Retrieval, vector databases, GraphRAG, chunking, and knowledge-graph practice.
9 articles
Systematic comparison of Microsoft GraphRAG (community detection + global summarization) and HKUDS LightRAG (dual-layer graph + incremental update) across index construction, retrieval paradigm, cost structure, query quality, and use cases. Includes a decision tree by data scale, query type, and ops budget.
RAG upstream caps downstream performance. A systematic comparison of four chunking strategies -- fixed-size, recursive, semantic, and agentic -- with quantitative selection guidance, Chonkie / LlamaIndex / LangChain tooling comparison, and offline evaluation methods.
A production-engineering deep dive into RAG two-stage retrieval: Reranker model selection, Hybrid Search fusion strategies, Qdrant sparse+dense implementation, and offline evaluation set design -- taking production RAG recall from 60% to 90%.
Traditional vector RAG only finds "similar chunks." GraphRAG extracts entities and relationships into a knowledge graph, letting agents understand "who, where, when, and how things connect." Compare Microsoft GraphRAG vs LightRAG approaches.
Most RAG pipelines fail at retrieval, not generation. This article covers five chunking strategies, hybrid search, reranking pipelines, and a production-ready decision framework.
Production-focused best practices for index design, filtering, reranking, and evaluation when building RAG retrieval layers with Qdrant.
A comprehensive comparison of popular open-source vector databases Milvus, Chroma, and Weaviate, helping you choose the best vector database for RAG applications.
Learn how to evaluate RAG systems using Ragas and DeepEval, including measuring key metrics like faithfulness, answer relevance, and context precision.
An in-depth explanation of Retrieval-Augmented Generation and how to build private knowledge bases for AI agents to improve accuracy and reliability.