A new approach using Quadratic Unconstrained Binary Optimization (QUBO) for evidence selection in retrieval-augmented generation (RAG) systems achieves competitive exact-match and token-F1 performance…
Researchers fine-tuned LLaMA 3 (8B) as a drop-in reranker for RAG pipelines, achieving gains of 14% in answer relevancy, 16% in context precision, 19% in answer similarity, and 21% in answer correctne…
A new framework called RouteRec, introduced in a preprint on arXiv, evaluates task-aware agent ranking under cost constraints for recommender systems, finding that item-level learned aggregation outpe…
Smolbren, a new CLI tool, turns Markdown vaults into local, queryable knowledge graphs with full-text search, using frontmatter to discover ontology and supporting Cypher queries and BM25 search. Desi…
A developer built Canton Compliance Hub, a free multilingual resource that helps foreign founders navigate Swiss business compliance without hallucinating answers. The system uses hybrid retrieval wit…
A 2026 study from UC San Diego, UC Berkeley, Texas A&M, and UIUC found that context pruning—masking stale observations from an AI agent's history—improves accuracy by up to 11.7 points in some setups …
A developer building Bastra Recall, an MIT-licensed MCP memory server for Claude, discovered that their initial 98.3% benchmark was misleading because it queried each memory with its own trigger phras…
A developer building ContextQuery, a production RAG system on free-tier infrastructure, achieved 100% retrieval precision by implementing hybrid retrieval with Reciprocal Rank Fusion (RRF). The approa…
A developer building a coding agent's memory system chose SQLite's FTS5 full-text search over vector search, arguing that for structured, keyword-dense content like stack traces, logs, and error codes…
Databricks launched Lakebase Search on Neon, a hybrid vector and BM25 full-text retrieval system built as two Postgres extensions optimized for Neon's storage-compute separation architecture, enabling…
A developer outlines a production-ready RAG pipeline that combines dense vector search with BM25 keyword search via Reciprocal Rank Fusion, adds a cross-encoder reranker for accuracy, and emphasizes r…
A developer introduced the Hybrid Retrieval pattern, which combines semantic vector search with keyword-based BM25 search using Reciprocal Rank Fusion (RRF) to improve retrieval precision. The pattern…
Senior AI/ML interviews now focus on real-world production challenges rather than theoretical knowledge, with interviewers asking candidates how they would handle system failures at 2am, latency spike…
Greg Reda prototyped a PDF chatbot from scratch in October 2023, deliberately avoiding frameworks like LangChain to understand pipeline mechanics. The two-phase architecture separates ingestion from i…
A developer built a Hybrid RAG system combining FAISS for dense vector search and BM25 for keyword search, fused via Reciprocal Rank Fusion, orchestrated with LangGraph and Claude Sonnet, and deployed…
A developer identifies the 'index distribution problem' as a fundamental flaw in agent-based search systems, where retrieval indexes encode past relevance judgments rather than semantic truth, causing…
Researchers Bhavik Chandna and Procheta Sen introduced a counterfactual explanation framework for retrieval models that identifies which terms need to be added to a document to improve its ranking, ad…
Steve Harris and the author have built Lume, an open-source Rust hybrid search engine designed for agentic systems, which combines field-aware BM25, dense vectors, and an entity graph to provide audit…
Mariana Souza describes a three-index Elasticsearch architecture for persistent LLM agent memory that achieves 0.89 recall without tenant leaks. The system separates episodic, semantic, and procedural…
Semantic search using vector databases outperforms keyword search for AI agents that need to retrieve information by meaning rather than exact word matches, but keyword search remains faster, cheaper,…