RAG / 检索增强

🐋 Полный гайд на русском: как установить и запустить DeepSeek локально (V4, R1) на ПК, Mac и сервере — Ollama, llama.cpp, LM Studio, vLLM, Open WebUI, API, RAG…

GitHub

Enterprise RAG unlocks insights from knowledge sources like SharePoint, Google Drive, and Confluence, but those sources carry complex permissions. Learn how Amazon Quick and Amazon…

AI 点评 · 企业RAG最大隐患是越权检索敏感文档，亚马逊这套方案直击权限治理痛点，值得关注。

AWS ML

Long-context inference and Retrieval-Augmented Generation (RAG) handle evidence selection at vastly different scales, from a single long prompt to an entire corpus. We ask whether a single model-inter…

HuggingFace Papers

Build a Retrieval Augmented Generation (RAG) application on Amazon Bedrock Managed Knowledge Base with LangChain, and see how agentic retrieval handles the multi-part questions tha…

AWS ML

Interactive desktop app with 51 labs covering ML fundamentals, transformers, RAG, agents, fine-tuning and quantization and more.

GitHub

Reasoning traces improve large language models (LLMs), but current models are trained to reason mostly in English. It has been shown that forcing a model to reason in another language degrades accurac…

HuggingFace Papers

Enterprises adopting retrieval-augmented generation (RAG) face a recurring operational decision: promote, revise, or block a system version. The evidence is incomplete and the metrics come from fallib…

HuggingFace Papers

Long-document search with Jev and PageIndex

GitHub

Self-hosted AI platform on Kubernetes (k3s) for AI agents, RAG and MLOps: MCP tool servers, LangGraph, LiteLLM model routing with an evaluation gate, MLflow, Da…

GitHub

Manually extracting data from hundreds of vendor contracts doesn't scale, and RAG chat tools fall short on portfolio-wide questions. This post shares a contract intelligence platfo…

AI 点评 · 合同智能平台展示多智能体协作落地路径，企业级AI从单点问答走向组合分析值得关注。

AWS ML

Document rerankers determine what evidence reaches the downstream model in RAG and deep research, yet mainstream rerankers select by relevance matching, and individually relevant documents rarely cons…

HuggingFace Papers

Dense retrieval powers retrieval-augmented generation, semantic search, and question answering, yet the theoretical basis for choosing between shared and dual query-document projections remains unclea…

HuggingFace Papers

Online misinformation increasingly appears in spoken formats such as news clips, podcasts, interviews, political speeches, and social media videos, creating a need for fact-checking systems that can v…

arXiv

Hi HN, I built ai·rete·rag because I kept seeing teams put an LLM in charge of decisions that need to be auditable (lending, fraud, clinical triage), then bolt on "guardrails" afte…

Hacker News

Hi HN, I built ai·rete·rag because I kept seeing teams put an LLM in charge of decisions that need to be auditable (lending, fraud, clinical triage), then bolt on "guardrails" afte…

Hacker News

Retrieval-Augmented Generation (RAG) systems over enterprise knowledge bases must ingest heterogeneous document formats -- PDFs, Word documents, presentations, and scans -- whose content is locked ins…

HuggingFace Papers

Agent/RAG/AI应用：Agent零基础入门学习笔记➕编程平台

GitHub

Choosing the right vector store for your Amazon Bedrock Knowledge Bases RAG application affects performance and cost. This post compares Amazon OpenSearch Service, Amazon Aurora Po…

AWS ML

Local-first voice memory assistant — capture speech, transcribe live, and ask a private RAG chatbot grounded in what you've actually said. No cloud required.

GitHub

Pick the right generative AI customization approach on AWS with an 8-step decision framework, from prompt engineering and RAG to fine-tuning, continued pre-training, and Amazon Nov…

AWS ML

TitanRAG - An open-source RAG infrastructure for building scalable, multi-tenant and multimodal AI applications.

