apunkt/PageIndex
1
0
Fork 0
mirror of https://github.com/VectifyAI/PageIndex.git synced 2026-07-03 20:41:02 +02:00
Code Issues Projects Releases Packages Wiki Activity

fix(pifs): clean partial add pageindex cache

Browse source
This commit is contained in:
BukeLy 2026-05-31 21:11:26 +08:00
parent eca5edd8a9
commit 2d55fd2f5a
2 changed files with 44 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
pageindex/filesystem/core.py
View file

@ -1756,11 +1756,12 @@ class PageIndexFileSystem:
records: list[dict[str, Any]],
preexisting_doc_ids: set[str],
) -> None:
doc_ids: list[str] = []
doc_ids = sorted(self._pageindex_cache_doc_ids() - preexisting_doc_ids)
for record in records:
doc_id = str(record.get("pageindex_doc_id") or "").strip()
if doc_id and doc_id not in preexisting_doc_ids:
doc_ids.append(doc_id)
doc_ids = sorted(set(doc_ids))
if not doc_ids:
return
workspace = self.pageindex_client_workspace