mirror of
https://github.com/open-webui/open-webui
synced 2024-11-27 06:20:01 +00:00
49 lines
1.4 KiB
Python
49 lines
1.4 KiB
Python
import logging
|
|
from typing import Optional
|
|
|
|
import requests
|
|
from open_webui.apps.retrieval.web.main import SearchResult, get_filtered_results
|
|
from open_webui.env import SRC_LOG_LEVELS
|
|
|
|
log = logging.getLogger(__name__)
|
|
log.setLevel(SRC_LOG_LEVELS["RAG"])
|
|
|
|
|
|
def search_serpstack(
|
|
api_key: str,
|
|
query: str,
|
|
count: int,
|
|
filter_list: Optional[list[str]] = None,
|
|
https_enabled: bool = True,
|
|
) -> list[SearchResult]:
|
|
"""Search using serpstack.com's and return the results as a list of SearchResult objects.
|
|
|
|
Args:
|
|
api_key (str): A serpstack.com API key
|
|
query (str): The query to search for
|
|
https_enabled (bool): Whether to use HTTPS or HTTP for the API request
|
|
"""
|
|
url = f"{'https' if https_enabled else 'http'}://api.serpstack.com/search"
|
|
|
|
headers = {"Content-Type": "application/json"}
|
|
params = {
|
|
"access_key": api_key,
|
|
"query": query,
|
|
}
|
|
|
|
response = requests.request("POST", url, headers=headers, params=params)
|
|
response.raise_for_status()
|
|
|
|
json_response = response.json()
|
|
results = sorted(
|
|
json_response.get("organic_results", []), key=lambda x: x.get("position", 0)
|
|
)
|
|
if filter_list:
|
|
results = get_filtered_results(results, filter_list)
|
|
return [
|
|
SearchResult(
|
|
link=result["url"], title=result.get("title"), snippet=result.get("snippet")
|
|
)
|
|
for result in results[:count]
|
|
]
|