{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreia6i5sdlnhtksz4coaszvujzx7jz6t3ldxu2ftwbefltfxrlzskaq",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mmvsscbaj2n2"
},
"path": "/t/vector-store-api-calls-returning-504s-503s-and-generally-being-slow/1381938#post_4",
"publishedAt": "2026-05-28T10:23:19.000Z",
"site": "https://community.openai.com",
"textContent": "Yeah, well ~300 resources really shouldn’t be enough by itself to trigger systemic pagination failures.\n\nThe `failed: 4` correlation is much more interesting though. If the consistently failing vector store is also the only one containing failed entries, I wonder if the list/pagination path is hitting some bad state or retry edge case while resolving failed file metadata internally\n\nHmm.. Especially since:\n\n * the successful store has zero failed files\n\n * the failing store consistently has non-zero failed entries\n\n * and the failures occur during listing rather than upload.\n\n\n\n\nSo it might be worth testing by manually removing/recreating only the failed entries (or recreating the store cleanly) to see whether the pagination instability disappears",
"title": "Vector Store API calls returning 504s, 503s, and generally being slow"
}