# One Assistant Multiple Vector Stores?

**URL:** <https://community.openai.com/t/one-assistant-multiple-vector-stores/831759>\
**Category:** API\
**Tags:** assistants, assistants-api\
**Created:** [June 20, 2024, 7:01pm UTC](https://community.openai.com/t/one-assistant-multiple-vector-stores/831759 "2024-06-20T19:01:34Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![hemnaathR](https://avatars.discourse-cdn.com/v4/letter/h/ba8739/32.png) [@hemnaathR](https://community.openai.com/u/hemnaathR)\
**Post date:** [June 20, 2024, 7:01pm UTC](https://community.openai.com/t/one-assistant-multiple-vector-stores/831759/1 "2024-06-20T19:01:34Z")

</div>

Hello, based on FileSearch [docs] for Assistants([https://platform.openai.com/docs/assistants/tools/file-search/how-it-works](https://platform.openai.com/docs/assistants/tools/file-search/how-it-works)), it mentions that “Today, you can attach at most one vector store to an assistant and at most one vector store to a thread.”

Does that mean there is work going on the enable the Assistant to connect to multiple vector stores in the near future? I noticed that the parameter that takes in the vector store id is also vector\_store\_ids (plural)

---

<div class="post-metadata">

**Author:** ![\_j](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/_j/32/766292_2.png) [@\_j](https://community.openai.com/u/_j)\
**Post date:** [June 20, 2024, 10:23pm UTC](https://community.openai.com/t/one-assistant-multiple-vector-stores/831759/3 "2024-06-20T22:23:37Z")

</div>

What does “today” imply? It might be simply uncertainty. “Today you can attach vector stores (but more will be available in the future) | (but they’ll be discontinued when we write something better) | (but we gave up on the lost investment in assistants)”

There’s actually a third vector store, when you attach files to a message for file\_search.

All the vector stores are simply added to the results that can be returned from a single file search function the AI can call. A file the user uploaded is in the same chunk repository as documents that power the assistant.

My take: Today, you can write something better with chat completions and your own augmented generation and document curation.