Tags: #rag

OpenViking is an open-source context database for AI Agents, unifying memory, resources, and skills through a file system paradigm to enable hierarchical context delivery and self-evolving capabilities.

An open-source platform for comprehensive tracing, evaluation, and optimization of LLM applications, RAG systems, and agentic workflows.

An open-source AI platform offering an advanced, feature-rich chat interface compatible with all major LLMs, enabling RAG, web search, and custom agents.

An open-source AI orchestration framework for building production-ready LLM applications with modular pipelines and agent workflows.

FastGPT is an LLM-powered platform for building AI agents and complex question-answering systems, offering out-of-the-box data processing, RAG, and visual workflow orchestration.

A production-grade, open-source platform for building and deploying AI-powered instant messaging bots across various chat platforms.

An LLM-powered framework for deep document understanding, semantic retrieval, and context-aware Q&A, leveraging RAG and advanced reasoning agents for enterprise knowledge management.

An open-source Retrieval-Augmented Generation (RAG) engine that integrates RAG with Agent capabilities to provide a superior context layer for Large Language Models (LLMs).

An open LLM devops platform for building, deploying, and managing next-generation enterprise AI applications with comprehensive features like GenAI workflow, RAG, and Agent capabilities.

An open-source, full-featured framework for building, deploying, and managing autonomous multi-agent AI applications with ease.

A user-friendly, self-hosted AI platform providing a powerful interface for interacting with various LLMs, including Ollama and OpenAI-compatible APIs, with advanced RAG capabilities.

An open-source platform for building enterprise-grade AI agents, integrating RAG, robust workflows, and multi-modal capabilities to enhance smart Q&A and automate complex business scenarios.

LightRAG is a simple and fast framework for Retrieval-Augmented Generation, designed to enhance LLM performance with external knowledge.

LlamaIndex is an open-source framework designed to build intelligent agentic applications by connecting Large Language Models (LLMs) with private or custom data sources, focusing on document understanding and OCR.

An all-in-one AI framework for semantic search, LLM orchestration, and language model workflows, powered by an embeddings database.

An all-in-one visual development platform that simplifies the creation, debugging, and deployment of AI agents using low-code/no-code approaches.

A self-hostable AI second brain that integrates with local/online LLMs to provide answers from your documents and the web, build custom agents, and automate research.

A cross-platform Markdown AI note-taking application that leverages AI to transform fragmented knowledge into organized, readable notes.

PageIndex is a vectorless, reasoning-based RAG system that builds hierarchical tree indexes for human-like, context-aware document retrieval, outperforming traditional vector-based methods.

DocsGPT is an open-source AI platform for building intelligent agents and assistants, offering private, multi-model support, deep research, and document analysis for enterprise search.

A unified Python framework for building local, private, and secure enterprise RAG pipelines using small, specialized LLMs and a comprehensive model catalog.

FlagEmbedding (BGE) is a comprehensive toolkit offering state-of-the-art embedding models for efficient search, Retrieval-Augmented Generation (RAG), and various multimodal AI applications.

A modular graph-based Retrieval-Augmented Generation (RAG) system designed to extract structured data from unstructured text using LLMs to enhance reasoning on private data.

An enterprise-grade, all-in-one AI application development framework supporting multi-vendor LLM integration, secure knowledge bases, visual workflow orchestration, and intelligent agent deployment.

An enterprise-grade, multi-tenant AI agent platform by China Unicom, offering a comprehensive suite for building intelligent agents, workflows, RAG, and managing models with a developer-friendly license.

LEANN is an innovative on-device vector database enabling private, efficient, and fast Retrieval Augmented Generation (RAG) across all your personal data with significant storage savings.

A comprehensive collection of over 80 practical examples, tutorials, and recipes for building powerful LLM-powered applications.

An open-source PDF parser for AI-ready data extraction and automated PDF accessibility remediation, offering benchmark-leading accuracy.

An idiomatic, open-source Java library simplifying the integration of Large Language Models (LLMs) into JVM applications with unified APIs and a comprehensive toolbox.

An official guide and collection of recipes for building applications with the Llama model family, covering inference, fine-tuning, and RAG.

A comprehensive, full-stack guide to Retrieval Augmented Generation (RAG) technology for large language model application development, covering theory, practice, and engineering best practices.

A comprehensive, job-oriented guide for AI Agent development, covering core technologies, practical projects, and interview preparation for LLM-related roles.

A beginner-friendly, hands-on tutorial for large language model (LLM) application development, focusing on practical skills and RAG implementation.

A repository showcasing various advanced Retrieval-Augmented Generation (RAG) techniques through detailed notebook tutorials.

A data framework designed to integrate custom data with large language models in JavaScript/TypeScript environments.

An enterprise-grade platform for easily deploying agentic RAG applications in your own cloud infrastructure, offering an alternative to hosted solutions like OpenAI's custom GPTs.

Build and customize RAG pipelines and chatbots over your data using natural language, powered by Streamlit.

A unified Ruby API to interact with various Large Language Models (LLMs) from different providers, simplifying AI integration into Ruby and Rails applications.

A free, all-in-one platform for building, evaluating, and optimizing AI systems, offering tools for RAG, agents, fine-tuning, and synthetic data generation.

An AI-powered extension for Paperless-ngx that automates document classification, smart tagging, and enables semantic search using various AI models.

A low-code MCP framework for building complex and innovative RAG pipelines, standardizing components and enabling precise orchestration.

An open-source, cloud-native vector database enabling semantic search at scale by combining vector similarity with structured filtering and AI capabilities.

An open-source, offline-deployable RAG and Agent application built with Langchain, supporting various LLMs for private, local knowledge base Q&A.

