Get the latest tech news
Vector database company Qdrant wants RAG to be more cost-effective
Qdrant's BM42 is a new search model that extracts data from chunks of a document which it says makes vector search more efficient.
More companies are looking to include retrieval augmented generation (RAG) systems in their technology stack, and new methods to improve it are now coming to light. “When we apply traditional keyword matching algorithms, the most commonly used one is BM25, which assumes documents have enough size to calculate statistics,” Vasnetsov said. It works with a pre-trained language model that can identify relationships between words and include related terms that may not be the same between the search query text and the documents it references.
Or read this on Venture Beat
