mirror of
https://github.com/danswer-ai/danswer.git
synced 2025-03-26 17:51:54 +01:00
37daf4f3e4
- Removes AI Thoughts by default - only shows when validation fails - Removes punctuation "words" from queries in addition to stopwords (Vespa ignores punctuation anyways) - Fixes Vespa deletion script for larger doc counts
37 lines
1.1 KiB
Python
37 lines
1.1 KiB
Python
# This file is purely for development use, not included in any builds
|
|
import os
|
|
import sys
|
|
|
|
import requests
|
|
|
|
# makes it so `PYTHONPATH=.` is not required when running this script
|
|
parent_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
|
|
sys.path.append(parent_dir)
|
|
|
|
from danswer.configs.app_configs import DOCUMENT_INDEX_NAME # noqa: E402
|
|
from danswer.document_index.vespa.index import DOCUMENT_ID_ENDPOINT # noqa: E402
|
|
from danswer.utils.logger import setup_logger # noqa: E402
|
|
|
|
logger = setup_logger()
|
|
|
|
|
|
def wipe_vespa_index() -> None:
|
|
continuation = None
|
|
should_continue = True
|
|
while should_continue:
|
|
params = {"selection": "true", "cluster": DOCUMENT_INDEX_NAME}
|
|
if continuation:
|
|
params = {**params, "continuation": continuation}
|
|
response = requests.delete(DOCUMENT_ID_ENDPOINT, params=params)
|
|
response.raise_for_status()
|
|
|
|
response_json = response.json()
|
|
print(response_json)
|
|
|
|
continuation = response_json.get("continuation")
|
|
should_continue = bool(continuation)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
wipe_vespa_index()
|