’).

Returns:

Dict[str, Any] – The OpenAI API response containing: - object: ‘list’ - data: List of assistant objects - first_id: str - last_id: str - has_more: bool

Example

import asyncio
from typing import Dict, Any
from autogen_ext.agents.openai import OpenAIAgent
from openai import AsyncOpenAI


async def example() -> None:
    client = AsyncOpenAI()
    agent = OpenAIAgent(
        name="test_agent",
        description="Test agent",
        client=client,
        model="gpt-4",
        instructions="You are a helpful assistant.",
    )
    assistants: Dict[str, Any] = await agent.list_assistants(limit=5)
    print(assistants)


asyncio.run(example())
async load_state(state: Mapping[str, Any]) → None[source]#

Restore agent from saved state. Default implementation for stateless agents.

async modify_assistant(assistant_id: str, name: str | None = None, description: str | None = None, instructions: str | None = None, metadata: Dict[str, Any] | None = None, model: str | None = None, reasoning_effort: str | None = None, response_format: str | None = None, temperature: float | None = None, tool_resources: Dict[str, Any] | None = None, tools: List[Any] | None = None, top_p: float | None = None, **kwargs: Any) → Dict[str, Any][source]#

Modify (update) an assistant by its ID using the OpenAI API.

Parameters:

  • assistant_id (str) – The ID of the assistant to update.

  • name (Optional[str]) – New name for the assistant.

  • description (Optional[str]) – New description.

  • instructions (Optional[str]) – New instructions.

  • metadata (Optional[dict]) – New metadata.

  • model (Optional[str]) – New model.

  • reasoning_effort (Optional[str]) – New reasoning effort.

  • response_format (Optional[str]) – New response format.

  • temperature (Optional[float]) – New temperature.

  • tool_resources (Optional[dict]) – New tool resources.

  • tools (Optional[list]) – New tools.

  • top_p (Optional[float]) – New top_p value.

  • **kwargs – Additional keyword arguments.

Returns:

Dict[str, Any] – The updated assistant object.

Example

import asyncio
from typing import Dict, Any
from autogen_ext.agents.openai import OpenAIAgent
from openai import AsyncOpenAI


async def example() -> None:
    client = AsyncOpenAI()
    agent = OpenAIAgent(
        name="test_agent",
        description="Test agent",
        client=client,
        model="gpt-4",
        instructions="You are a helpful assistant.",
    )
    updated: Dict[str, Any] = await agent.modify_assistant(
        assistant_id="asst_123",
        instructions="You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.",
        tools=[{"type": "file_search"}],
        tool_resources={"file_search": {"vector_store_ids": []}},
    )
    print(updated)


asyncio.run(example())
async on_messages(messages: Sequence[BaseChatMessage], cancellation_token: CancellationToken) → Response[source]#

Handles incoming messages and returns a response.

Note

Agents are stateful and the messages passed to this method should be the new messages since the last call to this method. The agent should maintain its state between calls to this method. For example, if the agent needs to remember the previous messages to respond to the current message, it should store the previous messages in the agent state.

async on_messages_stream(messages: Sequence[BaseChatMessage], cancellation_token: CancellationToken) → AsyncGenerator[Annotated[ToolCallRequestEvent | ToolCallExecutionEvent | MemoryQueryEvent | UserInputRequestedEvent | ModelClientStreamingChunkEvent | ThoughtEvent | SelectSpeakerEvent | CodeGenerationEvent | CodeExecutionEvent, FieldInfo(annotation=NoneType, required=True, discriminator='type')] | TextMessage | MultiModalMessage | StopMessage | ToolCallSummaryMessage | HandoffMessage | Response, None][source]#

Handles incoming messages and returns a stream of messages and and the final item is the response. The base implementation in BaseChatAgent simply calls on_messages() and yields the messages in the response.

