1780 related articles

A systematic guide to standardized datasets for RAG retrieval experiments, covering BEIR, MS MARCO, Natural Questions, and TREC benchmarks for dense, sparse, and hybrid retrieval evaluation.

A deep dive into two frontier dense retrieval works: Hobbit uses gradient analysis to automatically construct hard batches; Disco replaces single-document competition with submodular collaborative coverage, reshaping Top-K retrieval.

RAG (Retrieval-Augmented Generation) is a key technology for solving LLM hallucinations. This guide breaks down how RAG works, its advantages, and real-world use cases — no math required.

Poor RAG retrieval? The root cause often lies in the Embedding model. This article explores why fine-tuning embedding models is necessary, the limits of general Embeddings, and where Embedding fine-tuning fits in RAG optimization.

GBrain's 12-step deep retrieval pipeline and knowledge graph construction outperforms traditional RAG by 31% — with full local offline deployment for data security and lower API costs.

A complete guide to building RAG systems: covering data preprocessing, vector databases, embedding models, hybrid search, re-ranking, and advanced topics like Graph RAG and multimodal RAG.

A complete guide to RAG evolution from Naive RAG through Advanced, Agentic, Graph, and Multimodal RAG — covering core techniques, pain points solved, and real-world use cases.

A deep dive into full-pipeline optimization for enterprise RAG systems, covering multi-turn query rewriting, retrieval tuning, and quality evaluation to take RAG from demo to production.
TutorialsRAG (Retrieval-Augmented Generation) is the core solution for LLM hallucination. Learn RAG concepts, how it works, three causes of hallucination, and the complete learning path from basics to Knowledge Graph RAG.
Deep DivesA deep dive into RAG (Retrieval-Augmented Generation) technology, covering LLM hallucinations, data staleness, and limited expertise, plus RAG workflows, core components, and LangChain learning paths.
Deep DivesDeep dive into RAG retrieval: how Top-K rough recall filters candidates, Rerank precision sorting improves relevance, and compression optimizes context for LLM generation.
Product ReviewsLightningRAG is an open-source full-stack RAG framework built with Vue and Gin, supporting knowledge base management, vector search, and multi-model integration. A deep dive into its architecture and comparison with LangChain and Dify.
TutorialsLearn how to build a Coze knowledge base with RAG retrieval and workflow configuration. Covers document chunking strategies, agent setup, and enterprise Q&A.

Yoggi is a safe AI chat assistant for children ages 3-15, offering age-adaptive answers, real-time voice chat, image generation, strict content filtering, and parental controls.

Aymo AI integrates 45+ major AI models like GPT, Claude, and Gemini into one secure workspace with side-by-side comparison, file chat, web search, and team collaboration to reduce multi-platform costs.

Google Gemini exhibits identity confusion, claiming to be other AI models. Deep dive into why LLMs get their identity wrong, how training data contamination causes AI hallucinations, and what this means for AI product trustworthiness.

Is a linguistics-to-computational-linguistics master's worth it? This article analyzes career paths in computational linguistics in the AI era, the competitive advantages of a hybrid background, and practical advice for transitioning from humanities to NLP.

Second Brain desktop brings unified persistent memory across AI tools for Mac and Windows, featuring intelligent recall, auto-built knowledge graphs, and self-hosted data via Cloudflare.

Firecrawl releases new /search API using a dedicated model to extract precise excerpts, achieving 10x token efficiency and 94.7% SimpleQA accuracy for AI agents.

Fluree AI replaces traditional RAG by querying structured data directly, giving AI agents cited, verifiable, and permission-controlled enterprise context via MCP protocol.