highperfocused/danswer
1
0
Fork 0
mirror of https://github.com/danswer-ai/danswer.git synced 2025-09-23 12:31:30 +02:00
Code Issues Packages Projects Releases Wiki Activity

Add config to skip zendesk article labels

Browse Source
This commit is contained in:
Kevin Shi
2024-07-18 11:45:03 -06:00
committed by Chris Weaver
parent 2dc7e64dd7
commit 6b561b8ca9
2 changed files with 14 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
backend/danswer/configs/app_configs.py
View File

@@ -223,6 +223,11 @@ MAX_PRUNING_DOCUMENT_RETRIEVAL_PER_MINUTE = int(
os.environ.get("MAX_PRUNING_DOCUMENT_RETRIEVAL_PER_MINUTE", 0) os.environ.get("MAX_PRUNING_DOCUMENT_RETRIEVAL_PER_MINUTE", 0)
) )
# comma delimited list of zendesk article labels to skip indexing for
ZENDESK_CONNECTOR_SKIP_ARTICLE_LABELS = os.environ.get(
"ZENDESK_CONNECTOR_SKIP_ARTICLE_LABELS", ""
).split(",")
##### #####
# Indexing Configs # Indexing Configs

10
backend/danswer/connectors/zendesk/connector.py
View File

@@ -4,6 +4,7 @@ from zenpy import Zenpy # type: ignore
from zenpy.lib.api_objects.help_centre_objects import Article # type: ignore from zenpy.lib.api_objects.help_centre_objects import Article # type: ignore
from danswer.configs.app_configs import INDEX_BATCH_SIZE from danswer.configs.app_configs import INDEX_BATCH_SIZE
from danswer.configs.app_configs import ZENDESK_CONNECTOR_SKIP_ARTICLE_LABELS
from danswer.configs.constants import DocumentSource from danswer.configs.constants import DocumentSource
from danswer.connectors.cross_connector_utils.miscellaneous_utils import ( from danswer.connectors.cross_connector_utils.miscellaneous_utils import (
time_str_to_utc, time_str_to_utc,
@@ -81,7 +82,14 @@ class ZendeskConnector(LoadConnector, PollConnector):
) )
doc_batch = [] doc_batch = []
for article in articles: for article in articles:
if article.body is None or article.draft: if (
article.body is None
or article.draft
or any(
label in ZENDESK_CONNECTOR_SKIP_ARTICLE_LABELS
for label in article.label_names
)
):
continue continue
doc_batch.append(_article_to_document(article)) doc_batch.append(_article_to_document(article))