lior-k

Hi, sorry for the late response. and thanks! same as issue #25 - your indexed vector dimension (` data = np.random.rand(10, 8, 8).tolist()`) is 8, while you are using a...

Hi Zakkery. Thanks for the PR. I'll add my comments in-line But 1 in general - several files instead of 1 helps me keep the clutter of Plugin boiler plate...

Hi Zakkery. note that master was changed to use float vectors instead of doubles. please review your changes against master. thanks

What is the ES version you guys use?

It shouldn't matter that the plugin is compiled with 1.8 I guess the error has a different cause

I understand that this is the error that is returned in the HTTP response. + Please specify the full error in the ES log, including stack trace. + please share...

The plug-in uses pure cosine-similarity or dot-product to compare vectors. So the K nearest neighbors it returns are the exact K, not any assessment like LSH and others On Wed,...

Yes, it uses brute force to calculate cosine-similarity. Meaning O(n) It is not faster than hnswlib or fasis etc... It is faster then other ES plugins that did the same...

BTW, we use k-means with this plug-in inorder to traverse only the input vector nearest clusters instead of the entire corpus. On Fri, Oct 30, 2020, 2:21 AM Seung wrote:...

Never tested. This plugin existes way before the official support. If you do test the performance differences please let us all know 🙏 On Thu, Jan 14, 2021, 5:20 PM...