feat(capabilities): add env-keyed searxng/linkup/baidu discover providers

This commit is contained in:
CREDO23 2026-07-01 17:08:58 +02:00
parent adc39d1062
commit 329bc63b6c
6 changed files with 345 additions and 0 deletions

View file

@ -0,0 +1,53 @@
"""Baidu AI Search discover provider (env-keyed via ``BAIDU_API_KEY``)."""
from __future__ import annotations
import httpx
from app.capabilities.web.discover.schemas import DiscoverHit
from app.config import config
_ENDPOINT = "https://qianfan.baidubce.com/v2/ai_search/chat/completions"
_SNIPPET_MAX = 300
class BaiduProvider:
name = "baidu"
def is_available(self) -> bool:
return bool(config.BAIDU_API_KEY)
async def search(self, query: str, top_k: int) -> list[DiscoverHit]:
max_per_type = min(top_k, 20)
payload = {
"messages": [{"role": "user", "content": query}],
"model": config.BAIDU_MODEL,
"search_source": config.BAIDU_SEARCH_SOURCE,
"resource_type_filter": [{"type": "web", "top_k": max_per_type}],
"stream": False,
}
headers = {
"X-Appbuilder-Authorization": f"Bearer {config.BAIDU_API_KEY}",
"Content-Type": "application/json",
}
async with httpx.AsyncClient(timeout=90.0) as client:
response = await client.post(_ENDPOINT, headers=headers, json=payload)
response.raise_for_status()
hits: list[DiscoverHit] = []
for reference in response.json().get("references", []):
url = reference.get("url", "")
if not url:
continue
content = reference.get("content", "") or ""
hits.append(
DiscoverHit(
url=url,
title=reference.get("title") or url,
snippet=content[:_SNIPPET_MAX] or None,
provider=self.name,
)
)
if len(hits) >= top_k:
break
return hits

View file

@ -0,0 +1,40 @@
"""Linkup discover provider (env-keyed via ``LINKUP_API_KEY``)."""
from __future__ import annotations
import asyncio
from linkup import LinkupClient
from app.capabilities.web.discover.schemas import DiscoverHit
from app.config import config
class LinkupProvider:
name = "linkup"
def is_available(self) -> bool:
return bool(config.LINKUP_API_KEY)
async def search(self, query: str, top_k: int) -> list[DiscoverHit]:
client = LinkupClient(api_key=config.LINKUP_API_KEY)
response = await asyncio.to_thread(
client.search, query=query, depth="standard", output_type="searchResults"
)
hits: list[DiscoverHit] = []
for result in getattr(response, "results", None) or []:
url = getattr(result, "url", "") or ""
if not url:
continue
content = getattr(result, "content", "") or ""
hits.append(
DiscoverHit(
url=url,
title=getattr(result, "name", "") or url,
snippet=content or None,
provider=self.name,
)
)
if len(hits) >= top_k:
break
return hits

View file

@ -0,0 +1,28 @@
"""SearXNG discover provider, wrapping the platform-env SearXNG search service."""
from __future__ import annotations
from app.capabilities.web.discover.schemas import DiscoverHit
from app.services import web_search_service
class SearxngProvider:
"""Env-keyed via ``SEARXNG_DEFAULT_HOST`` (the platform SearXNG instance)."""
name = "searxng"
def is_available(self) -> bool:
return web_search_service.is_available()
async def search(self, query: str, top_k: int) -> list[DiscoverHit]:
result_object, _documents = await web_search_service.search(query, top_k)
return [
DiscoverHit(
url=source["url"],
title=source.get("title") or source["url"],
snippet=source.get("description") or None,
provider=self.name,
)
for source in result_object.get("sources", [])
if source.get("url")
]