GitHub

Open-source Agentic AI Academy for engineering trustworthy AI agents from learning to production: agents, RAG, MCP, evaluation, security, observability, governa…

GitHub

Open-source Agentic AI Academy for engineering trustworthy AI agents from learning to production: agents, RAG, MCP, evaluation, security, observability, governa…

GitHub

大模型（LLM）全栈学习路线与中文教程🔥：覆盖 Prompt Engineering、RAG、AI Agent、MCP、微调、模型部署、Transformer、AI 编程与大厂面试，从入门到生产实践。

GitHub

魔搭紫皮书｜ModelScope Cookbook：面向开发者的开源模型应用实战指南，覆盖模型选型、推理、微调、评测、RAG、Agent 与 AIGC，从跑通第一个模型到构建实际应用。

GitHub

Production LLM applications rarely receive a question nobody has asked before. Support assistants and RAG pipelines field the same intents thousands of times a day, each phrased di…

AI 点评 · 语义缓存让重复问答不再重复烧钱，LLM应用降本增效的关键基建。

MarkTechPost

A decision-oriented LLM engineering knowledge base — from Attention to production. 291 cards, 36-card path: fundamentals, RAG, Agents, and shipping.

GitHub

A decision-oriented LLM engineering knowledge base — from Attention to production. 291 cards, 36-card path: fundamentals, RAG, Agents, and shipping.

GitHub

Text-to-motion (T2M) generation maps natural language to human joint movements, aiding gaming, VR, and robotics. Retrieval-Augmented Text-to-Motion (RAG-T2M) improves generation on complex description…

HuggingFace Papers

Learn how to build a generative AI-based support operations platform on AWS that converts training videos into structured SOPs, applies Retrieval-Augmented Generation to guide tick…

AI 点评 · 用生成式AI将培训视频转为标准作业流程，并借RAG优化工单处理，展现云上客服自动化的落地范式。

AWS ML

Embedding-based code retrieval is a core component of coding agents and retrieval-augmented code generation, where retrieving correct code matters more than retrieving lexically similar code. Existing…

HuggingFace Papers

BioMedRAG introduced retrieval-augmented generation with a learned chunk scorer for biomedical information extraction. However, it relies on fixed-size chunking which can fragment semantic evidence. W…

arXiv

VetarAI 是一款运行在本地的agent桌面应用，可自由创建多个隔离项目，项目内动态编排主 Agent 与子 Agent。原生支持任务委派、可视化工作流等。全部数据保存在本地，不依赖任何云端服务。内置Rag知识库，真正降低上下文缓存读取压力，且支持自动关键词或语意索引，随时调用知识仓库的内容。

GitHub

Civil infrastructure compliance checking has long relied on engineers manually reading legacy 2D plans; however, OCR-based automation strips away the geometry and layout essential for interpreting the…

arXiv

A zero-dependency Python tool to resolve relative Markdown links and inline images as Base64 strings for RAG and Multimodal LLMs.

GitHub

As Retrieval-Augmented Generation (RAG) shifts toward diverse portfolio generation, it is stymied by two critical bottlenecks: flawed measurement of evidence utilization, and suboptimal context budget…

HuggingFace Papers

Speech-based applications pass spoken queries through automatic speech recognition (ASR) before any retrieval module, so ASR errors enter the pipeline as a fixed upstream constraint. We empirically te…

HuggingFace Papers

A retrieval-augmented QA system can return different answers after an index expansion even when its requested model identifier, prompt, retrieval policy, evidence depth, rendering, and exposed generat…

HuggingFace Papers

Input tokens are often a meaningful part of the cost of running Retrieval Augmented Generation (RAG) at scale. This post describes a query-aware context compression pattern on Amaz…

AI 点评 · 成本痛点直击，查询感知压缩为RAG规模化落地提供实用降本方案。

AWS ML

A free, self-paced 24-week AI engineering course: Python, machine learning, LLMs, RAG, fine-tuning, agents and MCP, Azure and Vertex and Bedrock, and Databricks…

GitHub

Visual document retrieval is a critical component of multimodal retrieval-augmented generation, aiming to identify query-relevant pages from document collections where evidence is distributed across t…

HuggingFace Papers

基于 Hybrid RAG 与 LangGraph 的本地代码仓库理解工具，支持中英文提问、语义检索、证据引用和多问题拆分

GitHub

基于 Hybrid RAG 与 LangGraph 的本地代码仓库理解工具，支持中英文提问、语义检索、证据引用和多问题拆分

GitHub

Parliamentary proceedings are a primary record of democratic deliberation, yet their volume and fragmentation make multi-perspective access difficult for citizens, journalists, and researchers. Applyi…

HuggingFace Papers

Dynamic Master Logic (DML) provides a hierarchical framework for representing system behavior by linking functional objectives to underlying structural elements. However, DML construction typically re…

arXiv

Learn how OneAdvanced, a UK enterprise software provider, built a UK-sovereign AI platform by self-hosting Llama 4 Maverick and Llama Guard 4 on Amazon SageMaker AI, with a RAG pip…

AWS ML

Hands-on, framework-free Colab notebooks for the AI Engineer / Forward Deployed Engineer (FDE) skill set — model APIs, structured output, tool calling, RAG, eva…

GitHub

Answering complex conditional questions using Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) remains a challenge, particularly in domain-specific contexts where general-purpose…

AI 点评 · 知识图谱自动构建加上下文检索，让复杂条件问答更可解释，直击大模型落地痛点。

arXiv

Regression testing and configuration sweeps for RAG pipelines, with the statistics to know whether a change actually helped.

