highperfocused/danswer
1
0
Fork 0
mirror of https://github.com/danswer-ai/danswer.git synced 2025-06-02 11:09:20 +02:00
Code Issues Packages Projects Releases Wiki Activity

Tracking update (#3605)

Browse Source 
* tracking update

* k
This commit is contained in:
pablonyx 2025-01-06 09:17:00 -08:00 committed by GitHub
parent 6c9c25642d
commit e3b2c9d944
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
backend/onyx/document_index/vespa/index.py
View File

@ -338,7 +338,7 @@ class VespaIndex(DocumentIndex):
# `old_version` documents. # `old_version` documents.
enriched_doc_infos: list[EnrichedDocumentIndexingInfo] = [] enriched_doc_infos: list[EnrichedDocumentIndexingInfo] = []
for document_id, _ in doc_id_to_previous_chunk_cnt.items(): for document_id, doc_count in doc_id_to_previous_chunk_cnt.items():
last_indexed_chunk = doc_id_to_previous_chunk_cnt.get(document_id, None) last_indexed_chunk = doc_id_to_previous_chunk_cnt.get(document_id, None)
# If the document has no `chunk_count` in the database, we know that it # If the document has no `chunk_count` in the database, we know that it
# has the old chunk ID system and we must check for the final chunk index # has the old chunk ID system and we must check for the final chunk index
@ -356,6 +356,10 @@ class VespaIndex(DocumentIndex):
http_client=http_client, http_client=http_client,
) )
# If the document has previously indexed chunks, we know it previously existed
if doc_count or last_indexed_chunk:
existing_docs.add(document_id)
enriched_doc_info = EnrichedDocumentIndexingInfo( enriched_doc_info = EnrichedDocumentIndexingInfo(
doc_id=document_id, doc_id=document_id,
chunk_start_index=doc_id_to_new_chunk_cnt.get(document_id, 0), chunk_start_index=doc_id_to_new_chunk_cnt.get(document_id, 0),