As with any tech decision, the right tool depends on the context. But as LLM development matures, the trend is clear: we’re moving toward simplicity, agility, and tight integration.
AI
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.
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.
New in Solr & Lucene 9 is the ability to do inequality operations to search against payloads on terms. We’ll go through this how new feature works using some different use cases.
KMW Founder, Kevin Watters, gives a talk at the Activate Search & AI conference on using Search as the brain for an open sourced, life-sized, 3D printed, humanoid robot. Of particular interest to the Solr community was the section of this talk highlighting training a Neural Network off of a Solr index in real-time.
Then: Enterprises spend a lot of time to make their content well-curated so that it can be exposed in a search engine.