mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-09-22 12:36:26 +00:00
b809b7bc7d
* fix(web-fetch): resolve relative URLs in extracted Markdown Pass the request URL through Jina and Browserless extraction and resolve link/image destinations before Readability removes document base tags. Preserve the optional legacy API and fallback text behavior. Fixes #5307 Signed-off-by: tiammomo <26957354+tiammomo@users.noreply.github.com> * fix(web-fetch): address provider and base URL review feedback Signed-off-by: tiammomo <26957354+tiammomo@users.noreply.github.com> * fix(web-fetch): preserve HTML source when resolving destinations Signed-off-by: tiammomo <26957354+tiammomo@users.noreply.github.com> --------- Signed-off-by: tiammomo <26957354+tiammomo@users.noreply.github.com>
69 lines
2.4 KiB
Python
69 lines
2.4 KiB
Python
import asyncio
|
|
|
|
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()
|
|
|
|
|
|
def _coerce_bool(value: object, default: bool) -> bool:
|
|
if isinstance(value, bool):
|
|
return value
|
|
if isinstance(value, str):
|
|
normalized = value.strip().lower()
|
|
if normalized in {"1", "true", "yes", "on"}:
|
|
return True
|
|
if normalized in {"0", "false", "no", "off"}:
|
|
return False
|
|
return default
|
|
|
|
|
|
def _coerce_timeout(value: object, default: int) -> int:
|
|
if isinstance(value, bool):
|
|
return default
|
|
if isinstance(value, int):
|
|
return value
|
|
if isinstance(value, str):
|
|
try:
|
|
return int(value)
|
|
except ValueError:
|
|
return default
|
|
return default
|
|
|
|
|
|
def _coerce_proxy(value: object) -> str | None:
|
|
if not isinstance(value, str):
|
|
return None
|
|
proxy = value.strip()
|
|
return proxy or None
|
|
|
|
|
|
@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
|
|
proxy = None
|
|
trust_env = True
|
|
config = get_app_config().get_tool_config("web_fetch")
|
|
if config is not None:
|
|
timeout = _coerce_timeout(config.model_extra.get("timeout"), timeout)
|
|
proxy = _coerce_proxy(config.model_extra.get("proxy"))
|
|
trust_env = _coerce_bool(config.model_extra.get("trust_env"), trust_env)
|
|
html_content = await jina_client.crawl(url, return_format="html", timeout=timeout, proxy=proxy, trust_env=trust_env)
|
|
if isinstance(html_content, str) and html_content.startswith("Error:"):
|
|
return html_content
|
|
article = await asyncio.to_thread(readability_extractor.extract_article, html_content, url=url)
|
|
return article.to_markdown()[:4096]
|