ZJunCher/xiaoyan-ai-dev-assistant: 基于 RAG 混合检索与多轮记忆的 AI 研发助手，支持团队知识问答，也适合新手学习 RAG 应用开发。
基于 RAG 混合检索与多轮记忆的 AI 研发助手，支持团队知识问答，也适合新手学习 RAG 应用开发。
#RAG
428 articles tagged with RAG
How I Built a RAG-Powered Conversational Assistant for Odoo ERP
Every enterprise runs on data — sales orders, invoices, inventory counts, customer records — but...
How /search and /ask Work: Local Hybrid RAG with ChromaDB + SQLite FTS5
This is the second article in a five-part series about building Llamail, a private local AI email...
Auto-Merging RAG: Hierarchical Retrieval ⛓️
🚨 The Problem: Context Fragmentation Imagine a 50-page legal contract. If you chunk it...
RAG is Not Dead - It’s Just Becoming Agent Memory
RAG is not dead. It just got promoted. For years, retrieval-augmented generation helped apps pull the...
Agents that monitor themselves: a self-auditing RAG on Tiger's Agentic Postgres
An experiment in giving an LLM agent the SQL primitives to watch its own retrieval quality. We build a tiny RAG on Tiger's Agentic Postgres stack, then expose ragvitals' drift dime...
Fully open-source RAG with pgvector + pgai + Ollama, and ragvitals watching for drift
An end-to-end open-source RAG stack on Postgres: pgvector for storage, pgai for embedding and generation inside SQL, Ollama for serving Gemma 2 and Llama 3.1 locally, and a 5-dimen...
RAG Series (13): Query Optimization — Asking Better Questions
The Same Question, Completely Different Results Vector retrieval has a fragility that's...
Traditional RAG works for simple lookups, but supply chain leaders need AI that can plan, evaluate, and synthesize evide...
Traditional RAG works for simple lookups, but supply chain leaders need AI that can plan, evaluate, and synthesize evidence. https://hackernoon.com/beyond-chat-why-enterprise-suppl...
Why Your RAG Chatbot Looks Great in Week 1 and Hallucinates by Month 2
💡 Week 1 demo → "this is amazing." Month 2 production → "why is it hallucinating?" I've seen this...
Beyond SQL: How to Build a High-Performance On-Device Vector Search Engine for Android
In the traditional world of Android development, we’ve spent decades perfecting the art of the exact...
Building a multi-tenant RAG pipeline with Postgres. Part 0: Overview
Today I want to start with a series of articles describing my experience building a multi-tenant RAG...
Avi Chawla (@_avichawla)프롬프트 엔지니어링, RAG, 컨텍스트 엔지니어링, 파인튜닝, 에이전트, LLM 배포/최적화, 안전성·평가·관측성까지 포함한 풀스택 AI 엔지니어링 로드맵을 소개합니다. 무...
Avi Chawla (@_avichawla)프롬프트 엔지니어링, RAG, 컨텍스트 엔지니어링, 파인튜닝, 에이전트, LLM 배포/최적화, 안전성·평가·관측성까지 포함한 풀스택 AI 엔지니어링 로드맵을 소개합니다. 무료 오픈소스 자료도 함께 제공되어 AI 개발자에게 유용합니다.https://x.com/_avichawla/s...
TechCrunch drops a massive new glossary to define complex terms like RAG, RLHF, and Large Language Models for everyday u...
TechCrunch drops a massive new glossary to define complex terms like RAG, RLHF, and Large Language Models for everyday users. The tech industry is pushing for total AI literacy in ...
Most RAG failures don’t crash. They silently return bad answers. I built a repair layer for that.
Most RAG tooling provides a score but fails to specify what actually went wrong. I had retrieval...
Generation 2 — RAG-Augmented Models (2022–2023)
Generation 2: RAG — The Era of Grounded Knowledge (2022–2023) In the first generation of AI, models...
Blockify Cuts RAG Corpus by 40x, Boosts Retrieval 2.3xBlockify claims 40x corpus reduction and 2.3x relevance gain over ...
Blockify Cuts RAG Corpus by 40x, Boosts Retrieval 2.3xBlockify claims 40x corpus reduction and 2.3x relevance gain over naive RAG. Open-source on GitHub, but lacks benchmark detail...
Your RAG can't answer 'why' -- GraphRAG finds what vector search misses
The question that broke my RAG pipeline I had a solid RAG setup. Embeddings, vector store,...
Beyond Vector Search: Why GraphRAG is the Next Frontier for LLMs
Beyond Vector Search: Why GraphRAG is the Next Frontier for LLMs For the past year, the...
Graphs for RAG: Knowledge Graph and GraphRAG (GraphDB)
Introduction I introduced RAG for LLM inference in the previous post in this series. As I...
A 19th Century Author Taught Me RAG.
I asked a 14 billion parameter LLM to remember a short story by Nathaniel Hawthorne and it told me it...
Show HN: Nexa-gauge – Cache/cost-aware graph-based eval for LLM and RAGNexa-gauge는 LLM, RAG, 에이전트 시스템의 생성 결과를 평가하기 위한 파이...
Show HN: Nexa-gauge – Cache/cost-aware graph-based eval for LLM and RAGNexa-gauge는 LLM, RAG, 에이전트 시스템의 생성 결과를 평가하기 위한 파이썬 패키지이자 CLI 도구로, 그래프 기반 평가 파이프라인을 통해 반복 가능한 품질 지표와 비용 추정, 캐시...
Small-to-Big RAG: Your AI Needs a Better Context 🧠
If your text chunks are too small, the AI misses the context. If they are too big, the search becomes...
You're doing RAG wrong
There's a new approach that: cuts corpus size by 40x. reduces tokens per query by 3x. improves vector...