新增用户意图确认功能

This commit is contained in:
likun committed 2026-05-13 14:36:44 +08:00
1 parent cf2e4bdd9c
commit b8926f00d7
574 files changed
+97664 -97208

No files matched your search

@@ -1,32 +1,32 @@
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()
@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 = await asyncio.to_thread(readability_extractor.extract_article, html_content)
return article.to_markdown()[:4096]
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()
@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 = await asyncio.to_thread(readability_extractor.extract_article, html_content)
return article.to_markdown()[:4096]