LangChain

LangChain adapter for Flyte.

Bring your own LangChain agent and run it durably on Flyte. The adapter provides:

• flyteplugins.agents.langchain.tool — turn a Flyte @env.task into a LangChain StructuredTool (a BaseTool) that executes as a durable child action (own container/GPU, retries, caching).
• flyteplugins.agents.langchain.run_agent — run the LangChain agent (a compiled create_agent graph) inside your task and return the final answer. Either pass a pre-built agent or let it build one from tools + model + instructions.

Each tool call runs as a durable Flyte child action, and the run timeline is rendered into the Flyte task report.

Directory

Methods

Methods

run_agent()

def run_agent(
    input: str,
    tools: typing.Sequence[typing.Any] = (),
    model: typing.Any = None,
    instructions: str | None = None,
    agent: typing.Any = None,
    name: str = 'langchain-agent',
    durable: bool = True,
    observability: bool = True,
    memory_key: str | None = None,
    config: dict[str, typing.Any] | None = None,
    **agent_kwargs: typing.Any,
) -> str

Run a LangChain agent with the given tools and prompt; return the final text.

Await this from an async task as await run_agent(...); from a sync task use flyteplugins.agents.langchain.run_agent_sync instead.

Call this from inside an @env.task — that task is the durable parent. Within it, each tool call runs as a durable Flyte child action. Give the enclosing task retries=... for self-healing and report=True to see the agent timeline.

Provide either a pre-built agent (a compiled graph from create_agent) or tools + model to have one built for you.

Returns: The agent’s final output as a string.

run_agent_sync()

def run_agent_sync(
    input: str,
    tools: typing.Sequence[typing.Any] = (),
    model: typing.Any = None,
    instructions: str | None = None,
    agent: typing.Any = None,
    name: str = 'langchain-agent',
    durable: bool = True,
    observability: bool = True,
    memory_key: str | None = None,
    config: dict[str, typing.Any] | None = None,
    **agent_kwargs: typing.Any,
) -> str

Synchronous variant of run_agent for use in sync tasks; runs the async implementation on a dedicated event loop.

Run a LangChain agent with the given tools and prompt; return the final text.

Await this from an async task as await run_agent(...); from a sync task use flyteplugins.agents.langchain.run_agent_sync instead.

Call this from inside an @env.task — that task is the durable parent. Within it, each tool call runs as a durable Flyte child action. Give the enclosing task retries=... for self-healing and report=True to see the agent timeline.

Provide either a pre-built agent (a compiled graph from create_agent) or tools + model to have one built for you.

Returns

The agent’s final output as a string.

tool()

def tool(
    func: AsyncFunctionTaskTemplate | typing.Callable | None = None,
    name: str | None = None,
    description: str | None = None,
) -> typing.Any

Convert a Flyte task (or plain callable) into a LangChain StructuredTool.

• For an @env.task: returns a StructuredTool whose async coroutine runs the task as a durable Flyte child action when the agent invokes it. The input schema is derived from the task’s typed signature. The backing task is wired to flyteplugins.agents.core.ToolTaskResolver and exposed via __wrapped_task__ so it resolves to itself on the worker (no recursion).
• For a plain (async) callable: returns a StructuredTool that runs it inline.

Usable bare, parametrized, or as a direct call:

@tool
@env.task
async def get_weather(city: str) -> str: ...