# KNN \_score not lining up with similarity filter

**URL:** https://discuss.elastic.co/t/knn-score-not-lining-up-with-similarity-filter/376088
**Category:** Elasticsearch
**Tags:** vector-search
**Created:** [March 18, 2025, 6:35pm UTC](https://discuss.elastic.co/t/knn-score-not-lining-up-with-similarity-filter/376088 "2025-03-18T18:35:21Z")
**Posts on this page:** 1
**Showing post:** 4

<div class="post-metadata">

### Author: ![Yakob](https://avatars.discourse-cdn.com/v4/letter/y/f04885/32.png) [@Yakob](https://discuss.elastic.co/u/Yakob)
#### Post date: [March 24, 2025, 3:20pm UTC](https://discuss.elastic.co/t/knn-score-not-lining-up-with-similarity-filter/376088/4 "2025-03-24T15:20:20Z")

</div>

Thank you so much for your replies Alex and John! I apologize for my delayed response; I was out of town for a few days last week. To answer your questions:

> First, I was wondering why you are using k=10000 and num\_candidates=10000. Could you clarify?

The index I am working with has 1,500,000 documents and the product desire is to grab as many sufficiently relevant documents as possible. From spot checking, I have found that a similarity of 0.8 seems to be the sweet spot where returned documents are still relevant enough for my app's purpose. Most search vectors will not hit a full 10k results, but it does happen sometimes where 10k relevant results are expected and correct. The app I'm working on runs this KNN query to build a pool of possible final documents, which is then further refined later in the app (I can't use a filtered KNN search because of the issues outlined in my other post here: [Efficient Subquery Combinations](https://discuss.elastic.co/t/efficient-subquery-combinations/374234)). As an aside, my team is considering increasing `index.max_result_window` to 20k as the 10k limit will occasionally keep us from grabbing a few desired documents.

Reading through the docs, use of `max_size` `k` and `num_candidates` does seem to be an anti-pattern. I haven't done a lot of vector math up to this point, so I will research the HNSW algorithm so I can better understand those minutiae.

> So it should follow this formula: (2 \* \_score) - 1  
> Or in your case: (2 \* 0.95) -1 = 0.8500066  
> Which I think makes sense based on what you described: that what you are seeing the document show up when you have `0.85` similarity as your threshold. I would expect anything above that and it will not return including `0.90`.

Yes, you are correct! I had already read the KNN document you linked, but I missed that formula. I ran a few more test queries and all of the responses follow the expected values when using the formula:

```auto
_score = (similarity + 1) / 2

```

Thanks for clearing this up for me! This answers my original question, but I'm happy to learn more about KNN or answer any other questions you two have.

---

_[View the full topic](https://discuss.elastic.co/t/knn-score-not-lining-up-with-similarity-filter/376088)._