2024-06-22 14:36:15 +00:00
|
|
|
import logging
|
|
|
|
|
2024-08-27 22:10:27 +00:00
|
|
|
import requests
|
2024-09-28 00:23:09 +00:00
|
|
|
from open_webui.apps.retrieval.web.main import SearchResult
|
2024-09-04 14:54:48 +00:00
|
|
|
from open_webui.env import SRC_LOG_LEVELS
|
2024-08-27 22:10:27 +00:00
|
|
|
from yarl import URL
|
2024-06-22 14:36:15 +00:00
|
|
|
|
|
|
|
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]:
|
2024-06-22 14:36:15 +00:00
|
|
|
"""
|
|
|
|
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
|
2024-06-22 14:36:15 +00:00
|
|
|
"""
|
|
|
|
jina_search_endpoint = "https://s.jina.ai/"
|
2024-11-04 01:07:24 +00:00
|
|
|
headers = {"Accept": "application/json", "Authorization": f"Bearer {api_key}"}
|
2024-06-22 14:36:15 +00:00
|
|
|
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
|