Starred repositories
AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation
2024 CCF BDCI 赛题一 「TuGraph for AI」RAG在智能问答场景中的落地 A榜第15名知识库数据集分享。
2024 CCF BDCI 赛题一 「TuGraph for AI」RAG在智能问答场景中的落地 A榜第15名思路分享。
收录NLP竞赛策略实现、各任务baseline、相关竞赛经验贴(当前赛事、往期赛事、训练赛)、NLP会议时间、常用自媒体、GPU推荐等,持续更新中
Sample database for SQL Server, Oracle, MySQL, PostgreSQL, SQLite, DB2
This repository contains advanced LLM-based chatbots for Q&A using LLM agents, and Retrieval Augmented Generation (RAG) and with different databases. (VectorDB, GraphDB, SQLite, CSV, XLSX, etc.)
🧠 纯原生 Python 实现的 RAG 框架 | FAISS + BM25 混合检索 | 支持 Ollama / SiliconFlow | 适合新手入门学习
RAG-Fusion: multi-query generation + Reciprocal Rank Fusion for better retrieval-augmented generation. Includes evaluation harness with NFCorpus/BEIR.
A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval
ApeRAG: Production-ready GraphRAG with multi-modal indexing, AI agents, MCP support, and scalable K8s deployment
High accuracy RAG for answering questions from scientific documents with citations
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 open-source RAG-based tool for chatting with your documents.
🚀 2026届大模型算法岗实习面经 | 包含 DeepSeek/Qwen 技术报告解析、手撕 PPO/RoPE/Transformer、RLHF 核心与八股文 | 持续更新中...
这个是由清华大学基础模型研究中心主办的《2024金融行业·大模型挑战赛》复赛参赛方案
yanqiangmiffy / claude-code
Forked from ultraworkers/claw-codeClaude Code Snapshot for Research. All original source code is the property of Anthropic.
2022 WAIC 黑客松蚂蚁财富赛道:AntSQL大规模金融语义解析中文Text-to-SQL挑战赛 一位萌新的代码 嘻嘻嘻
2022 WAIC - 黑客松蚂蚁财富赛道 - AntSQL大规模金融语义解析中文Text-to-SQL挑战赛 TOP11
A-RAG: Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces. State-of-the-art RAG framework with keyword, semantic, and chunk read tools for multi-hop QA.
IRIS 是一个基于 Agentic Workflow(智能体工作流)的自动化深度调研与报告生成系统。它摒弃了传统的单向 RAG 问答模式,通过构建多节点状态机(State Machine),实现了从意图识别、路径规划、动态检索(混合/本地)、深度撰写到自我审查与局部修改的全自动闭环。
👾 下一代透明智能体架构 | Next-Gen Transparent Agent Architecture 🔍 全行为审计 | 🛡️ 两段式安全调用 | 🧠 双水位记忆 | ⏰ 心跳任务 📊 P0 级事故率降低 80% | 兼容 OpenClaw + Claude Code 技能生态
Implementation of my AI agent system for ERC 3: https://erc.timetoact-group.at
A presentation-design skill for Codex and Claude Code that turns page-structured Markdown into styled 1600x900 HTML slides, PNG renders, and exportable PPTX decks.
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
企业级 Agentic RAG 智能体 - 全链路覆盖文档解析、多路检索、意图识别、问题重写、会话记忆、MCP 工具调用与深度思考。面向真实业务场景,从 0 到 1 完整工程实现。