mirror of
https://github.com/open-webui/open-webui.git
synced 2026-08-14 09:42:27 -06:00
Classic298
2d18727ab8
Raising GLOBAL_LOG_LEVEL to WARNING buys quieter output but not less work: 241 INFO call sites interpolate their payload into an f-string before the logging call gets to drop it. The heaviest is get_doc, which logs every chunk id and metadata dict in a collection, so on the full-context retrieval path that is the entire knowledge base, once per chat request.
That one line at WARNING, CPython 3.12:
| knowledge base | payload | before | after |
| -------------- | ------- | -------- | ------- |
| top-k of 3 | 1.2 kB | 3.8 us | 0.07 us |
| 500 chunks | 201 kB | 583.6 us | 0.08 us |
| 5000 chunks | 2.0 MB | 5.8 ms | 0.15 us |
The lazy form log.info('query_doc:result %s %s', result.ids, result.metadatas) hands the payload to record.getMessage(), which the InterceptHandler only reaches once a record has passed the level check. Output at INFO is byte-identical. Two sites that already built their message eagerly, one str concat and one % operator, move to the same lazy form.
47 lines
1.3 KiB
Python
47 lines
1.3 KiB
Python
import logging
|
|
from typing import Optional
|
|
from urllib.parse import urlencode
|
|
|
|
import requests
|
|
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
|
|
|
|
log = logging.getLogger(__name__)
|
|
|
|
|
|
def search_searchapi(
|
|
api_key: str,
|
|
engine: str,
|
|
query: str,
|
|
count: int,
|
|
filter_list: Optional[list[str]] = None,
|
|
) -> list[SearchResult]:
|
|
"""Search using searchapi.io's API and return the results as a list of SearchResult objects.
|
|
|
|
Args:
|
|
api_key (str): A searchapi.io API key
|
|
query (str): The query to search for
|
|
"""
|
|
url = 'https://www.searchapi.io/api/v1/search'
|
|
|
|
engine = engine or 'google'
|
|
|
|
payload = {'engine': engine, 'q': query, 'api_key': api_key}
|
|
|
|
url = f'{url}?{urlencode(payload)}'
|
|
response = requests.request('GET', url)
|
|
|
|
json_response = response.json()
|
|
log.info('results from searchapi search: %s', json_response)
|
|
|
|
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['link'],
|
|
title=result.get('title'),
|
|
snippet=result.get('snippet'),
|
|
)
|
|
for result in results[:count]
|
|
]
|