GitHub

In this tutorial, we build an advanced multimodal retrieval-augmented generation pipeline with NVIDIA NeMo Retriever. We begin by configuring a Python 3.12 environment, installing…

MarkTechPost

Recent optimization studies on Retrieval-Augmented Generation (RAG) have exploited chunk-level KV cache reuse to avoid processing long retrieved contexts for higher efficiency, while significant infor…

arXiv

Recent optimization studies on Retrieval-Augmented Generation (RAG) have exploited chunk-level KV cache reuse to avoid processing long retrieved contexts for higher efficiency, while significant infor…

HuggingFace Papers

Retrieval-augmented generation (RAG) is indispensable for enhancing large language models. However, RAGs are increasingly susceptible to poisoning attacks, in which adversarial documents are injected…

HuggingFace Papers

Retrieval-augmented generation over long documents is dominated by one design: chunk the text, embed the chunks, and surface the top-k nearest neighbours of the query. We argue that for an important c…

arXiv

Learn how to build 24/7 automated AI agents & chatbots for your website, SaaS, or Shopify store with zero coding required.

GitHub

Modern Greek is absent from NVIDIA's Nemotron retrieval models and from major multilingual retrieval benchmarks, despite being important for retrieval-augmented generation (RAG) in legal, energy, fina…

arXiv

2026 年编程导航 AI 编程实战新项目，基于 Taro + React + FastAPI + DeepSeek 的 AI 闯关学习小程序，支持一句话 / 文本主题 AI 出题、闯关答题与即时讲解、联网搜索增强、RAG 私有知识库出题、AI 生图配图、微信登录与通关复盘报告。覆盖 LangChain / LangG…

GitHub

Move beyond traditional text-based parsing with PixelRAG, an end-to-end system that treats web pages and PDFs as images. This tutorial explores the complete pipeline—from rendering…

MarkTechPost

Modern Greek is absent from NVIDIA's Nemotron retrieval models and from major multilingual retrieval benchmarks, despite being important for retrieval-augmented generation (RAG) in legal, energy, fina…

HuggingFace Papers

AI 点评 · 向量检索的三大盲区，直接击中RAG技术落地痛点。

InfoQ

Retrieval-augmented generation (RAG) imposes a prefill cost proportional to retrieved context length, and -- with Transformer backbones -- a KV-cache that grows with each generated token. State-Space…

arXiv

An agentic LLM-powered knowledge assistant that enhances RAG capabilities through automated entity extraction, structured data analysis, and SQL-based reasoning…

GitHub

Sparse retrieval underpins modern search systems, from web search to retrieval-augmented generation. Existing work has introduced Learned Sparse Retrieval (LSR) to push beyond exact lexical matching t…

HuggingFace Papers

Self-hosted AI workbench for knowledge, RAG, model providers, and safely governed user-built agents. Public Preview; production Agent Runtime remains gated. 自托管…

GitHub

企业级 AI Agent 平台 | Spring Boot 3 + LangChain4j | ReAct 推理 + 多路召回 RAG + 语义缓存 + 多智能体协作

GitHub

Evidence-grounded veterinary research workbench with local RAG, bounded LLM agents, auditable tool use, citations, abstention, and human review.

GitHub

A practical guide to AI: from running your first local model to building your own agents. 52 files covering LLMs, Ollama, RAG, prompt engineering, machine learn…

GitHub

RAG ReAct Agent - A Retrieval-Augmented Generation system with ReAct (Reasoning+Acting) agent loop for intelligent question answering with multi-hop reasoning

GitHub

A zero-to-100 learning path for applied AI engineering — RAG, embeddings, vector search, agents, MCP, and the production engineering around them. 56 pages, buil…

GitHub

Enterprise multi-source RAG platform with multimodal embedding, hybrid vector/BM25 retrieval, MCP & RBAC support

GitHub