# Discrepancy in embeddings precision

**URL:** <https://community.openai.com/t/discrepancy-in-embeddings-precision/78666>\
**Category:** API\
**Created:** [February 28, 2023, 5:15pm UTC](https://community.openai.com/t/discrepancy-in-embeddings-precision/78666 "2023-02-28T17:15:56Z")\
**Posts on this page:** 1\
**Showing post:** 8

<div class="post-metadata">

**Author:** ![curt.kennedy](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/curt.kennedy/32/709249_2.png) [@curt.kennedy](https://community.openai.com/u/curt.kennedy)\
**Post date:** [February 28, 2023, 6:55pm UTC](https://community.openai.com/t/discrepancy-in-embeddings-precision/78666/8 "2023-02-28T18:55:36Z")

</div>

Using the API method I am getting, on average, 9 decimal places. This is more than sufficient to use since all the vectors are scaled to unit length from the embedding engine. In your ada-002 example, it has 1536 dimensions, so if you imagine a unit vector in this space with equal values, you get a vector of 1/sqrt(1536), which is 0.0255…, so 2 decimal places. Using higher dimension models like the old davinci embedding, this could get worse, but only by a factor of 10, so you are still good.

So, like stated earlier, for this model dimension, anything more than 6-7 decimal places isn’t carrying much information and it can actually be bad if you store your intermediate embeddings as strings in a database (so it cuts the DB size in half for the lower precision, which is better too).

---

_[View the full topic](https://community.openai.com/t/discrepancy-in-embeddings-precision/78666)._