{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreid6tpoi6gn2q3fpus5sh5tma22cmagphbecg4lvlo52zcnntojvmi",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mmvssk45kac2"
  },
  "path": "/t/vector-store-api-calls-returning-504s-503s-and-generally-being-slow/1381938#post_3",
  "publishedAt": "2026-05-28T10:18:11.000Z",
  "site": "https://community.openai.com",
  "textContent": "Hi S_z,\n\nThank you for such a quick response. I’ll try reducing the page limit and add some back off. Persistence could be an option, but requires significantly more engineering effort and the vector stores are not large. They have, at most, 300 resources.\n\nThe idea that listing 300 resources in a vector store is simply too much for the system to handle is laughable. It would be a massive disappointment if this is enough to cause a trillion dollar company’s API to fail.\n\nTo clarify, nothing is happening in parallel, I am synchronously running three vector store setups. One of them is empty because it relies on full script completion. For the other two, I have used this code:\n\n\n    const vectorStore = await openai.vectorStores.retrieve(vectorStoreId);\n    console.dir(vectorStore.file_counts, { depth: null });\n\n\nTo get this output for one that regularly succeeds:\n\n\n    { in_progress: 0, completed: 172, failed: 0, cancelled: 0, total: 172 }\n\n\nAnd this for the other that regularly fails:\n\n\n    { in_progress: 0, completed: 268, failed: 4, cancelled: 0, total: 272 }\n\n\nThe only obvious difference is the `failed` count being none zero. Could this be causing the issue?",
  "title": "Vector Store API calls returning 504s, 503s, and generally being slow"
}