Repository History
20 repositories tagged with RAG
LazyLLM: Low-Code Development for Multi-Agent LLM Applications
LazyLLM offers a low-code development tool designed for building multi-agent LLM applications with ease. It simplifies the creation of complex AI applications, providing a streamlined workflow for rapid prototyping, data feedback, and iterative optimization. Developers can leverage its extensive features for deployment, cross-platform compatibility, and efficient model fine-tuning.
Headroom: Drastically Reduce LLM Token Usage for AI Agents
Headroom is an innovative context compression layer for AI agents, designed to significantly reduce token usage for LLMs. It achieves 60-95% fewer tokens across various inputs like tool outputs, logs, files, and RAG chunks, all while preserving answer accuracy. This powerful tool enhances efficiency and cost-effectiveness for AI interactions.
PixelRAG: Pixel-Native Search for Visual Retrieval-Augmented Generation
PixelRAG revolutionizes search by enabling pixel-native retrieval, moving beyond traditional text parsing. It renders documents as screenshots, preserving visual context like tables and charts, which is crucial for accurate answers from reader models. This allows for searching any document based on its visual appearance, not just its textual content.
GitNexus: The Zero-Server Code Intelligence Engine for Code Exploration
GitNexus is a powerful client-side knowledge graph creator that operates entirely in your browser or locally via CLI. It transforms GitHub repositories or ZIP files into interactive knowledge graphs, complete with a built-in Graph RAG Agent. This innovative engine is perfect for deep code exploration and enhancing AI agent reliability without needing any server infrastructure.
Graphify: Transform Your Codebase into a Queryable Knowledge Graph
Graphify is an innovative AI coding assistant skill that converts any codebase, documentation, and even multimedia files into a queryable knowledge graph. This powerful tool allows developers to navigate complex projects by querying relationships between components, rather than manually searching through files. It integrates seamlessly with popular AI assistants, providing deep insights and streamlining development workflows.
rag-from-scratch: Building Retrieval Augmented Generation Systems
This repository by LangChain AI offers a comprehensive guide to understanding and implementing Retrieval Augmented Generation (RAG) from scratch. It includes a series of Jupyter notebooks and an accompanying video playlist, making complex RAG concepts accessible for practical application. The resource highlights RAG's advantages over fine-tuning for factual recall in Large Language Models (LLMs).
Article-Assistant--RAG-Telegram-Bot: AI-Powered Knowledge Base via Telegram
The Article Assistant is a sophisticated RAG (Retrieval-Augmented Generation) Telegram bot designed to create interactive knowledge bases from various documents. Users can upload PDFs or provide URLs, and the bot will provide AI-powered answers with source citations. This tool efficiently transforms static content into a dynamic, queryable resource.
Qwen-Agent: A Comprehensive Framework for LLM Applications and Agent Development
Qwen-Agent is a powerful framework designed for developing advanced Large Language Model (LLM) applications, built upon Qwen models. It offers robust capabilities including function calling, a code interpreter, RAG, and multi-context protocol (MCP) support. The framework enables developers to create sophisticated AI agents with planning, tool usage, and memory features, serving as the backend for applications like Qwen Chat.
Intervo: Open-Source Conversational AI Platform for Voice and Chat
Intervo is an open-source platform designed for building, deploying, and managing advanced, goal-oriented AI agents for both voice and chat. It enables users to create complex, multi-step conversational workflows that understand user intent, perform tasks, and integrate seamlessly with existing systems. This versatile platform supports multimodal interactions, from real-time voice calls to web chat, making it suitable for a wide range of applications.
NUDGE: Lightweight Non-Parametric Embedding Fine-Tuning for Retrieval
NUDGE is a lightweight, non-parametric tool designed to fine-tune pre-trained embeddings, significantly enhancing retrieval and RAG pipelines. It operates by adjusting data embeddings directly, rather than modifying model parameters, to maximize accuracy. This approach often leads to over 10% improvement in retrieval accuracy and runs in minutes.
Vanna: Chat with Your SQL Database Using LLMs and Agentic Retrieval
Vanna is an open-source Python library that enables natural language interaction with SQL databases, leveraging Large Language Models (LLMs) for accurate text-to-SQL generation. Version 2.0 introduces enterprise-grade features like user-aware permissions, a modern web interface, and streaming responses, making it ideal for secure and scalable data analytics applications.
Cheshire Cat AI Core: An AI Agent Microservice Framework
Cheshire Cat AI Core is an open-source framework designed for building custom AI agents as microservices. It offers an API-first approach, enabling easy integration of conversational layers into applications with WebSocket chat and a customizable REST API. Key features include built-in RAG with Qdrant, extensibility via plugins, function calling, and full Dockerization for straightforward deployment.