mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-04-25 11:18:22 +00:00
5350b2fb24
* feat(community): add Exa search as community tool provider Add Exa (exa.ai) as a new community search provider alongside Tavily, Firecrawl, InfoQuest, and Jina AI. Exa is an AI-native search engine with neural, keyword, and auto search types. New files: - community/exa/tools.py: web_search_tool and web_fetch_tool - tests/test_exa_tools.py: 10 unit tests with mocked Exa client Changes: - pyproject.toml: add exa-py dependency - config.example.yaml: add commented-out Exa configuration examples Usage: set `use: deerflow.community.exa.tools:web_search_tool` in config.yaml and provide EXA_API_KEY. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(community): address PR review comments for Exa tools - Make _get_exa_client() accept tool_name param so web_fetch reads its own config - Remove __init__.py to match namespace package pattern of other providers - Add duplicate tool name warning in config.example.yaml - Add regression tests for web_fetch config resolution Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * Update revision in uv.lock to 3 --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
80 lines
2.7 KiB
Python
80 lines
2.7 KiB
Python
import json
|
|
|
|
from exa_py import Exa
|
|
from langchain.tools import tool
|
|
|
|
from deerflow.config import get_app_config
|
|
|
|
|
|
def _get_exa_client(tool_name: str = "web_search") -> Exa:
|
|
config = get_app_config().get_tool_config(tool_name)
|
|
api_key = None
|
|
if config is not None and "api_key" in config.model_extra:
|
|
api_key = config.model_extra.get("api_key")
|
|
return Exa(api_key=api_key)
|
|
|
|
|
|
@tool("web_search", parse_docstring=True)
|
|
def web_search_tool(query: str) -> str:
|
|
"""Search the web.
|
|
|
|
Args:
|
|
query: The query to search for.
|
|
"""
|
|
try:
|
|
config = get_app_config().get_tool_config("web_search")
|
|
max_results = 5
|
|
search_type = "auto"
|
|
contents_max_characters = 1000
|
|
if config is not None:
|
|
max_results = config.model_extra.get("max_results", max_results)
|
|
search_type = config.model_extra.get("search_type", search_type)
|
|
contents_max_characters = config.model_extra.get("contents_max_characters", contents_max_characters)
|
|
|
|
client = _get_exa_client()
|
|
res = client.search(
|
|
query,
|
|
type=search_type,
|
|
num_results=max_results,
|
|
contents={"highlights": {"max_characters": contents_max_characters}},
|
|
)
|
|
|
|
normalized_results = [
|
|
{
|
|
"title": result.title or "",
|
|
"url": result.url or "",
|
|
"snippet": "\n".join(result.highlights) if result.highlights else "",
|
|
}
|
|
for result in res.results
|
|
]
|
|
json_results = json.dumps(normalized_results, indent=2, ensure_ascii=False)
|
|
return json_results
|
|
except Exception as e:
|
|
return f"Error: {str(e)}"
|
|
|
|
|
|
@tool("web_fetch", parse_docstring=True)
|
|
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.
|
|
"""
|
|
try:
|
|
client = _get_exa_client("web_fetch")
|
|
res = client.get_contents([url], text={"max_characters": 4096})
|
|
|
|
if res.results:
|
|
result = res.results[0]
|
|
title = result.title or "Untitled"
|
|
text = result.text or ""
|
|
return f"# {title}\n\n{text[:4096]}"
|
|
else:
|
|
return "Error: No results found"
|
|
except Exception as e:
|
|
return f"Error: {str(e)}"
|