Note

Agents are stateful and the messages passed to this method should be the new messages since the last call to this method. The agent should maintain its state between calls to this method. For example, if the agent needs to remember the previous messages to respond to the current message, it should store the previous messages in the agent state.

async on_reset(cancellation_token: CancellationToken) → None[source]#

Resets the agent to its initialization state.

property produced_message_types: Sequence[Type[TextMessage] | Type[MultiModalMessage] | Type[StopMessage] | Type[ToolCallSummaryMessage] | Type[HandoffMessage]]#

Return the types of messages that this agent can produce.

async retrieve_assistant(assistant_id: str) → Dict[str, Any][source]#

Retrieve a single assistant by its ID using the OpenAI API.

Parameters:

assistant_id (str) – The ID of the assistant to retrieve.

Returns:

Dict[str, Any] – The assistant object.

Example

import asyncio
from typing import Dict, Any
from autogen_ext.agents.openai import OpenAIAgent
from openai import AsyncOpenAI


async def example() -> None:
    client = AsyncOpenAI()
    agent = OpenAIAgent(
        name="test_agent",
        description="Test agent",
        client=client,
        model="gpt-4",
        instructions="You are a helpful assistant.",
    )
    assistant: Dict[str, Any] = await agent.retrieve_assistant("asst_abc123")
    print(assistant)


asyncio.run(example())
async save_state() → Mapping[str, Any][source]#

Export state. Default implementation for stateless agents.

class OpenAIAssistantAgent(name: str, description: str, client: AsyncOpenAI | AsyncAzureOpenAI, model: str, instructions: str, tools: Iterable[Literal['code_interpreter', 'file_search'] | Tool | Callable[[...], Any] | Callable[[...], Awaitable[Any]]] | None = None, assistant_id: str | None = None, thread_id: str | None = None, metadata: Dict[str, str] | None = None, response_format: Literal['auto'] | ResponseFormatText | ResponseFormatJSONObject | ResponseFormatJSONSchema | None = None, temperature: float | None = None, tool_resources: ToolResources | None = None, top_p: float | None = None)[source]#

Bases: BaseChatAgent

An agent implementation that uses the Assistant API to generate responses.

Installation:

pip install "autogen-ext[openai]"
# pip install "autogen-ext[openai,azure]"  # For Azure OpenAI Assistant

This agent leverages the Assistant API to create AI assistants with capabilities like:

  • Code interpretation and execution

  • File handling and search

  • Custom function calling

  • Multi-turn conversations

The agent maintains a thread of conversation and can use various tools including

  • Code interpreter: For executing code and working with files

  • File search: For searching through uploaded documents

  • Custom functions: For extending capabilities with user-defined tools

Key Features:

  • Supports multiple file formats including code, documents, images

  • Can handle up to 128 tools per assistant

  • Maintains conversation context in threads

  • Supports file uploads for code interpreter and search

  • Vector store integration for efficient file search

  • Automatic file parsing and embedding

You can use an existing thread or assistant by providing the thread_id or assistant_id parameters.

Examples

Use the assistant to analyze data in a CSV file:

from openai import AsyncOpenAI
from autogen_core import CancellationToken
import asyncio
from autogen_ext.agents.openai import OpenAIAssistantAgent
from autogen_agentchat.messages import TextMessage


async def example():
    cancellation_token = CancellationToken()

    # Create an OpenAI client
    client = AsyncOpenAI(api_key="your-api-key", base_url="your-base-url")

    # Create an assistant with code interpreter
    assistant = OpenAIAssistantAgent(
        name="Python Helper",
        description="Helps with Python programming",
        client=client,
        model="gpt-4",
        instructions="You are a helpful Python programming assistant.",
        tools=["code_interpreter"],
    )

    # Upload files for the assistant to use
    await assistant.on_upload_for_code_interpreter("data.csv", cancellation_token)

    # Get response from the assistant
    response = await assistant.on_messages(
        [TextMessage(source="user", content="Analyze the data in data.csv")], cancellation_token
    )

    print(response)

    # Clean up resources
    await assistant.delete_uploaded_files(cancellation_token)
    await assistant.delete_assistant(cancellation_token)


asyncio.run(example())

