Vector Stores Documentation Batching Not Explicit Enough


I think including a few things in the Vector Stores documentation would be helpful.

  1. Limits - Provide an explicit mention that uploading files to the vector store counts towards the batch TPD limit (of the embedding model?).
  2. Embedding model—I assume that the vector store uses text-embedding-3-large, as mentioned in the file_search How It Works section. However, this information seems more for inference/retrieval than for storing the vectors themselves.

I think being a bit more explicit with these would help.