整合
CrewAI
給 CrewAI agent 一個用 Thunderbit 跑網頁研究的 tool
CrewAI agent 需要新鮮、乾淨的網頁內容當輸入。把 /distill 包成一個 CrewAI tool，crew 裡任何 agent 都能隨時讀 URL。
安裝
pip install crewai httpx自訂 tool
from crewai.tools import BaseTool
import httpx
API = "https://openapi.thunderbit.com/openapi/v1"
H = {"Authorization": "Bearer YOUR_API_KEY"}
class ReadUrlTool(BaseTool):
name: str = "read_url"
description: str = (
"Fetch a URL and return clean Markdown. Use for any web research task: "
"docs, articles, product pages, search results."
)
def _run(self, url: str) -> str:
resp = httpx.post(f"{API}/distill",
headers=H,
json={"url": url, "renderMode": "basic"},
timeout=60.0)
resp.raise_for_status()
return resp.json()["data"]["markdown"]接進 Crew
from crewai import Agent, Task, Crew
researcher = Agent(
role="Web Researcher",
goal="Gather authoritative information from public web pages",
backstory="Skilled at distilling long pages into key facts.",
tools=[ReadUrlTool()],
)
task = Task(
description="Research how vector databases compare in 2026.",
expected_output="A concise comparison table.",
agent=researcher,
)
Crew(agents=[researcher], tasks=[task]).kickoff()小技巧
- 多來源研究時，再開一個
/batch/distill包出來的 tool（叫read_urls），讓 agent 平行去抓 - 把回傳的 Markdown 截到約 8k token 再丟給 agent —— 避免吃爆 context
相關文件
這份整合會擴出多 agent crew 模板 —— 敬請期待。