Vamshi Vijay Nakkirtha
Vamshi Vijay Nakkirtha
Hi @Neoanarika ,, It would be nice to have the function to retrieve all the nodes that are part of the existing index. Was just wondering any reason we did...
This issue is to track the feature request for k-NN plugin support for Windows. Please +1 if you are looking for this feature
Provide details of benchmarking environment like - instance type used - number of vectors - dimensions - algo params Provide metrics - Search latencies - Indexing throughput
By default k-NN plugin uses dense vector for Cosine similarity measure. NMS library has support for sparse vector space type. We could enable this support in k-NN plugin.
We have noticed when Elasticsearch upgrades to the latest version of Lucene, to maintain backward compatibility it allows to write using latest codec and allows to read old indices with...
By default k-NN plugin uses dense vector for Euclidean distance similarity measure. NMS library has support for sparse vector space type. We could enable this support in k-NN plugin.
Upgrade to version commons-beanutils:commons-beanutils:1.9.4; org.apache.struts:struts2-core:2.0.5
AD plugin had ability to selectively start/stop nodes for a multi node cluster. This is been removed part of refactor when building ODFE1.6 support. We will have to add this...
OpenSearch supports approximate vector search powered by Lucene engine, nmslib engine, faiss engine and also bruteforce vector search using painless scripting functions. As OpenSearch is popular search engine, it would...
OpenSearch supports [approximate vector search](https://github.com/opensearch-project/k-NN/) powered by Lucene engine, nmslib engine, faiss engine and also bruteforce vector search using painless scripting functions. As OpenSearch is popular search engine, it would...