LAS data lake - AgentKit 文档

Overview

las (from veadk.tools.builtin_tools.las import las) is built on the AI multimodal data lake service LAS, providing creation, preview, query/analysis, editing, and cleaning of multimodal datasets.

Environment & prerequisites

Requirements:

Configure the API key for the agent’s reasoning model.
Create a LAS general dataset in advance and obtain its DatasetId.
Configure the LAS service DatasetId and URL (how to get the URL).

Environment variables (must be set as environment variables):

MODEL_AGENT_API_KEY: API key for the agent’s reasoning model
TOOL_LAS_URL: LAS MCP Server service address
TOOL_LAS_DATASET_ID: dataset ID used by the LAS service

Usage

examples/tools/las/agent.py

import asyncio

from veadk import Agent, Runner
from veadk.memory.short_term_memory import ShortTermMemory
from veadk.tools.builtin_tools.las import las

agent = Agent(
    name="las_agent",
    model_name="doubao-seed-1-8-251228",
    description="Answer using data in LAS.",
    instruction=(
        "You are a poet. First use the las tool to search the ds_public dataset for "
        "relevant content, then write a poem based on the results."
    ),
    tools=[las],
)

runner = Runner(agent=agent, short_term_memory=ShortTermMemory())


async def main():
    response = await runner.run("Write a Chinese-style poem about wood and love")
    print(response)


if __name__ == "__main__":
    asyncio.run(main())

Last modified on September 19, 2026