KMW Technology is a professional services firm that creates cutting edge applications powered by open source Search and AI technologies with a focus on Solr, OpenSearch and Elasticsearch.
KMW’s offerings include: consulting, design, implementation, training and support.
Not only does KMW possess deep expertise in search and machine learning, they also have a full team that delivers complete, working solutions. And they’re easy and fun to work with. I cannot recommend them highly enough.
Keeeb
KMW is the third Solr consultancy HTS engaged to resolve our Solr query and operational issues. The first two consultancies didn’t make the progress that we had hoped, while KMW exceeded our expectations. The difference with KMW is their detailed level of knowledge of Solr, the immediately actionable recommendations and the ongoing support through implementation. We’ve seen as much as 40x improvements to query latency on the same hardware based on their recommendations, we highly recommend KMW.
Hightech-Solutions (HTS)
KMW brings a unique blend of expertise – the functional expertise around search technology and the ability to fit into our company’s operational cadence. KMW has literally become an extension of our team.
Kibo Commerce
KMW Technology










We describe the process of using retrieval-augmented generation (RAG) to create a question-answering system about Solr and OpenSearch using an assortment of LLMs from HuggingFace and OpenAI.
In Lucene-based search engines like OpenSearch and Solr, keyword aggregations ignore duplicate values that occur within a multi-valued field. We built an OpenSearch plugin to overcome this limitation.
We created a POC vector search application using OpenSearch. In this post, we discuss what we did to get it working as well as investigate how popular search features like sorting, aggregating and filtering can be utilized in vector search.