Skip to main content

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:
  1. Configure the API key for the agent’s reasoning model.
  2. Configure the Q&A Agent ID (create an agent in the console, then copy its ID) into the TOOL_VESEARCH_ENDPOINT environment variable.
  3. 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

Parameters and result checks

TOOL_VESEARCH_ENDPOINT is an existing agent ID, not an HTTP URL. The call returns a text summary, but failures may also return error text, so a string result alone does not establish success. The request timeout is 30 seconds. CLOUD_PROVIDER=byteplus does not switch this service.
This direct call uses only the Q&A service configuration. An outer reasoning model is additionally required when using the tool through Runner.
Last modified on September 19, 2026