A hands-on course to learn LLMs, LLMOps, and vector databases by building, training, and deploying a real-time financial advisor LLM system.

An open-source BaaS platform that unifies hundreds of LLM models and provides comprehensive tools for developing, deploying, and managing AI-native applications and LLM-based agents.

An intelligent dialogue system leveraging RAG technology to build custom Q&A systems from diverse knowledge bases.

A ComfyUI-based framework for building comprehensive LLM agent workflows, integrating diverse AI models, tools, and social platforms.

An open-source playbook providing end-to-end, code-first tutorials for building production-grade GenAI agents, from prototype to enterprise deployment.

A production-ready RAG framework that provides modular, API-driven components and a UI to streamline the deployment and management of Retrieval Augmented Generation applications.

A comprehensive practical guide and accompanying code repository for LLM engineers, covering the full lifecycle of building, deploying, and monitoring advanced LLM and RAG applications on AWS with LLMOps best practices.

Learn to build a personalized AI assistant leveraging your 'Second Brain' knowledge base using advanced LLM, RAG, and agentic techniques with MLOps best practices.

An end-to-end AI Agent Engineering Platform providing an open-source TypeScript framework for building intelligent agents and a console for production-ready operations and observability.

An AI-native database designed for LLM applications, offering incredibly fast hybrid search across dense vector, sparse vector, tensor, and full-text data.

HelixDB is an open-source graph-vector database built in Rust, designed to simplify AI application development by unifying various data models into a single, low-latency platform.

Memvid is a serverless, single-file memory layer for AI agents, providing instant retrieval and long-term, versioned memory without complex RAG pipelines or databases.

A comprehensive learning resource providing tutorials and demos to master Milvus for building advanced AI applications with unstructured data.

A lightweight, versatile JavaScript search engine supporting full-text, vector, and hybrid search, deployable across browser, server, and edge environments, with RAG capabilities.

A framework providing ready-to-deploy templates for building scalable, high-accuracy RAG and AI enterprise search applications with live data synchronization.

A comprehensive AI development tutorial using Spring Boot 3 and Spring AI to build AI applications and autonomous agents, enhancing developers' AI skills and career competitiveness.

DeepSearcher is an open-source platform that leverages LLMs and vector databases to enable deep research, intelligent Q&A, and comprehensive reporting on private enterprise data.

An all-in-one API platform for building intelligent search, recommendations, and RAG applications with advanced semantic capabilities.

A free, hands-on course to build a production-ready LLM & RAG system, including a personalized AI replica, applying LLMOps best practices.

A comprehensive repository offering practical implementations and evaluation guidance for advanced and agentic Retrieval-Augmented Generation (RAG) techniques.

Easy Dataset is a powerful application for creating high-quality datasets for LLM fine-tuning, RAG, and model evaluation, featuring intelligent document processing and a comprehensive evaluation system.

A structured, community-driven learning platform designed to make complex applied AI concepts accessible and practical for everyone.

A comprehensive open-source project summarizing research papers, models, datasets, and applications in Prompt Engineering, Large Language Models (LLMs), and AIGC.

A comprehensive, open-source guide and resource hub for prompt engineering, context engineering, RAG, and AI Agents, designed to help developers and researchers master LLM interactions.

A comprehensive repository offering structured learning paths, practical projects, and career preparation resources for Generative AI and Machine Learning.

A comprehensive AI-native toolset for accurate document search and storage, designed to integrate complex context from visually rich and multimodal data into AI applications.

A feature-rich web GUI for ChatGPT and various LLMs, offering advanced functionalities like agents, file-based QA, web search, and finetuning with a refined user experience.

An open-source framework that automates the evaluation and optimization of Retrieval-Augmented Generation (RAG) pipelines using AutoML-style automation for specific datasets.

A collaborative, spreadsheet-like platform for building, experimenting with, and evaluating AI applications, especially those leveraging Retrieval-Augmented Generation (RAG).

ChatWiki is an AI agent and RAG knowledge base platform for WeChat official accounts, enabling workflow automation and intelligent customer service.

A private and local AI-powered desktop app for personal knowledge management, offering semantic search, automatic note linking, and Q&A on your notes.

Streamer-Sales is an AI large language model designed for live streaming sales, generating compelling product descriptions and integrating advanced features like digital human generation, RAG, TTS, ASR, and Agent capabilities.

An LLM-based professional knowledge assistant designed to provide accurate technical support in group chat scenarios without message flooding.

PySpur is a visual playground designed to accelerate the iteration, debugging, and deployment of AI agents, helping engineers overcome common challenges like prompt hell and workflow blindspots.

A C#/.NET library for efficient local execution of Large Language Models (LLMs) like LLaMA and LLAVA, leveraging llama.cpp.

BotSharp is an open-source .NET framework for building sophisticated AI multi-agent applications, enabling seamless integration of Large Language Models into enterprise business systems.

A native macOS app that allows users to chat with a local LLM, responding with information from files, folders, and websites on your Mac, ensuring privacy and offline functionality.

An end-to-end AI platform for data, model, and pipeline orchestration, offering ETL, LLM hosting, and RAG capabilities to streamline AI application development.

A graph-native platform for storing, enriching, and retrieving structured knowledge to power AI applications and intelligent agents.

AdalFlow is a PyTorch-like open-source library designed to build and automatically optimize large language model (LLM) applications, from chatbots and RAG systems to complex AI agents.

An open-source, customizable RAG UI and framework for secure, multi-modal document Q&A with various LLM support.

CocoIndex is an incremental data indexing framework that provides continuously fresh context from diverse enterprise data sources for AI agents and LLM applications.