Repo AI đang lênCập nhật hằng ngày từ GitHub

Build your own serverless AI Chat with Retrieval-Augmented-Generation using LangChain.js, TypeScript and Azure

SGPT: GPT Sentence Embeddings for Semantic Search

Neum AI is a best-in-class framework to manage the creation and synchronization of vector embeddings at large scale.

🚀 Catalyst is a C# Natural Language Processing library built for speed. Inspired by spaCy's design, it brings pre-trained models, out-of-the box support for training word and document embeddings, and flexible entity recognition models.

RAG for Local LLM, chat with PDF/doc/txt files, ChatPDF. 纯原生实现RAG功能，基于本地LLM、embedding模型、reranker模型实现，支持GraphRAG，无须安装任何第三方agent库。

End-to-end RAG system design, evaluation, and optimization. 极客时间RAG训练营，RAG 10大组件全面拆解，4个实操项目吃透 RAG 全流程。RAG的落地，往往是面向业务做RAG，而不是反过来面向RAG做业务。这就是为什么我们需要针对不同场景、不同问题做针对性的调整、优化和定制化。魔鬼全在细节中，我们深入进去探究。

An LLM-powered advanced RAG pipeline built from scratch

Use late-interaction multi-modal models such as ColPali in just a few lines of code.

This repository contains the implementation of AutoSchemaKG, a novel framework for automatic knowledge graph construction that combines schema generation via conceptualization.

[EMNLP'25] s3 - ⚡ Efficient & Effective Search Agent Training via RL for RAG (RLVR for Search with Minimal Data)

A Graph RAG System for Evidenced-based Medical Information Retrieval [ACL 2025]

Full-text and semantic search on any Postgres

Long-term memory for AI assistants. Graph + vector store that recalls decisions, relationships, and context across sessions.

Embedding-based discovery of duplicated logic for projects too large or messy to maintain reliably

Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch

This NVIDIA RAG blueprint serves as a reference solution for a foundational Retrieval Augmented Generation (RAG) pipeline.

Learn vector search with Rust and DataFusion; the C++/BusTub track is deprecated.

Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pure Swift

Fuzzy string matching, grouping, and evaluation.

Train Models Contrastively in Pytorch

The retrieval layer for production AI systems. Lightning-fast (<10ms) search without vector databases. Built for browser, edge, on-device, and cloud.

Fast, streaming indexing, query, and agentic LLM applications in Rust

Ontology-Augmented Generation for AI agents.

MemoRizz: A Python library serving as a memory layer for AI applications. Leverages popular databases and storage solutions to optimize memory usage. Provides utility classes and methods for efficient data management.

The open source Meme Search Engine and Finder. Free and built to self-host locally with Python, Ruby, and Docker.

Transform audio-visual content into navigable knowledge.

Curated List of Persian Natural Language Processing and Information Retrieval Tools and Resources

Ingest files for retrieval augmented generation (RAG) with open-source Large Language Models (LLMs), all without 3rd parties or sensitive data leaving your network.

2025 年 AI 编程助手实战项目（作者：程序员鱼皮），基于 Spring Boot 3.5 + Java 21 + LangChain4j + AI 构建智能编程学习与求职辅导机器人，覆盖 AI 大模型接入、LangChain4j 核心特性、流式对话、Prompt 工程、RAG 检索增强、向量数据库、Tool Calling 工具调用、MCP 模型上下文协议、Web 爬虫、安全防护、Vue.js 前端开发、SSE 服务端推送等企业级 AI 应用开发技术。帮助开发者掌握 AI 时代必备技能，熟悉 LangChain 框架，提升编程学习效率和求职竞争力，成为企业需要的 AI 全栈开发人才。

Framework for enhancing LLMs for RAG tasks using fine-tuning.

SQL as a Function for Rust — an embedded SQL database with a typed ORM and pluggable LMDB/RocksDB storage.

An Educational Project (step by step) to teach how to build a production-ready app for RAG application.

One-click, privacy-first exporter for Claude.ai chats — clean Markdown with artifacts and attachments, ready for Obsidian and RAG.

The prime repository for state-of-the-art Multilingual Question Answering research and development.

This repo contains the code for "VLM2Vec / MMEB" [ICLR 2025], "VLM2Vec-V2 / MMEB-V2" [TMLR 2026], and "MMEB-V3" [COLM 2026]

VectorFlow is a high volume vector embedding pipeline that ingests raw data, transforms it into vectors and writes it to a vector DB of your choice.

Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.

Chat with multiple PDFs locally

MIT-licensed, COM-free .NET libraries for creating, reading, editing, converting, rendering, and extracting Office, PDF, email, OneNote, and text formats.

🔥 Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation 🔥. Our toolkit integrates 40 pre-retrieved benchmark datasets and supports 7+ retrieval techniques, 24+ state-of-the-art Reranking models, and multiple RAG methods.

Library for faster pinned CPU <-> GPU transfer in Pytorch

企业级 AI 智能体 Agent 平台，覆盖智能对话、文档知识问答、联网搜索、RAG 检索、MCP 工具协议、Skills 扩展等完整能力。三层执行器体系、双通道混合检索、组合式切块引擎、会话记忆管理、全链路可观测，每个环节都经过深 度设计和工程化打磨。

为 Bilibili、YouTube 及本地视频提供 AI 视频摘要和知识库.AI video summarizer and knowledge base for Bilibili, YouTube and local videos.

Anything — 파일 이름이 아니라 본문으로 찾는 문서 검색기. HWP·PDF·Office 전문 검색을 오프라인으로. Windows·macOS | Offline content search across Korean documents (HWP, PDF, Office). Windows and macOS

RAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug in different LLMs, embeddings, and vector stores, and now includes seamless MCP integration to connect external tools and data sources.

On-device AI for Flutter — Gemma and other LLMs, multimodal, function calling, embeddings, RAG and speech on Android, iOS, Web, macOS, Windows and Linux.

Open-source AI Agent Customer Service Platform. Build AI agent teams with LLM orchestration, RAG knowledge base, multi-channel support, and human collaboration.

Open-source, self-hosted alternative to NotebookLM. Chat with your documents, generate audio summaries, and ground AI in your own sources—built with Supabase and N8N on a React frontend.

Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server

A Python vector database you just need - no more, no less.