Volcengine search - AgentKit 文档

Overview

Tool identifier vesearch. vesearch searches via Volcengine’s web-aware Q&A Agent. The tool reads its own credentials from environment variables — you do not pass an api_key on the Agent. Import path: from veadk.tools.builtin_tools.vesearch import vesearch

Environment & prerequisites

Requirements:

Configure the API key for the agent’s reasoning model.
Configure the Q&A Agent ID (create an agent in the console, then copy its ID) into the TOOL_VESEARCH_ENDPOINT environment variable.
Configure the Q&A Agent API key into the TOOL_VESEARCH_API_KEY environment variable.

Environment variables:

MODEL_AGENT_API_KEY: API key for the agent’s reasoning model
TOOL_VESEARCH_ENDPOINT: the Q&A Agent ID (must be set as an environment variable)
TOOL_VESEARCH_API_KEY: the Q&A Agent API key

Usage

examples/tools/vesearch/agent.py

import asyncio

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

agent = Agent(
    name="vesearch_agent",
    model_name="doubao-seed-2-1-pro-260628",
    description="An agent that answers questions with veSearch.",
    instruction="You are a helpful assistant. Use the vesearch tool to look things up online.",
    tools=[vesearch],
)

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


async def main():
    response = await runner.run("What's the weather in Hangzhou today?")
    print(response)


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

Last modified on September 19, 2026