π Try ApeRAG Live Demo - Experience the full platform capabilities with our hosted demo ApeRAG is a production-ready RAG (Retrieval-Augmented Generation) platform that combines Graph RAG, vector search, and full-text search with advanced AI agents. Build sophisticated AI applications with hybrid retrieval, multimodal document processing, intelligent agents, and enterprise-grade management feature
Add this skill
npx mdskills install apecloud/aperagProduction-ready RAG platform with comprehensive documentation but lacks agent-specific instructions
1# ApeRAG2[](https://archestra.ai/mcp-catalog/apecloud__aperag)34**π [Try ApeRAG Live Demo](https://rag.apecloud.com/)** - Experience the full platform capabilities with our hosted demo56789101112ApeRAG is a production-ready RAG (Retrieval-Augmented Generation) platform that combines Graph RAG, vector search, and full-text search with advanced AI agents. Build sophisticated AI applications with hybrid retrieval, multimodal document processing, intelligent agents, and enterprise-grade management features.1314ApeRAG is the best choice for building your own Knowledge Graph, Context Engineering, and deploying intelligent AI agents that can autonomously search and reason across your knowledge base.1516[ι θ―»δΈζζζ‘£](README-zh.md)1718- [Quick Start](#quick-start)19- [Key Features](#key-features)20- [Kubernetes Deployment (Recommended for Production)](#kubernetes-deployment-recommended-for-production)21- [Development](./docs/en-US/development-guide.md)22- [Build Docker Image](./docs/en-US/build-docker-image.md)23- [Acknowledgments](#acknowledgments)24- [License](#license)2526## Quick Start2728> Before installing ApeRAG, make sure your machine meets the following minimum system requirements:29>30> - CPU >= 2 Core31> - RAM >= 4 GiB32> - Docker & Docker Compose3334The easiest way to start ApeRAG is through Docker Compose. Before running the following commands, make sure that [Docker](https://docs.docker.com/get-docker/) and [Docker Compose](https://docs.docker.com/compose/install/) are installed on your machine:3536```bash37git clone https://github.com/apecloud/ApeRAG.git38cd ApeRAG39cp envs/env.template .env40docker-compose up -d --pull always41```4243After running, you can access ApeRAG in your browser at:44- **Web Interface**: http://localhost:3000/web/45- **API Documentation**: http://localhost:8000/docs4647#### MCP (Model Context Protocol) Support4849ApeRAG supports [MCP (Model Context Protocol)](https://modelcontextprotocol.io/) integration, allowing AI assistants to interact with your knowledge base directly. After starting the services, configure your MCP client with:5051```json52{53 "mcpServers": {54 "aperag-mcp": {55 "url": "https://rag.apecloud.com/mcp/",56 "headers": {57 "Authorization": "Bearer your-api-key-here"58 }59 }60 }61}62```6364**Authentication** (by priority):651. **HTTP Authorization Header** (Recommended): `Authorization: Bearer your-api-key`662. **Environment Variable** (Fallback): `APERAG_API_KEY=your-api-key`6768**Important**: Replace `https://rag.apecloud.com` with your actual ApeRAG API URL and `your-api-key-here` with a valid API key from your ApeRAG settings.6970The MCP server provides:71- **Collection browsing**: List and explore your knowledge collections72- **Hybrid search**: Search using vector, full-text, and graph methods73- **Intelligent querying**: Ask natural language questions about your documents7475#### Enhanced Document Parsing7677For enhanced document parsing capabilities, ApeRAG supports an **advanced document parsing service** powered by MinerU, which provides superior parsing for complex documents, tables, and formulas.7879<details>80<summary><strong>Enhanced Document Parsing Commands</strong></summary>8182```bash83# Enable advanced document parsing service84DOCRAY_HOST=http://aperag-docray:8639 docker compose --profile docray up -d8586# Enable advanced parsing with GPU acceleration87DOCRAY_HOST=http://aperag-docray-gpu:8639 docker compose --profile docray-gpu up -d88```8990Or use the Makefile shortcuts (requires [GNU Make](https://www.gnu.org/software/make/)):91```bash92# Enable advanced document parsing service93make compose-up WITH_DOCRAY=19495# Enable advanced parsing with GPU acceleration (recommended)96make compose-up WITH_DOCRAY=1 WITH_GPU=197```9899</details>100101#### Development & Contributing102103For developers interested in source code development, advanced configurations, or contributing to ApeRAG, please refer to our [Development Guide](./docs/en-US/development-guide.md) for detailed setup instructions.104105## Key Features106107**1. Advanced Index Types**:108Five comprehensive index types for optimal retrieval: **Vector**, **Full-text**, **Graph**, **Summary**, and **Vision** - providing multi-dimensional document understanding and search capabilities.109110**2. Intelligent AI Agents**:111Built-in AI agents with MCP (Model Context Protocol) tool support that can automatically identify relevant collections, search content intelligently, and provide web search capabilities for comprehensive question answering.112113**3. Enhanced Graph RAG with Entity Normalization**:114Deeply modified LightRAG implementation with advanced entity normalization (entity merging) for cleaner knowledge graphs and improved relational understanding.115116**4. Multimodal Processing & Vision Support**:117Complete multimodal document processing including vision capabilities for images, charts, and visual content analysis alongside traditional text processing.118119**5. Hybrid Retrieval Engine**:120Sophisticated retrieval system combining Graph RAG, vector search, full-text search, summary-based