mirror of
https://github.com/open-webui/open-webui.git
synced 2026-08-03 06:30:51 -05:00
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.
73 lines
1.9 KiB
Python
73 lines
1.9 KiB
Python
import logging
|
|
from dataclasses import dataclass
|
|
from typing import Optional
|
|
|
|
import requests
|
|
from open_webui.retrieval.web.main import SearchResult
|
|
|
|
log = logging.getLogger(__name__)
|
|
|
|
EXA_API_BASE = 'https://api.exa.ai'
|
|
|
|
|
|
@dataclass
|
|
class ExaResult:
|
|
url: str
|
|
title: str
|
|
text: str
|
|
|
|
|
|
def search_exa(
|
|
api_key: str,
|
|
query: str,
|
|
count: int,
|
|
filter_list: Optional[list[str]] = None,
|
|
) -> list[SearchResult]:
|
|
"""Search using Exa Search API and return the results as a list of SearchResult objects.
|
|
|
|
Args:
|
|
api_key (str): A Exa Search API key
|
|
query (str): The query to search for
|
|
count (int): Number of results to return
|
|
filter_list (Optional[list[str]]): List of domains to filter results by
|
|
"""
|
|
log.info('Searching with Exa for query: %s', query)
|
|
|
|
headers = {'Authorization': f'Bearer {api_key}', 'Content-Type': 'application/json'}
|
|
|
|
payload = {
|
|
'query': query,
|
|
'numResults': count or 5,
|
|
'includeDomains': filter_list,
|
|
'contents': {'text': True, 'highlights': True},
|
|
'type': 'auto', # Use the auto search type (keyword or neural)
|
|
}
|
|
|
|
try:
|
|
response = requests.post(f'{EXA_API_BASE}/search', headers=headers, json=payload)
|
|
response.raise_for_status()
|
|
data = response.json()
|
|
|
|
results = []
|
|
for result in data['results']:
|
|
results.append(
|
|
ExaResult(
|
|
url=result['url'],
|
|
title=result['title'],
|
|
text=result['text'],
|
|
)
|
|
)
|
|
|
|
log.info('Found %s results', len(results))
|
|
return [
|
|
SearchResult(
|
|
link=result.url,
|
|
title=result.title,
|
|
snippet=result.text,
|
|
)
|
|
for result in results
|
|
]
|
|
except Exception as e:
|
|
log.error(f'Error searching Exa: {e}')
|
|
return []
|