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.
OpenSearch
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.
Instead of delving into the mathematical definitions of TF-IDF and BM25, we will help you develop an intuitive understanding of these metrics using a series of simple examples.