Use Azure OpenAI Assistant with AAD authentication:

from openai import AsyncAzureOpenAI
import asyncio
from azure.identity import DefaultAzureCredential, get_bearer_token_provider
from autogen_core import CancellationToken
from autogen_ext.agents.openai import OpenAIAssistantAgent
from autogen_agentchat.messages import TextMessage


async def example():
    cancellation_token = CancellationToken()

    # Create an Azure OpenAI client
    token_provider = get_bearer_token_provider(DefaultAzureCredential())
    client = AsyncAzureOpenAI(
        azure_deployment="YOUR_AZURE_DEPLOYMENT",
        api_version="YOUR_API_VERSION",
        azure_endpoint="YOUR_AZURE_ENDPOINT",
        azure_ad_token_provider=token_provider,
    )

    # Create an assistant with code interpreter
    assistant = OpenAIAssistantAgent(
        name="Python Helper",
        description="Helps with Python programming",
        client=client,
        model="gpt-4o",
        instructions="You are a helpful Python programming assistant.",
        tools=["code_interpreter"],
    )

    # Get response from the assistant
    response = await assistant.on_messages([TextMessage(source="user", content="Hello.")], cancellation_token)

    print(response)

    # Clean up resources
    await assistant.delete_assistant(cancellation_token)


asyncio.run(example())
Parameters:

  • name (str) – Name of the assistant

  • description (str) – Description of the assistant’s purpose

  • client (AsyncOpenAI | AsyncAzureOpenAI) – OpenAI client or Azure OpenAI client instance

  • model (str) – Model to use (e.g. “gpt-4”)

  • instructions (str) – System instructions for the assistant

  • tools (Optional[Iterable[Union[Literal["code_interpreter", "file_search"], Tool | Callable[..., Any] | Callable[..., Awaitable[Any]]]]]) – Tools the assistant can use

  • assistant_id (Optional[str]) – ID of existing assistant to use

  • thread_id (Optional[str]) – ID of existing thread to use

  • metadata (Optional[Dict[str, str]]) – Additional metadata for the assistant.

  • response_format (Optional[AssistantResponseFormatOptionParam]) – Response format settings

  • temperature (Optional[float]) – Temperature for response generation

  • tool_resources (Optional[ToolResources]) – Additional tool configuration

  • top_p (Optional[float]) – Top p sampling parameter

async delete_assistant(cancellation_token: CancellationToken) → None[source]#

Delete the assistant if it was created by this instance.

async delete_uploaded_files(cancellation_token: CancellationToken) → None[source]#

Delete all files that were uploaded by this agent instance.

async delete_vector_store(cancellation_token: CancellationToken) → None[source]#

Delete the vector store if it was created by this instance.

async handle_incoming_message(message: BaseChatMessage, cancellation_token: CancellationToken) → None[source]#

Handle regular text messages by adding them to the thread.

async load_state(state: Mapping[str, Any]) → None[source]#

Restore agent from saved state. Default implementation for stateless agents.

property messages: AsyncMessages#
async on_messages(messages: Sequence[BaseChatMessage], cancellation_token: CancellationToken) → Response[source]#

Handle incoming messages and return a response.

async on_messages_stream(messages: Sequence[BaseChatMessage], cancellation_token: CancellationToken) → AsyncGenerator[BaseAgentEvent | BaseChatMessage | Response, None][source]#

Handle incoming messages and return a response.

async on_reset(cancellation_token: CancellationToken) → None[source]#

Handle reset command by deleting new messages and runs since initialization.

async on_upload_for_code_interpreter(file_paths: str | Iterable[str], cancellation_token: CancellationToken) → None[source]#

Handle file uploads for the code interpreter.

Handle file uploads for file search.

property produced_message_types: Sequence[type[BaseChatMessage]]#

The types of messages that the assistant agent produces.

property runs: AsyncRuns#
async save_state() → Mapping[str, Any][source]#

Export state. Default implementation for stateless agents.

property threads: AsyncThreads#