highperfocused/danswer
1
0
Fork 0
mirror of https://github.com/danswer-ai/danswer.git synced 2025-09-20 04:37:09 +02:00
Code Issues Packages Projects Releases Wiki Activity

Seeding count issue (#4009)

Browse Source 
* k

* k

* quick nit

* nit
This commit is contained in:
pablonyx
2025-02-16 12:49:25 -08:00
committed by GitHub
parent e441c899af
commit ec0e55fd39
2 changed files with 7 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
backend/onyx/background/celery/tasks/shared/tasks.py
View File

@@ -105,6 +105,7 @@ def document_by_cc_pair_cleanup_task(
tenant_id=tenant_id, tenant_id=tenant_id,
chunk_count=chunk_count, chunk_count=chunk_count,
) )
delete_documents_complete__no_commit( delete_documents_complete__no_commit(
db_session=db_session, db_session=db_session,
document_ids=[document_id], document_ids=[document_id],

9
backend/onyx/seeding/load_docs.py
View File

@@ -61,10 +61,10 @@ def _create_indexable_chunks(
doc_updated_at=None, doc_updated_at=None,
primary_owners=[], primary_owners=[],
secondary_owners=[], secondary_owners=[],
chunk_count=1, chunk_count=preprocessed_doc["chunk_ind"] + 1,
) )
if preprocessed_doc["chunk_ind"] == 0:
ids_to_documents[document.id] = document ids_to_documents[document.id] = document
chunk = DocMetadataAwareIndexChunk( chunk = DocMetadataAwareIndexChunk(
chunk_id=preprocessed_doc["chunk_ind"], chunk_id=preprocessed_doc["chunk_ind"],
@@ -92,6 +92,7 @@ def _create_indexable_chunks(
boost=DEFAULT_BOOST, boost=DEFAULT_BOOST,
large_chunk_id=None, large_chunk_id=None,
) )
chunks.append(chunk) chunks.append(chunk)
return list(ids_to_documents.values()), chunks return list(ids_to_documents.values()), chunks
@@ -192,6 +193,7 @@ def seed_initial_documents(
last_successful_index_time=last_index_time, last_successful_index_time=last_index_time,
seeding_flow=True, seeding_flow=True,
) )
cc_pair_id = cast(int, result.data) cc_pair_id = cast(int, result.data)
processed_docs = fetch_versioned_implementation( processed_docs = fetch_versioned_implementation(
"onyx.seeding.load_docs", "onyx.seeding.load_docs",
@@ -249,4 +251,5 @@ def seed_initial_documents(
.values(chunk_count=doc.chunk_count) .values(chunk_count=doc.chunk_count)
) )
db_session.commit()
kv_store.store(KV_DOCUMENTS_SEEDED_KEY, True) kv_store.store(KV_DOCUMENTS_SEEDED_KEY, True)