Reranking in RAG - "the second step to pick the most relevant results."
° Retrieve top K docs
° Re‑rank with a cross‑encoder or LLM scoring
° Pick top 3–5
° Generate response
Re-ranking allows pulling more vectors, not just nearest neighbors like basic RAG.
10
0 comments
Tanmay Kapurkar
5
Reranking in RAG - "the second step to pick the most relevant results."
AI Automation Society
skool.com/ai-automation-society
A community built to master no-code AI automations. Join to learn, discuss, and build the systems that will shape the future of work.
Leaderboard (30-day)
Powered by