Semantic Cache 및 BM25 압축을 통한 API 비용 50% 절감
How I Cut My Anthropic API Bill by 50% With a Local Python Tool
How I Cut My Anthropic API Bill by 50% With a Local Python Tool
Why hybrid search is the boring default we keep recommending
BM25+Bigram 기반 RAG 최적화로 응답 속도 4.4s 달성 및 배포 단순화
Kreuzberg & SurrealDB: from unstructured documents to hybrid retrieval
Moving Beyond Simple Vector Search: Why Hybrid Search is Essential for RAG
RAG Series (10): Hybrid Search — Retrieving More, Missing Less
로컬 SQLite 기반 컨텍스트 주입으로 Claude Code 회상 정확도 88% 달성
CTX: I gave Claude Code a memory that actually works
데이터 샌드박스 격리와 BM25 검색을 통한 컨텍스트 윈도우 98% 절감
New SurrealDB docs search using hybrid search and HNSW/BM25 reranking
Beyond Keyword Search: How Synthadoc v0.2.0 Combines BM25 and Vector Search to Build a Smarter Domain Wiki
The AI-Native Database Nobody Told You About: 5 Hidden Uses of Infinity in 2026
Why I used a 50-year-old algorithm instead of embeddings to cut Claude API token costs
FLAMEHAVEN FileSearch: Why This RAG Engine Feels Different from the Usual Stack
BM25-벡터 하이브리드 검색 기반 AI 에이전트 로그 지식 베이스 구축
BM25와 LLM을 결합한 비정형 데이터 정규화 및 가성비 랭킹 시스템 구축
Hybrid search in Manticore Search
I built a context engine that saves Claude Code 73% of its tokens on large codebases