I used the assistant api to upload about 1500 documents of type docx,json, and txt containing 29MB and attached the vector store to a new assistant. For some I’m on day 2 of waiting for it to finish indexing. In comparison from what I could tell it took a few hours a few weeks ago for 42mb of about 1700 file vector store.
Are they cheaping out on us? Any plans on expedited indexing in the future? I get that embeddings are expensive, but come on now, 29MB in over 1 day???
Any insights??
The Embeddings API is not expensive?
Store locally in Postgres?
Client requirements are for OpenAI usage. I would love to do this, client might want it in the future. Why offer embedding processing, storage, and retrieval if it takes forever to process. It’s still “Indexing” probably on queue to save OpenAI some money.
I use OpenAI, I just store their embeddings on my infra.
The Assistant API has lots of limitations and is very costly imho.
I’m having a similar problem, but just using the playground (not the API). My vector store is 129 MB and Open AI says it can handle 512 MB. But it spends days and days (tbh weeks) saying it was “indexing”… It’s never completed it. No idea what to do.
it is happening the same to me, some have a solution or fix de problem?
Happening today for me too. Was fine yesterday but even uploading a 2k text file gets hung at indexing - this is via the API and through the Assistants platform.. Spent hours thinking it was my code 
The issues with the vector stores have been reported to staff and this will hopefully be resolved very soon!
Following. Thanks.
I was also failing to process a very small file (120kb)
Same here, uploading the files is no issue, only 200kb and 108kb . however, linking the files to the vector store is not working anymore. vectorstore remains empy. and vectorstore is continuesly indexing.
The same problem. Infinite indexing
I thought it’s only me who’s experiencing such an issue.
Thought it was related to my actions, where I removed files that were included into the vectore store. Not detached but removed without detachment.
wow when trying to escalate to open ai support in regards to the vector stores remaining indexing (for hours now) after creating a new store and 2 new files max 200kb each im still waiting which is hours now.. I tried to contact their support (via chatbot ofcourse) , here the chatbots reply : .. Thank you for explaining the impact—this definitely sounds urgent if your automatic order processing is blocked. Based on your detailed troubleshooting and the critical business impact, I recommend reaching out to a support specialist who can investigate this issue right away. Would you like to connect with a support specialist now to review and resolve your indexing issue as soon as possible? If so, please confirm, and I’ll get this escalated for you.
OpenAI • 3m ago
yes
Escalated to a support specialist; You can expect a response within 2-3 days. Replies will also be sent via email. You can add additional comments to this conversation if needed.
Guess we’re gonna need an other system for mission critical processes.
Same issue waiting for hours
To my OpenAI friends…
You could save all of us – your loyal customers – if you would keep your status page (status.openai.com) up to date with failures like this. Our systems have been trying to upload content since last night with 100% failure rate. At the rate that you are growing, I understand that you will have problems. I’d just appreciate if you would do a better job of communicating about it when you are having these problems.
Hi, apologies for the disruption this has caused. We're looking into this now!
The status page is live! We'll keep it updated as we work towards a solution.
This should be fixed! We'll continue monitoring the fix for any degradations. Thank you all for your patience and understanding while we worked through this.
The problem is back today Help!!
Hi everyone, apologies for the disruption. We're working on this now!