Glossary › RAG

Reranking

Second-stage retrieval where a cross-encoder model re-scores retrieved documents for query relevance. More accurate than bi-encoder similarity alone. Adds 50-200ms latency.

Where this is taught

• Advanced Retrieval — Hybrid Search, Reranking, and Parent-Child Chunking — Phase 4: RAG Pipelines in Workflows
• Retrieval, Reranking, and Hybrid Search — Phase 6: RAG Systems & Knowledge Grounding
• Retrieval Tuning on Proprietary Documents — Phase 3: Enterprise RAG Systems
• Dify Knowledge Base Deep Dive — Chunking, Indexing, and Retrieval — Phase 6: Dify & Visual AI App Builders
• Performance Optimization & Scaling — Phase 8: Production Hardening & Operations
• RAG Pipeline End-to-End — Phase 3: Enterprise RAG Systems

More in RAG

Chunking · Semantic Search · Hybrid Search

Learn this by building

DeVenture Academy teaches AI engineering through projects, with hands-on labs you run on your own machine using real tools.

Create a free account — the opening phases of 29 of 35 courses are free, no credit card. Or see Pro pricing.

All courses · Pricing · About · FAQ · Glossary