· 3 days ago· Dev.to
Analysis temporarily unavailable. Please try again in a moment.
My RAG pipeline looked fine on paper. Fast retrieval. Decent cosine scores. But when I tested it with real queries, the top results were always a little off. Documents that shared vocabulary with the query kept showing up instead of documents that actually answered it. The model was doing its job. T
#cloud-computing#information-retrieval#natural-language-processing#ai-models