langchain Architecture Docs
Home / Function/ acreate_assistant() — langchain Function Reference

acreate_assistant() — langchain Function Reference

Architecture documentation for the acreate_assistant() function in base.py from the langchain codebase.

Function python AgentOrchestration ClassicChains calls 2

Entity Profile

Dependency Diagram

graph TD
  0f5c9475_3691_d056_8802_a7822050a218["acreate_assistant()"]
  09337f8e_7eda_ea1a_ab7c_b599191c842b["OpenAIAssistantRunnable"]
  0f5c9475_3691_d056_8802_a7822050a218 -->|defined in| 09337f8e_7eda_ea1a_ab7c_b599191c842b
  d6532dd4_8f84_ba8d_106d_016c747876a7["_get_openai_async_client()"]
  0f5c9475_3691_d056_8802_a7822050a218 -->|calls| d6532dd4_8f84_ba8d_106d_016c747876a7
  5f87b6cf_7369_e43d_b38f_8a427415879c["_get_assistants_tool()"]
  0f5c9475_3691_d056_8802_a7822050a218 -->|calls| 5f87b6cf_7369_e43d_b38f_8a427415879c
  style 0f5c9475_3691_d056_8802_a7822050a218 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/agents/openai_assistant/base.py lines 386–418

    async def acreate_assistant(
        cls,
        name: str,
        instructions: str,
        tools: Sequence[BaseTool | dict],
        model: str,
        *,
        async_client: openai.AsyncOpenAI | openai.AsyncAzureOpenAI | None = None,
        **kwargs: Any,
    ) -> OpenAIAssistantRunnable:
        """Async create an AsyncOpenAI Assistant and instantiate the Runnable.

        Args:
            name: Assistant name.
            instructions: Assistant instructions.
            tools: Assistant tools. Can be passed in OpenAI format or as BaseTools.
            model: Assistant model to use.
            async_client: AsyncOpenAI client.
                Will create default async_client if not specified.
            **kwargs: Additional arguments.

        Returns:
            AsyncOpenAIAssistantRunnable configured to run using the created assistant.
        """
        async_client = async_client or _get_openai_async_client()
        openai_tools = [_get_assistants_tool(tool) for tool in tools]
        assistant = await async_client.beta.assistants.create(
            name=name,
            instructions=instructions,
            tools=openai_tools,
            model=model,
        )
        return cls(assistant_id=assistant.id, async_client=async_client, **kwargs)

Domain

Subdomains

Defined In

Calls

Source

Frequently Asked Questions

What does acreate_assistant() do?
acreate_assistant() is a function in the langchain codebase, defined in libs/langchain/langchain_classic/agents/openai_assistant/base.py.
Where is acreate_assistant() defined?
acreate_assistant() is defined in libs/langchain/langchain_classic/agents/openai_assistant/base.py at line 386.
What does acreate_assistant() call?
acreate_assistant() calls 2 function(s): _get_assistants_tool, _get_openai_async_client.

Analyze Your Own Codebase

Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.

Try Supermodel Free