Better RAG results with Reciprocal Rank Fusion and Hybrid Search
The problem with vector-only searchAt Assembled, our issue resolution engine is designed to assist customer support by suggesting potential answers to support queries. We use Retrieval Augmented Generation (RAG) for much of this pipeline because it's quicker to iterate on than fine-tuning, doesn’t require training on customer data (which many companies prefer), and generally provides high-quality results.However, we encountered a significant challenge with RAG: relying solely on vector search (e...
Read more at assembled.com