retrieval, and vision-based search for comprehensive document understanding.121122**6. MinerU Integration**:123Advanced document parsing service powered by MinerU technology, providing superior parsing for complex documents, tables, formulas, and scientific content with optional GPU acceleration.124125**7. Production-Grade Deployment**:126Full Kubernetes support with Helm charts and KubeBlocks integration for simplified deployment of production-grade databases (PostgreSQL, Redis, Qdrant, Elasticsearch, Neo4j).127128**8. Enterprise Management**:129Built-in audit logging, LLM model management, graph visualization, comprehensive document management interface, and agent workflow management.130131**9. MCP Integration**:132Full support for Model Context Protocol (MCP), enabling seamless integration with AI assistants and tools for direct knowledge base access and intelligent querying.133134**10. Developer Friendly**:135FastAPI backend, React frontend, async task processing with Celery, extensive testing, comprehensive development guides, and agent development framework for easy contribution and customization.136137## Kubernetes Deployment (Recommended for Production)138139> **Enterprise-grade deployment with high availability and scalability**140141Deploy ApeRAG to Kubernetes using our provided Helm chart. This approach offers high availability, scalability, and production-grade management capabilities.142143### Prerequisites144145* [Kubernetes cluster](https://kubernetes.io/docs/setup/) (v1.20+)146* [`kubectl`](https://kubernetes.io/docs/tasks/tools/) configured and connected to your cluster147* [Helm v3+](https://helm.sh/docs/intro/install/) installed148149### Clone the Repository150151First, clone the ApeRAG repository to get the deployment files:152153```bash154git clone https://github.com/apecloud/ApeRAG.git155cd ApeRAG156```157158### Step 1: Deploy Database Services159160ApeRAG requires PostgreSQL, Redis, Qdrant, and Elasticsearch. You have two options:161162**Option A: Use existing databases** - If you already have these databases running in your cluster, edit `deploy/aperag/values.yaml` to configure your database connection details, then skip to Step 2.163164**Option B: Deploy databases with KubeBlocks** - Use our automated database deployment (database connections are pre-configured):165166```bash167# Navigate to database deployment scripts168cd deploy/databases/169170# (Optional) Review configuration - defaults work for most cases171# edit 00-config.sh172173# Install KubeBlocks and deploy databases174bash ./01-prepare.sh # Installs KubeBlocks175bash ./02-install-database.sh # Deploys PostgreSQL, Redis, Qdrant, Elasticsearch176177# Monitor database deployment178kubectl get pods -n default179180# Return to project root for Step 2181cd ../../182```183184Wait for all database pods to be in `Running` status before proceeding.185186### Step 2: Deploy ApeRAG Application187188```bash189# If you deployed databases with KubeBlocks in Step 1, database connections are pre-configured190# If you're using existing databases, edit deploy/aperag/values.yaml with your connection details191192# Deploy ApeRAG193helm install aperag ./deploy/aperag --namespace default --create-namespace194195# Monitor ApeRAG deployment196kubectl get pods -n default -l app.kubernetes.io/instance=aperag197```198199### Configuration Options200201**Resource Requirements**: By default, includes [`doc-ray`](https://github.com/apecloud/doc-ray) service (requires 4+ CPU cores, 8GB+ RAM). To disable: set `docray.enabled: false` in `values.yaml`.202203**Advanced Settings**: Review `values.yaml` for additional configuration options including images, resources, and Ingress settings.204205### Access Your Deployment206207Once deployed, access ApeRAG using port forwarding:208209```bash210# Forward ports for quick access211kubectl port-forward svc/aperag-frontend 3000:3000 -n default212kubectl port-forward svc/aperag-api 8000:8000 -n default213214# Access in browser215# Web Interface: http://localhost:3000216# API Documentation: http://localhost:8000/docs217```218219For production environments, configure Ingress in `values.yaml` for external access.220221### Troubleshooting222223**Database Issues**: See `deploy/databases/README.md` for KubeBlocks management, credentials, and uninstall procedures.224225**Pod Status**: Check pod logs for any deployment issues:226```bash227kubectl logs -f deployment/aperag-api -n default228kubectl logs -f deployment/aperag-frontend -n default229```230231## Acknowledgments232233ApeRAG integrates and builds upon several excellent open-source projects:234235### LightRAG236The graph-based knowledge retrieval capabilities in ApeRAG are powered by a deeply modified version of [LightRAG](https://github.com/HKUDS/LightRAG):237- **Paper**: "LightRAG: Simple and Fast Retrieval-Augmented Generation" ([arXiv:2410.05779](https://arxiv.org/abs/2410.05779))238- **Authors**: Zirui Guo, Lianghao Xia, Yanhua Yu, Tu Ao, Chao Huang239- **License**: MIT License240241We have extensively modified LightRAG to support production-grade concurrent processing, distributed task queues (Celery/Prefect), and stateless operations. See our [LightRAG modifications changelog](./aperag/graph/changelog.md) for details.242243## Community244245* [Discord](https://discord.gg/FsKpXukFuB)246* [Feishu](docs%2Fen-US%2Fimages%2Ffeishu-qr-code.png)247248<img src="docs/en-US/images/feishu-qr-code.png" alt="Feishu" width="150"/>249250## Star History251252253254## License255256ApeRAG is licensed under the Apache License 2.0. See the [LICENSE](./LICENSE) file for details.
Full transparency β inspect the skill content before installing.