mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-05-21 15:36:48 +00:00
Shengyuan Wang
2f3744f807
* refactor: replace sync requests with async httpx in Jina AI client Replace synchronous `requests.post()` with `httpx.AsyncClient` in JinaClient.crawl() and make web_fetch_tool async. This is part of the planned async concurrency optimization for the agent hot path (see docs/TODO.md). * fix: address Copilot review feedback on async Jina client - Short-circuit error strings in web_fetch_tool before passing to ReadabilityExtractor, preventing misleading extraction results - Log missing JINA_API_KEY warning only once per process to reduce noise under concurrent async fetching - Use logger.exception instead of logger.error in crawl exception handler to preserve stack traces for debugging - Add async web_fetch_tool tests and warn-once coverage * fix: mock get_app_config in web_fetch_tool tests for CI The web_fetch_tool tests failed in CI because get_app_config requires a config.yaml file that isn't present in the test environment. Mock the config loader to remove the filesystem dependency. --------- Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
31 lines
1.4 KiB
Python
31 lines
1.4 KiB
Python
from langchain.tools import tool
|
|
|
|
from deerflow.community.jina_ai.jina_client import JinaClient
|
|
from deerflow.config import get_app_config
|
|
from deerflow.utils.readability import ReadabilityExtractor
|
|
|
|
readability_extractor = ReadabilityExtractor()
|
|
|
|
|
|
@tool("web_fetch", parse_docstring=True)
|
|
async def web_fetch_tool(url: str) -> str:
|
|
"""Fetch the contents of a web page at a given URL.
|
|
Only fetch EXACT URLs that have been provided directly by the user or have been returned in results from the web_search and web_fetch tools.
|
|
This tool can NOT access content that requires authentication, such as private Google Docs or pages behind login walls.
|
|
Do NOT add www. to URLs that do NOT have them.
|
|
URLs must include the schema: https://example.com is a valid URL while example.com is an invalid URL.
|
|
|
|
Args:
|
|
url: The URL to fetch the contents of.
|
|
"""
|
|
jina_client = JinaClient()
|
|
timeout = 10
|
|
config = get_app_config().get_tool_config("web_fetch")
|
|
if config is not None and "timeout" in config.model_extra:
|
|
timeout = config.model_extra.get("timeout")
|
|
html_content = await jina_client.crawl(url, return_format="html", timeout=timeout)
|
|
if isinstance(html_content, str) and html_content.startswith("Error:"):
|
|
return html_content
|
|
article = readability_extractor.extract_article(html_content)
|
|
return article.to_markdown()[:4096]
|