highperfocused/danswer
1
0
Fork 0
mirror of https://github.com/danswer-ai/danswer.git synced 2025-08-03 05:34:03 +02:00
Code Issues Packages Projects Releases Wiki Activity

More efficient Vespa indexing (#3552)

Browse Source 
---------

Co-authored-by: Chris Weaver <25087905+Weves@users.noreply.github.com>
This commit is contained in:
pablonyx
2024-12-30 21:51:14 -05:00
committed by GitHub
parent bec0f9fb23
commit 2783216781
13 changed files with 180 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
backend/onyx/seeding/load_docs.py
View File

@@ -86,6 +86,7 @@ def _create_indexable_chunks(
access=default_public_access,
document_sets=set(),
boost=DEFAULT_BOOST,
current_index_time=datetime.datetime.now(datetime.timezone.utc),
)
chunks.append(chunk)
@@ -217,7 +218,7 @@ def seed_initial_documents(
# as we just sent over the Vespa schema and there is a slight delay
index_with_retries = retry_builder(tries=15)(document_index.index)
index_with_retries(chunks=chunks, fresh_index=cohere_enabled)
index_with_retries(chunks=chunks)
# Mock a run for the UI even though it did not actually call out to anything
mock_successful_index_attempt(