open-webui/backend/open_webui/retrieval/web/jina_search.py

40 lines
1.1 KiB
Python
Raw Permalink Normal View History

import logging
2024-08-27 22:10:27 +00:00
import requests
2024-12-12 02:05:42 +00:00
from open_webui.retrieval.web.main import SearchResult
from open_webui.env import SRC_LOG_LEVELS
2024-08-27 22:10:27 +00:00
from yarl import URL
log = logging.getLogger(__name__)
log.setLevel(SRC_LOG_LEVELS["RAG"])
2024-11-04 01:07:24 +00:00
def search_jina(api_key: str, query: str, count: int) -> list[SearchResult]:
"""
Search using Jina's Search API and return the results as a list of SearchResult objects.
Args:
query (str): The query to search for
count (int): The number of results to return
Returns:
2024-08-14 12:46:31 +00:00
list[SearchResult]: A list of search results
"""
jina_search_endpoint = "https://s.jina.ai/"
2024-11-04 01:07:24 +00:00
headers = {"Accept": "application/json", "Authorization": f"Bearer {api_key}"}
url = str(URL(jina_search_endpoint + query))
response = requests.get(url, headers=headers)
response.raise_for_status()
data = response.json()
results = []
for result in data["data"][:count]:
results.append(
SearchResult(
link=result["url"],
title=result.get("title"),
snippet=result.get("content"),
)
)
2024-06-22 23:15:19 +00:00
return results