Skip to content
All tags

#reranking

4 posts
ai guide The RAG Techniques Compendium

The Complete Guide to RAG System Patterns: A Ten-Generation Evolution from Naive to Multi-Agent with Practical Navigation

RAG has evolved far beyond simple 'search + generate' into a technology ecosystem spanning ten generations — and since 2025 into an Agentic/Reasoning era. This article is a systematic navigation guide: from Naive RAG to Multi-Agent/LongRAG across ten generations, the post-ten Agentic Era (Search-R1/RL search, MCP, GraphRAG 3.x, vision-native retrieval), retrieval strategies, chunking, embedding, reranking, evaluation frameworks, observability, and cost optimization. Each topic has a dedicated deep-dive article.

#rag#guide#retrieval#embedding#reranking#evaluation#agent
ai guide The RAG Techniques Compendium

ColBERT: The Third Way in Vector Search

Bi-Encoders are too coarse, Cross-Encoders are too slow — ColBERT's Late Interaction finds the sweet spot: token-level comparison between query and document, but with document vectors that can be precomputed.

#rag#colbert#late-interaction#retrieval#reranking#colpali#visual-rag
ai guide The RAG Techniques Compendium

Cross-Encoder Reranking: Surfacing the Most Relevant Documents

Vector search similarity scores don't equal relevance. Cross-Encoders use pairwise comparison to reorder results and push the truly relevant documents to the top.

#rag#reranking#cross-encoder#bge-reranker#retrieval
ai guide The RAG Techniques Compendium

MMR + Popularity Weighting: Recommendations That Are Both Relevant and Diverse

Ranking purely by relevance leaves you with five documents all describing the same route. MMR strikes a balance between relevance and diversity, and layering in popularity weighting makes results even more useful.

#rag#mmr#diversity#reranking#popularity#recommendation